[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-openai-boltz-small-molecule-adme":3,"mdc-8vn6xq-key":33,"related-repo-openai-boltz-small-molecule-adme":1101,"related-org-openai-boltz-small-molecule-adme":1224},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":11,"stars":22,"repoUrl":23,"updatedAt":24,"license":25,"forks":26,"topics":27,"repo":28,"sourceUrl":31,"mdContent":32},"boltz-small-molecule-adme","predict small molecule ADME properties","Predict Tier-1 ADME\u002FADMET for small molecules with Boltz from bare SMILES — no target, no docking. Use when the user wants solubility, permeability, or lipophilicity\u002FlogD for a molecule or list of molecules. Not for ranking molecules against a protein target (use boltz-small-molecule-screen, which already returns ADME free).",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},"openai","OpenAI","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fopenai.png",[12,16,19],{"name":13,"slug":14,"type":15},"Pharmacology","pharmacology","tag",{"name":17,"slug":18,"type":15},"Life Sciences","life-sciences",{"name":20,"slug":21,"type":15},"Chemistry","chemistry",3992,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fplugins","2026-06-30T19:00:57.102",null,465,[],{"repoUrl":23,"stars":22,"forks":26,"topics":29,"description":30},[],"OpenAI Plugins","https:\u002F\u002Fgithub.com\u002Fopenai\u002Fplugins\u002Ftree\u002FHEAD\u002Fplugins\u002Fboltz-api-cli\u002Fskills\u002Fboltz-small-molecule-adme","---\nname: boltz-small-molecule-adme\ndescription: Predict Tier-1 ADME\u002FADMET for small molecules with Boltz from bare SMILES — no target, no docking. Use when the user wants solubility, permeability, or lipophilicity\u002FlogD for a molecule or list of molecules. Not for ranking molecules against a protein target (use boltz-small-molecule-screen, which already returns ADME free).\n---\n\n## Workflow\n\nIf `boltz-api` is missing from `PATH`, use `boltz-cli-setup` for install\u002Fupdate guidance before retrying.\nIf a command reports missing or expired authentication, use `boltz-cli-setup` to start `boltz-api auth login --device-code` before retrying; do not ask permission first.\nIf the agent host sandbox blocks `boltz-api` install\u002Fauth\u002FAPI calls, use `boltz-cli-setup` to request the host sandbox bypass\u002Fescalation needed for user-wide CLI install, browser login, credential storage, temp files, or API access before retrying.\n\nUse this skill for standalone ADME triage on SMILES the user already has. No protein target is involved. If the user is also screening or docking those molecules against a target, prefer `boltz-small-molecule-screen` — it returns the same ADME block free as part of the screen.\n\n1. Normalize the molecules from raw SMILES, a CSV (auto-detect the SMILES column), `.smi`, or `.txt` into the `molecules` list. Each entry is `{smiles, id?}`; the optional `id` is echoed back as `external_id` on each result so you can map results to inputs.\n2. **Hard cap: 128 molecules per request.** If the list exceeds 128, split into batches of ≤128 and submit one request per batch (suffix the run name, for example `-b1`, `-b2`), then merge results. Never send more than 128 in one call — the API rejects it with `VALIDATION_ERROR: input.molecules must contain at most 128 items`.\n3. Author the payload YAML or JSON, run `estimate-cost`, show the USD cost, wait for explicit confirmation. ADME is priced at **$0.01 per molecule** (size-independent); `estimate-cost` returns the authoritative total — always quote it.\n4. `run` to submit and wait — ADME finishes in seconds, so it is synchronous and needs no background polling. `run` persists results locally under `--root-dir\u002F\u003Crun-name>\u002F`.\n5. Report from `\u003Coutput-root>\u002F\u003Crun-name>\u002Frun.json` → `output.molecules[]`. For each molecule show `external_id` (or `smiles`), `solubility`, `permeability`, and `lipophilicity`. The three values live under each molecule's `adme` object. Call out any molecule with `status: failed` and its `error` (an object `{code, message}`, e.g. code `adme_enumeration_failed`, message `Invalid SMILES`) — `adme` is `null` there; one bad SMILES fails only that molecule, not the batch. Read [references\u002Fresults.md](references\u002Fresults.md) for the output layout and [references\u002Fapi.md](references\u002Fapi.md) for the payload and batching details.\n\nADME values are approximate estimates for triage and ranking, not absolute measurements.\n\n## Command Pattern\n\n```bash\n# Replace placeholders with concrete absolute paths before running.\n# Use a short descriptive run name, for example: adme-\u003Clibrary>-v1\n\nboltz-api predictions:adme estimate-cost \\\n  --model adme-v1 --input @yaml:\u002F\u002F\u002Fabsolute\u002Fpath\u002Fpayload.yaml\n\n# `run` is synchronous (submit + wait + persist) and finishes in seconds — no background mode needed.\n# Claude Code: run as a normal Bash command. Codex: run as a foreground shell command; if Codex\n# returns a session_id because it is still running, poll it. Do not append \"&\" or use nohup in Codex.\nboltz-api predictions:adme run \\\n  --model adme-v1 \\\n  --idempotency-key \"\u003Crun-name>\" \\\n  --input @yaml:\u002F\u002F\u002Fabsolute\u002Fpath\u002Fpayload.yaml \\\n  --name \"\u003Crun-name>\" \\\n  --root-dir \"\u002Fabsolute\u002Fpath\u002Fboltz-experiments\" \\\n  --poll-interval-seconds 5\n# -> \u002Fabsolute\u002Fpath\u002Fboltz-experiments\u002F\u003Crun-name>\u002Frun.json  (output.molecules[].adme)\n```\n\nPayload is just a `molecules` list — the API body field name, not the direct CLI flag. `--model adme-v1` is required.\n\n## Always Do This\n\n- Keep payload field names exactly as the API body names shown in `references\u002Fapi.md` (`molecules`, each `{smiles, id?}`).\n- Pass `--model adme-v1` on every `estimate-cost`, `run`, and `start`.\n- Enforce the 128-molecule-per-request cap. Chunk larger libraries into ≤128 batches and submit each as its own run; merge the per-batch `run.json` outputs when reporting.\n- Use absolute paths for the output root and payload files. Do not `cd` into the run directory; pass the same `--root-dir` and use absolute paths so later relative paths do not drift.\n- Prefer one merged top-level payload via `--input @yaml:\u002F\u002F\u002Fabsolute\u002Fpath\u002Fpayload.yaml` or `@json:\u002F\u002F\u002Fabsolute\u002Fpath\u002Fpayload.json`. Keep `--model`, `--idempotency-key`, and `--workspace-id` top-level. Never use `@file:\u002F\u002F` or `@.\u002F`.\n- Run `estimate-cost` and show the USD total before submitting. ADME is $0.01\u002Fmolecule (size-independent); `estimate-cost` returns the authoritative total — always use it.\n- Use the same slug as both `--idempotency-key` and `--name` so re-runs resume via `.boltz-run.json`.\n- In permission-gated agents such as Claude Code, keep each Boltz call as a top-level command that starts with `boltz-api`. Prefer concrete arguments over `sh -c`, inline environment assignments, aliases, wrapper scripts, loops, or pipelines unless the user already allowed that exact command form.\n- ADME `run` is synchronous and finishes in seconds, so unlike the screen\u002Fdesign endpoints it needs no background\u002Fnon-blocking mode. In Claude Code, run it as a normal Bash call. In Codex, run it as a foreground shell command; if Codex returns a `session_id` because the command is still running, poll it. Do not append `&` or use `nohup` in Codex.\n- Do not require or accept a protein target — ADME is structure-free. If the user wants ADME *and* binding against a target, redirect to `boltz-small-molecule-screen`.\n\n## Escape Hatch\n\n- Payload reference: \u003Chttps:\u002F\u002Fapi.boltz.bio\u002Fdocs\u002Fapi\u002Fresources\u002Fpredictions\u002Fsubresources\u002Fadme\u002Fmethods\u002Fstart\u002F>\n- Guide: \u003Chttps:\u002F\u002Fapi.boltz.bio\u002Fdocs\u002Fguides\u002Fsmall-molecule-adme\u002F>\n- CLI flag names: `boltz-api predictions:adme run --help`\n\nRead [references\u002Fapi.md](references\u002Fapi.md) for the `molecules` payload shape, the per-molecule output fields, the 128-molecule cap, and error handling.\n\n## Outputs\n\nRead `\u003Coutput-root>\u002F\u003Crun-name>\u002Frun.json` and report `output.molecules[]`. There are no structure files — ADME returns scalar\u002Fcategorical values only. Read [references\u002Fresults.md](references\u002Fresults.md) for the local layout and per-molecule output fields; [references\u002Fapi.md](references\u002Fapi.md) has the full request\u002Fresponse schema.\n",{"data":34,"body":35},{"name":4,"description":6},{"type":36,"children":37},"root",[38,47,107,120,402,407,413,699,719,725,998,1004,1041,1059,1065,1095],{"type":39,"tag":40,"props":41,"children":43},"element","h2",{"id":42},"workflow",[44],{"type":45,"value":46},"text","Workflow",{"type":39,"tag":48,"props":49,"children":50},"p",{},[51,53,60,62,68,70,76,78,83,85,91,93,98,100,105],{"type":45,"value":52},"If ",{"type":39,"tag":54,"props":55,"children":57},"code",{"className":56},[],[58],{"type":45,"value":59},"boltz-api",{"type":45,"value":61}," is missing from ",{"type":39,"tag":54,"props":63,"children":65},{"className":64},[],[66],{"type":45,"value":67},"PATH",{"type":45,"value":69},", use ",{"type":39,"tag":54,"props":71,"children":73},{"className":72},[],[74],{"type":45,"value":75},"boltz-cli-setup",{"type":45,"value":77}," for install\u002Fupdate guidance before retrying.\nIf a command reports missing or expired authentication, use ",{"type":39,"tag":54,"props":79,"children":81},{"className":80},[],[82],{"type":45,"value":75},{"type":45,"value":84}," to start ",{"type":39,"tag":54,"props":86,"children":88},{"className":87},[],[89],{"type":45,"value":90},"boltz-api auth login --device-code",{"type":45,"value":92}," before retrying; do not ask permission first.\nIf the agent host sandbox blocks ",{"type":39,"tag":54,"props":94,"children":96},{"className":95},[],[97],{"type":45,"value":59},{"type":45,"value":99}," install\u002Fauth\u002FAPI calls, use ",{"type":39,"tag":54,"props":101,"children":103},{"className":102},[],[104],{"type":45,"value":75},{"type":45,"value":106}," to request the host sandbox bypass\u002Fescalation needed for user-wide CLI install, browser login, credential storage, temp files, or API access before retrying.",{"type":39,"tag":48,"props":108,"children":109},{},[110,112,118],{"type":45,"value":111},"Use this skill for standalone ADME triage on SMILES the user already has. No protein target is involved. If the user is also screening or docking those molecules against a target, prefer ",{"type":39,"tag":54,"props":113,"children":115},{"className":114},[],[116],{"type":45,"value":117},"boltz-small-molecule-screen",{"type":45,"value":119}," — it returns the same ADME block free as part of the screen.",{"type":39,"tag":121,"props":122,"children":123},"ol",{},[124,178,213,240,265],{"type":39,"tag":125,"props":126,"children":127},"li",{},[128,130,136,138,144,146,152,154,160,162,168,170,176],{"type":45,"value":129},"Normalize the molecules from raw SMILES, a CSV (auto-detect the SMILES column), ",{"type":39,"tag":54,"props":131,"children":133},{"className":132},[],[134],{"type":45,"value":135},".smi",{"type":45,"value":137},", or ",{"type":39,"tag":54,"props":139,"children":141},{"className":140},[],[142],{"type":45,"value":143},".txt",{"type":45,"value":145}," into the ",{"type":39,"tag":54,"props":147,"children":149},{"className":148},[],[150],{"type":45,"value":151},"molecules",{"type":45,"value":153}," list. Each entry is ",{"type":39,"tag":54,"props":155,"children":157},{"className":156},[],[158],{"type":45,"value":159},"{smiles, id?}",{"type":45,"value":161},"; the optional ",{"type":39,"tag":54,"props":163,"children":165},{"className":164},[],[166],{"type":45,"value":167},"id",{"type":45,"value":169}," is echoed back as ",{"type":39,"tag":54,"props":171,"children":173},{"className":172},[],[174],{"type":45,"value":175},"external_id",{"type":45,"value":177}," on each result so you can map results to inputs.",{"type":39,"tag":125,"props":179,"children":180},{},[181,187,189,195,197,203,205,211],{"type":39,"tag":182,"props":183,"children":184},"strong",{},[185],{"type":45,"value":186},"Hard cap: 128 molecules per request.",{"type":45,"value":188}," If the list exceeds 128, split into batches of ≤128 and submit one request per batch (suffix the run name, for example ",{"type":39,"tag":54,"props":190,"children":192},{"className":191},[],[193],{"type":45,"value":194},"-b1",{"type":45,"value":196},", ",{"type":39,"tag":54,"props":198,"children":200},{"className":199},[],[201],{"type":45,"value":202},"-b2",{"type":45,"value":204},"), then merge results. Never send more than 128 in one call — the API rejects it with ",{"type":39,"tag":54,"props":206,"children":208},{"className":207},[],[209],{"type":45,"value":210},"VALIDATION_ERROR: input.molecules must contain at most 128 items",{"type":45,"value":212},".",{"type":39,"tag":125,"props":214,"children":215},{},[216,218,224,226,231,233,238],{"type":45,"value":217},"Author the payload YAML or JSON, run ",{"type":39,"tag":54,"props":219,"children":221},{"className":220},[],[222],{"type":45,"value":223},"estimate-cost",{"type":45,"value":225},", show the USD cost, wait for explicit confirmation. ADME is priced at ",{"type":39,"tag":182,"props":227,"children":228},{},[229],{"type":45,"value":230},"$0.01 per molecule",{"type":45,"value":232}," (size-independent); ",{"type":39,"tag":54,"props":234,"children":236},{"className":235},[],[237],{"type":45,"value":223},{"type":45,"value":239}," returns the authoritative total — always quote it.",{"type":39,"tag":125,"props":241,"children":242},{},[243,249,251,256,258,264],{"type":39,"tag":54,"props":244,"children":246},{"className":245},[],[247],{"type":45,"value":248},"run",{"type":45,"value":250}," to submit and wait — ADME finishes in seconds, so it is synchronous and needs no background polling. ",{"type":39,"tag":54,"props":252,"children":254},{"className":253},[],[255],{"type":45,"value":248},{"type":45,"value":257}," persists results locally under ",{"type":39,"tag":54,"props":259,"children":261},{"className":260},[],[262],{"type":45,"value":263},"--root-dir\u002F\u003Crun-name>\u002F",{"type":45,"value":212},{"type":39,"tag":125,"props":266,"children":267},{},[268,270,276,278,284,286,291,293,299,301,307,308,314,316,322,324,330,332,338,340,346,348,354,356,362,364,370,372,377,379,385,387,393,395,400],{"type":45,"value":269},"Report from ",{"type":39,"tag":54,"props":271,"children":273},{"className":272},[],[274],{"type":45,"value":275},"\u003Coutput-root>\u002F\u003Crun-name>\u002Frun.json",{"type":45,"value":277}," → ",{"type":39,"tag":54,"props":279,"children":281},{"className":280},[],[282],{"type":45,"value":283},"output.molecules[]",{"type":45,"value":285},". For each molecule show ",{"type":39,"tag":54,"props":287,"children":289},{"className":288},[],[290],{"type":45,"value":175},{"type":45,"value":292}," (or ",{"type":39,"tag":54,"props":294,"children":296},{"className":295},[],[297],{"type":45,"value":298},"smiles",{"type":45,"value":300},"), ",{"type":39,"tag":54,"props":302,"children":304},{"className":303},[],[305],{"type":45,"value":306},"solubility",{"type":45,"value":196},{"type":39,"tag":54,"props":309,"children":311},{"className":310},[],[312],{"type":45,"value":313},"permeability",{"type":45,"value":315},", and ",{"type":39,"tag":54,"props":317,"children":319},{"className":318},[],[320],{"type":45,"value":321},"lipophilicity",{"type":45,"value":323},". The three values live under each molecule's ",{"type":39,"tag":54,"props":325,"children":327},{"className":326},[],[328],{"type":45,"value":329},"adme",{"type":45,"value":331}," object. Call out any molecule with ",{"type":39,"tag":54,"props":333,"children":335},{"className":334},[],[336],{"type":45,"value":337},"status: failed",{"type":45,"value":339}," and its ",{"type":39,"tag":54,"props":341,"children":343},{"className":342},[],[344],{"type":45,"value":345},"error",{"type":45,"value":347}," (an object ",{"type":39,"tag":54,"props":349,"children":351},{"className":350},[],[352],{"type":45,"value":353},"{code, message}",{"type":45,"value":355},", e.g. code ",{"type":39,"tag":54,"props":357,"children":359},{"className":358},[],[360],{"type":45,"value":361},"adme_enumeration_failed",{"type":45,"value":363},", message ",{"type":39,"tag":54,"props":365,"children":367},{"className":366},[],[368],{"type":45,"value":369},"Invalid SMILES",{"type":45,"value":371},") — ",{"type":39,"tag":54,"props":373,"children":375},{"className":374},[],[376],{"type":45,"value":329},{"type":45,"value":378}," is ",{"type":39,"tag":54,"props":380,"children":382},{"className":381},[],[383],{"type":45,"value":384},"null",{"type":45,"value":386}," there; one bad SMILES fails only that molecule, not the batch. Read ",{"type":39,"tag":388,"props":389,"children":391},"a",{"href":390},"references\u002Fresults.md",[392],{"type":45,"value":390},{"type":45,"value":394}," for the output layout and ",{"type":39,"tag":388,"props":396,"children":398},{"href":397},"references\u002Fapi.md",[399],{"type":45,"value":397},{"type":45,"value":401}," for the payload and batching details.",{"type":39,"tag":48,"props":403,"children":404},{},[405],{"type":45,"value":406},"ADME values are approximate estimates for triage and ranking, not absolute measurements.",{"type":39,"tag":40,"props":408,"children":410},{"id":409},"command-pattern",[411],{"type":45,"value":412},"Command Pattern",{"type":39,"tag":414,"props":415,"children":420},"pre",{"className":416,"code":417,"language":418,"meta":419,"style":419},"language-bash shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","# Replace placeholders with concrete absolute paths before running.\n# Use a short descriptive run name, for example: adme-\u003Clibrary>-v1\n\nboltz-api predictions:adme estimate-cost \\\n  --model adme-v1 --input @yaml:\u002F\u002F\u002Fabsolute\u002Fpath\u002Fpayload.yaml\n\n# `run` is synchronous (submit + wait + persist) and finishes in seconds — no background mode needed.\n# Claude Code: run as a normal Bash command. Codex: run as a foreground shell command; if Codex\n# returns a session_id because it is still running, poll it. Do not append \"&\" or use nohup in Codex.\nboltz-api predictions:adme run \\\n  --model adme-v1 \\\n  --idempotency-key \"\u003Crun-name>\" \\\n  --input @yaml:\u002F\u002F\u002Fabsolute\u002Fpath\u002Fpayload.yaml \\\n  --name \"\u003Crun-name>\" \\\n  --root-dir \"\u002Fabsolute\u002Fpath\u002Fboltz-experiments\" \\\n  --poll-interval-seconds 5\n# -> \u002Fabsolute\u002Fpath\u002Fboltz-experiments\u002F\u003Crun-name>\u002Frun.json  (output.molecules[].adme)\n","bash","",[421],{"type":39,"tag":54,"props":422,"children":423},{"__ignoreMap":419},[424,436,445,455,481,505,513,522,531,540,561,577,606,624,649,675,690],{"type":39,"tag":425,"props":426,"children":429},"span",{"class":427,"line":428},"line",1,[430],{"type":39,"tag":425,"props":431,"children":433},{"style":432},"--shiki-light:#90A4AE;--shiki-light-font-style:italic;--shiki-default:#546E7A;--shiki-default-font-style:italic;--shiki-dark:#676E95;--shiki-dark-font-style:italic",[434],{"type":45,"value":435},"# Replace placeholders with concrete absolute paths before running.\n",{"type":39,"tag":425,"props":437,"children":439},{"class":427,"line":438},2,[440],{"type":39,"tag":425,"props":441,"children":442},{"style":432},[443],{"type":45,"value":444},"# Use a short descriptive run name, for example: adme-\u003Clibrary>-v1\n",{"type":39,"tag":425,"props":446,"children":448},{"class":427,"line":447},3,[449],{"type":39,"tag":425,"props":450,"children":452},{"emptyLinePlaceholder":451},true,[453],{"type":45,"value":454},"\n",{"type":39,"tag":425,"props":456,"children":458},{"class":427,"line":457},4,[459,464,470,475],{"type":39,"tag":425,"props":460,"children":462},{"style":461},"--shiki-light:#E2931D;--shiki-default:#FFCB6B;--shiki-dark:#FFCB6B",[463],{"type":45,"value":59},{"type":39,"tag":425,"props":465,"children":467},{"style":466},"--shiki-light:#91B859;--shiki-default:#C3E88D;--shiki-dark:#C3E88D",[468],{"type":45,"value":469}," predictions:adme",{"type":39,"tag":425,"props":471,"children":472},{"style":466},[473],{"type":45,"value":474}," estimate-cost",{"type":39,"tag":425,"props":476,"children":478},{"style":477},"--shiki-light:#90A4AE;--shiki-default:#EEFFFF;--shiki-dark:#BABED8",[479],{"type":45,"value":480}," \\\n",{"type":39,"tag":425,"props":482,"children":484},{"class":427,"line":483},5,[485,490,495,500],{"type":39,"tag":425,"props":486,"children":487},{"style":466},[488],{"type":45,"value":489},"  --model",{"type":39,"tag":425,"props":491,"children":492},{"style":466},[493],{"type":45,"value":494}," adme-v1",{"type":39,"tag":425,"props":496,"children":497},{"style":466},[498],{"type":45,"value":499}," --input",{"type":39,"tag":425,"props":501,"children":502},{"style":466},[503],{"type":45,"value":504}," @yaml:\u002F\u002F\u002Fabsolute\u002Fpath\u002Fpayload.yaml\n",{"type":39,"tag":425,"props":506,"children":508},{"class":427,"line":507},6,[509],{"type":39,"tag":425,"props":510,"children":511},{"emptyLinePlaceholder":451},[512],{"type":45,"value":454},{"type":39,"tag":425,"props":514,"children":516},{"class":427,"line":515},7,[517],{"type":39,"tag":425,"props":518,"children":519},{"style":432},[520],{"type":45,"value":521},"# `run` is synchronous (submit + wait + persist) and finishes in seconds — no background mode needed.\n",{"type":39,"tag":425,"props":523,"children":525},{"class":427,"line":524},8,[526],{"type":39,"tag":425,"props":527,"children":528},{"style":432},[529],{"type":45,"value":530},"# Claude Code: run as a normal Bash command. Codex: run as a foreground shell command; if Codex\n",{"type":39,"tag":425,"props":532,"children":534},{"class":427,"line":533},9,[535],{"type":39,"tag":425,"props":536,"children":537},{"style":432},[538],{"type":45,"value":539},"# returns a session_id because it is still running, poll it. Do not append \"&\" or use nohup in Codex.\n",{"type":39,"tag":425,"props":541,"children":543},{"class":427,"line":542},10,[544,548,552,557],{"type":39,"tag":425,"props":545,"children":546},{"style":461},[547],{"type":45,"value":59},{"type":39,"tag":425,"props":549,"children":550},{"style":466},[551],{"type":45,"value":469},{"type":39,"tag":425,"props":553,"children":554},{"style":466},[555],{"type":45,"value":556}," run",{"type":39,"tag":425,"props":558,"children":559},{"style":477},[560],{"type":45,"value":480},{"type":39,"tag":425,"props":562,"children":564},{"class":427,"line":563},11,[565,569,573],{"type":39,"tag":425,"props":566,"children":567},{"style":466},[568],{"type":45,"value":489},{"type":39,"tag":425,"props":570,"children":571},{"style":466},[572],{"type":45,"value":494},{"type":39,"tag":425,"props":574,"children":575},{"style":477},[576],{"type":45,"value":480},{"type":39,"tag":425,"props":578,"children":580},{"class":427,"line":579},12,[581,586,592,597,602],{"type":39,"tag":425,"props":582,"children":583},{"style":466},[584],{"type":45,"value":585},"  --idempotency-key",{"type":39,"tag":425,"props":587,"children":589},{"style":588},"--shiki-light:#39ADB5;--shiki-default:#89DDFF;--shiki-dark:#89DDFF",[590],{"type":45,"value":591}," \"",{"type":39,"tag":425,"props":593,"children":594},{"style":466},[595],{"type":45,"value":596},"\u003Crun-name>",{"type":39,"tag":425,"props":598,"children":599},{"style":588},[600],{"type":45,"value":601},"\"",{"type":39,"tag":425,"props":603,"children":604},{"style":477},[605],{"type":45,"value":480},{"type":39,"tag":425,"props":607,"children":609},{"class":427,"line":608},13,[610,615,620],{"type":39,"tag":425,"props":611,"children":612},{"style":466},[613],{"type":45,"value":614},"  --input",{"type":39,"tag":425,"props":616,"children":617},{"style":466},[618],{"type":45,"value":619}," @yaml:\u002F\u002F\u002Fabsolute\u002Fpath\u002Fpayload.yaml",{"type":39,"tag":425,"props":621,"children":622},{"style":477},[623],{"type":45,"value":480},{"type":39,"tag":425,"props":625,"children":627},{"class":427,"line":626},14,[628,633,637,641,645],{"type":39,"tag":425,"props":629,"children":630},{"style":466},[631],{"type":45,"value":632},"  --name",{"type":39,"tag":425,"props":634,"children":635},{"style":588},[636],{"type":45,"value":591},{"type":39,"tag":425,"props":638,"children":639},{"style":466},[640],{"type":45,"value":596},{"type":39,"tag":425,"props":642,"children":643},{"style":588},[644],{"type":45,"value":601},{"type":39,"tag":425,"props":646,"children":647},{"style":477},[648],{"type":45,"value":480},{"type":39,"tag":425,"props":650,"children":652},{"class":427,"line":651},15,[653,658,662,667,671],{"type":39,"tag":425,"props":654,"children":655},{"style":466},[656],{"type":45,"value":657},"  --root-dir",{"type":39,"tag":425,"props":659,"children":660},{"style":588},[661],{"type":45,"value":591},{"type":39,"tag":425,"props":663,"children":664},{"style":466},[665],{"type":45,"value":666},"\u002Fabsolute\u002Fpath\u002Fboltz-experiments",{"type":39,"tag":425,"props":668,"children":669},{"style":588},[670],{"type":45,"value":601},{"type":39,"tag":425,"props":672,"children":673},{"style":477},[674],{"type":45,"value":480},{"type":39,"tag":425,"props":676,"children":678},{"class":427,"line":677},16,[679,684],{"type":39,"tag":425,"props":680,"children":681},{"style":466},[682],{"type":45,"value":683},"  --poll-interval-seconds",{"type":39,"tag":425,"props":685,"children":687},{"style":686},"--shiki-light:#F76D47;--shiki-default:#F78C6C;--shiki-dark:#F78C6C",[688],{"type":45,"value":689}," 5\n",{"type":39,"tag":425,"props":691,"children":693},{"class":427,"line":692},17,[694],{"type":39,"tag":425,"props":695,"children":696},{"style":432},[697],{"type":45,"value":698},"# -> \u002Fabsolute\u002Fpath\u002Fboltz-experiments\u002F\u003Crun-name>\u002Frun.json  (output.molecules[].adme)\n",{"type":39,"tag":48,"props":700,"children":701},{},[702,704,709,711,717],{"type":45,"value":703},"Payload is just a ",{"type":39,"tag":54,"props":705,"children":707},{"className":706},[],[708],{"type":45,"value":151},{"type":45,"value":710}," list — the API body field name, not the direct CLI flag. ",{"type":39,"tag":54,"props":712,"children":714},{"className":713},[],[715],{"type":45,"value":716},"--model adme-v1",{"type":45,"value":718}," is required.",{"type":39,"tag":40,"props":720,"children":722},{"id":721},"always-do-this",[723],{"type":45,"value":724},"Always Do This",{"type":39,"tag":726,"props":727,"children":728},"ul",{},[729,755,786,799,820,877,896,923,943,979],{"type":39,"tag":125,"props":730,"children":731},{},[732,734,739,741,746,748,753],{"type":45,"value":733},"Keep payload field names exactly as the API body names shown in ",{"type":39,"tag":54,"props":735,"children":737},{"className":736},[],[738],{"type":45,"value":397},{"type":45,"value":740}," (",{"type":39,"tag":54,"props":742,"children":744},{"className":743},[],[745],{"type":45,"value":151},{"type":45,"value":747},", each ",{"type":39,"tag":54,"props":749,"children":751},{"className":750},[],[752],{"type":45,"value":159},{"type":45,"value":754},").",{"type":39,"tag":125,"props":756,"children":757},{},[758,760,765,767,772,773,778,779,785],{"type":45,"value":759},"Pass ",{"type":39,"tag":54,"props":761,"children":763},{"className":762},[],[764],{"type":45,"value":716},{"type":45,"value":766}," on every ",{"type":39,"tag":54,"props":768,"children":770},{"className":769},[],[771],{"type":45,"value":223},{"type":45,"value":196},{"type":39,"tag":54,"props":774,"children":776},{"className":775},[],[777],{"type":45,"value":248},{"type":45,"value":315},{"type":39,"tag":54,"props":780,"children":782},{"className":781},[],[783],{"type":45,"value":784},"start",{"type":45,"value":212},{"type":39,"tag":125,"props":787,"children":788},{},[789,791,797],{"type":45,"value":790},"Enforce the 128-molecule-per-request cap. Chunk larger libraries into ≤128 batches and submit each as its own run; merge the per-batch ",{"type":39,"tag":54,"props":792,"children":794},{"className":793},[],[795],{"type":45,"value":796},"run.json",{"type":45,"value":798}," outputs when reporting.",{"type":39,"tag":125,"props":800,"children":801},{},[802,804,810,812,818],{"type":45,"value":803},"Use absolute paths for the output root and payload files. Do not ",{"type":39,"tag":54,"props":805,"children":807},{"className":806},[],[808],{"type":45,"value":809},"cd",{"type":45,"value":811}," into the run directory; pass the same ",{"type":39,"tag":54,"props":813,"children":815},{"className":814},[],[816],{"type":45,"value":817},"--root-dir",{"type":45,"value":819}," and use absolute paths so later relative paths do not drift.",{"type":39,"tag":125,"props":821,"children":822},{},[823,825,831,833,839,841,847,848,854,855,861,863,869,870,876],{"type":45,"value":824},"Prefer one merged top-level payload via ",{"type":39,"tag":54,"props":826,"children":828},{"className":827},[],[829],{"type":45,"value":830},"--input @yaml:\u002F\u002F\u002Fabsolute\u002Fpath\u002Fpayload.yaml",{"type":45,"value":832}," or ",{"type":39,"tag":54,"props":834,"children":836},{"className":835},[],[837],{"type":45,"value":838},"@json:\u002F\u002F\u002Fabsolute\u002Fpath\u002Fpayload.json",{"type":45,"value":840},". Keep ",{"type":39,"tag":54,"props":842,"children":844},{"className":843},[],[845],{"type":45,"value":846},"--model",{"type":45,"value":196},{"type":39,"tag":54,"props":849,"children":851},{"className":850},[],[852],{"type":45,"value":853},"--idempotency-key",{"type":45,"value":315},{"type":39,"tag":54,"props":856,"children":858},{"className":857},[],[859],{"type":45,"value":860},"--workspace-id",{"type":45,"value":862}," top-level. Never use ",{"type":39,"tag":54,"props":864,"children":866},{"className":865},[],[867],{"type":45,"value":868},"@file:\u002F\u002F",{"type":45,"value":832},{"type":39,"tag":54,"props":871,"children":873},{"className":872},[],[874],{"type":45,"value":875},"@.\u002F",{"type":45,"value":212},{"type":39,"tag":125,"props":878,"children":879},{},[880,882,887,889,894],{"type":45,"value":881},"Run ",{"type":39,"tag":54,"props":883,"children":885},{"className":884},[],[886],{"type":45,"value":223},{"type":45,"value":888}," and show the USD total before submitting. ADME is $0.01\u002Fmolecule (size-independent); ",{"type":39,"tag":54,"props":890,"children":892},{"className":891},[],[893],{"type":45,"value":223},{"type":45,"value":895}," returns the authoritative total — always use it.",{"type":39,"tag":125,"props":897,"children":898},{},[899,901,906,908,914,916,922],{"type":45,"value":900},"Use the same slug as both ",{"type":39,"tag":54,"props":902,"children":904},{"className":903},[],[905],{"type":45,"value":853},{"type":45,"value":907}," and ",{"type":39,"tag":54,"props":909,"children":911},{"className":910},[],[912],{"type":45,"value":913},"--name",{"type":45,"value":915}," so re-runs resume via ",{"type":39,"tag":54,"props":917,"children":919},{"className":918},[],[920],{"type":45,"value":921},".boltz-run.json",{"type":45,"value":212},{"type":39,"tag":125,"props":924,"children":925},{},[926,928,933,935,941],{"type":45,"value":927},"In permission-gated agents such as Claude Code, keep each Boltz call as a top-level command that starts with ",{"type":39,"tag":54,"props":929,"children":931},{"className":930},[],[932],{"type":45,"value":59},{"type":45,"value":934},". Prefer concrete arguments over ",{"type":39,"tag":54,"props":936,"children":938},{"className":937},[],[939],{"type":45,"value":940},"sh -c",{"type":45,"value":942},", inline environment assignments, aliases, wrapper scripts, loops, or pipelines unless the user already allowed that exact command form.",{"type":39,"tag":125,"props":944,"children":945},{},[946,948,953,955,961,963,969,971,977],{"type":45,"value":947},"ADME ",{"type":39,"tag":54,"props":949,"children":951},{"className":950},[],[952],{"type":45,"value":248},{"type":45,"value":954}," is synchronous and finishes in seconds, so unlike the screen\u002Fdesign endpoints it needs no background\u002Fnon-blocking mode. In Claude Code, run it as a normal Bash call. In Codex, run it as a foreground shell command; if Codex returns a ",{"type":39,"tag":54,"props":956,"children":958},{"className":957},[],[959],{"type":45,"value":960},"session_id",{"type":45,"value":962}," because the command is still running, poll it. Do not append ",{"type":39,"tag":54,"props":964,"children":966},{"className":965},[],[967],{"type":45,"value":968},"&",{"type":45,"value":970}," or use ",{"type":39,"tag":54,"props":972,"children":974},{"className":973},[],[975],{"type":45,"value":976},"nohup",{"type":45,"value":978}," in Codex.",{"type":39,"tag":125,"props":980,"children":981},{},[982,984,990,992,997],{"type":45,"value":983},"Do not require or accept a protein target — ADME is structure-free. If the user wants ADME ",{"type":39,"tag":985,"props":986,"children":987},"em",{},[988],{"type":45,"value":989},"and",{"type":45,"value":991}," binding against a target, redirect to ",{"type":39,"tag":54,"props":993,"children":995},{"className":994},[],[996],{"type":45,"value":117},{"type":45,"value":212},{"type":39,"tag":40,"props":999,"children":1001},{"id":1000},"escape-hatch",[1002],{"type":45,"value":1003},"Escape Hatch",{"type":39,"tag":726,"props":1005,"children":1006},{},[1007,1019,1030],{"type":39,"tag":125,"props":1008,"children":1009},{},[1010,1012],{"type":45,"value":1011},"Payload reference: ",{"type":39,"tag":388,"props":1013,"children":1017},{"href":1014,"rel":1015},"https:\u002F\u002Fapi.boltz.bio\u002Fdocs\u002Fapi\u002Fresources\u002Fpredictions\u002Fsubresources\u002Fadme\u002Fmethods\u002Fstart\u002F",[1016],"nofollow",[1018],{"type":45,"value":1014},{"type":39,"tag":125,"props":1020,"children":1021},{},[1022,1024],{"type":45,"value":1023},"Guide: ",{"type":39,"tag":388,"props":1025,"children":1028},{"href":1026,"rel":1027},"https:\u002F\u002Fapi.boltz.bio\u002Fdocs\u002Fguides\u002Fsmall-molecule-adme\u002F",[1016],[1029],{"type":45,"value":1026},{"type":39,"tag":125,"props":1031,"children":1032},{},[1033,1035],{"type":45,"value":1034},"CLI flag names: ",{"type":39,"tag":54,"props":1036,"children":1038},{"className":1037},[],[1039],{"type":45,"value":1040},"boltz-api predictions:adme run --help",{"type":39,"tag":48,"props":1042,"children":1043},{},[1044,1046,1050,1052,1057],{"type":45,"value":1045},"Read ",{"type":39,"tag":388,"props":1047,"children":1048},{"href":397},[1049],{"type":45,"value":397},{"type":45,"value":1051}," for the ",{"type":39,"tag":54,"props":1053,"children":1055},{"className":1054},[],[1056],{"type":45,"value":151},{"type":45,"value":1058}," payload shape, the per-molecule output fields, the 128-molecule cap, and error handling.",{"type":39,"tag":40,"props":1060,"children":1062},{"id":1061},"outputs",[1063],{"type":45,"value":1064},"Outputs",{"type":39,"tag":48,"props":1066,"children":1067},{},[1068,1069,1074,1076,1081,1083,1087,1089,1093],{"type":45,"value":1045},{"type":39,"tag":54,"props":1070,"children":1072},{"className":1071},[],[1073],{"type":45,"value":275},{"type":45,"value":1075}," and report ",{"type":39,"tag":54,"props":1077,"children":1079},{"className":1078},[],[1080],{"type":45,"value":283},{"type":45,"value":1082},". There are no structure files — ADME returns scalar\u002Fcategorical values only. Read ",{"type":39,"tag":388,"props":1084,"children":1085},{"href":390},[1086],{"type":45,"value":390},{"type":45,"value":1088}," for the local layout and per-molecule output fields; ",{"type":39,"tag":388,"props":1090,"children":1091},{"href":397},[1092],{"type":45,"value":397},{"type":45,"value":1094}," has the full request\u002Fresponse schema.",{"type":39,"tag":1096,"props":1097,"children":1098},"style",{},[1099],{"type":45,"value":1100},"html .light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html.light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html .default .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}html.dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}",{"items":1102,"total":1223},[1103,1121,1137,1149,1169,1191,1211],{"slug":1104,"name":1104,"fn":1105,"description":1106,"org":1107,"tags":1108,"stars":22,"repoUrl":23,"updatedAt":24},"accessibility-and-inclusive-visualization","make data visualizations accessible","Make data visualizations accessible and inclusive. Use when the user needs chart or diagram accessibility guidance, text alternatives for complex visuals, color and contrast review, keyboard support, reduced-motion behavior for animation or parallax, or an accessibility QA workflow for exported figures, UML-like diagrams, and dashboards.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1109,1112,1115,1118],{"name":1110,"slug":1111,"type":15},"Accessibility","accessibility",{"name":1113,"slug":1114,"type":15},"Charts","charts",{"name":1116,"slug":1117,"type":15},"Data Visualization","data-visualization",{"name":1119,"slug":1120,"type":15},"Design","design",{"slug":1122,"name":1122,"fn":1123,"description":1124,"org":1125,"tags":1126,"stars":22,"repoUrl":23,"updatedAt":1136},"agent-browser","automate browser interactions for agents","Browser automation CLI for AI agents. Use when the user needs to interact with websites, verify dev server output, test web apps, navigate pages, fill forms, click buttons, take screenshots, extract data, or automate any browser task. Also triggers when a dev server starts so you can verify it visually.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1127,1130,1133],{"name":1128,"slug":1129,"type":15},"Agents","agents",{"name":1131,"slug":1132,"type":15},"Browser Automation","browser-automation",{"name":1134,"slug":1135,"type":15},"Testing","testing","2026-04-06T18:41:03.44016",{"slug":1138,"name":1138,"fn":1139,"description":1140,"org":1141,"tags":1142,"stars":22,"repoUrl":23,"updatedAt":1148},"agent-browser-verify","verify dev server output with automated browser","Automated browser verification for dev servers. Triggers when a dev server starts to run a visual gut-check with agent-browser — verifies the page loads, checks for console errors, validates key UI elements, and reports pass\u002Ffail before continuing.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1143,1144,1147],{"name":1131,"slug":1132,"type":15},{"name":1145,"slug":1146,"type":15},"Local Development","local-development",{"name":1134,"slug":1135,"type":15},"2026-04-06T18:41:17.526867",{"slug":1150,"name":1150,"fn":1151,"description":1152,"org":1153,"tags":1154,"stars":22,"repoUrl":23,"updatedAt":1168},"agents-sdk","build AI agents on Cloudflare Workers","Build AI agents on Cloudflare Workers using the Agents SDK. Load when creating stateful agents, durable workflows, real-time WebSocket apps, scheduled tasks, MCP servers, or chat applications. Covers Agent class, state management, callable RPC, Workflows integration, and React hooks. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1155,1156,1159,1162,1165],{"name":1128,"slug":1129,"type":15},{"name":1157,"slug":1158,"type":15},"Cloudflare Workers","cloudflare-workers",{"name":1160,"slug":1161,"type":15},"SDK","sdk",{"name":1163,"slug":1164,"type":15},"Serverless","serverless",{"name":1166,"slug":1167,"type":15},"WebSockets","websockets","2026-04-06T18:39:51.717063",{"slug":1170,"name":1170,"fn":1171,"description":1172,"org":1173,"tags":1174,"stars":22,"repoUrl":23,"updatedAt":1190},"ai-elements","build chat UIs with AI Elements","AI Elements component library guidance — pre-built React components for AI interfaces built on shadcn\u002Fui. Use when building chat UIs, message displays, tool call rendering, streaming responses, reasoning panels, or any AI-native interface with the AI SDK.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1175,1178,1181,1184,1187],{"name":1176,"slug":1177,"type":15},"Frontend","frontend",{"name":1179,"slug":1180,"type":15},"React","react",{"name":1182,"slug":1183,"type":15},"shadcn\u002Fui","shadcn-ui",{"name":1185,"slug":1186,"type":15},"UI Components","ui-components",{"name":1188,"slug":1189,"type":15},"Vercel","vercel","2026-04-06T18:40:59.619419",{"slug":1192,"name":1192,"fn":1193,"description":1194,"org":1195,"tags":1196,"stars":22,"repoUrl":23,"updatedAt":1210},"ai-gateway","configure Vercel AI Gateway","Vercel AI Gateway expert guidance. Use when configuring model routing, provider failover, cost tracking, or managing multiple AI providers through a unified API.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1197,1200,1203,1206,1209],{"name":1198,"slug":1199,"type":15},"AI Infrastructure","ai-infrastructure",{"name":1201,"slug":1202,"type":15},"Cost Optimization","cost-optimization",{"name":1204,"slug":1205,"type":15},"LLM","llm",{"name":1207,"slug":1208,"type":15},"Performance","performance",{"name":1188,"slug":1189,"type":15},"2026-04-06T18:40:44.377464",{"slug":1212,"name":1212,"fn":1213,"description":1214,"org":1215,"tags":1216,"stars":22,"repoUrl":23,"updatedAt":1222},"ai-generation-persistence","implement persistence patterns for AI generations","AI generation persistence patterns — unique IDs, addressable URLs, database storage, and cost tracking for every LLM generation",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1217,1218,1221],{"name":1201,"slug":1202,"type":15},{"name":1219,"slug":1220,"type":15},"Database","database",{"name":1204,"slug":1205,"type":15},"2026-04-06T18:41:08.513425",600,{"items":1225,"total":1422},[1226,1247,1270,1287,1303,1320,1339,1351,1365,1379,1391,1406],{"slug":1227,"name":1227,"fn":1228,"description":1229,"org":1230,"tags":1231,"stars":1244,"repoUrl":1245,"updatedAt":1246},"prior-auth-packet-builder","build healthcare prior authorization packets","Build a concise prior authorization packet from local case files and payer policy docs.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1232,1235,1238,1241],{"name":1233,"slug":1234,"type":15},"Documents","documents",{"name":1236,"slug":1237,"type":15},"Healthcare","healthcare",{"name":1239,"slug":1240,"type":15},"Insurance","insurance",{"name":1242,"slug":1243,"type":15},"Regulatory Compliance","regulatory-compliance",28169,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fopenai-agents-python","2026-04-16T05:11:39.180399",{"slug":1248,"name":1248,"fn":1249,"description":1250,"org":1251,"tags":1252,"stars":1267,"repoUrl":1268,"updatedAt":1269},"aspnet-core","build ASP.NET Core web applications","Build, review, refactor, or architect ASP.NET Core web applications using current official guidance for .NET web development. Use when working on Blazor Web Apps, Razor Pages, MVC, Minimal APIs, controller-based Web APIs, SignalR, gRPC, middleware, dependency injection, configuration, authentication, authorization, testing, performance, deployment, or ASP.NET Core upgrades.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1253,1256,1258,1261,1264],{"name":1254,"slug":1255,"type":15},".NET","dotnet",{"name":1257,"slug":1248,"type":15},"ASP.NET Core",{"name":1259,"slug":1260,"type":15},"Blazor","blazor",{"name":1262,"slug":1263,"type":15},"C#","csharp",{"name":1265,"slug":1266,"type":15},"Web Development","web-development",23787,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fskills","2026-04-12T05:07:02.819491",{"slug":1271,"name":1271,"fn":1272,"description":1273,"org":1274,"tags":1275,"stars":1267,"repoUrl":1268,"updatedAt":1286},"chatgpt-apps","build ChatGPT Apps SDK applications","Build, scaffold, refactor, and troubleshoot ChatGPT Apps SDK applications that combine an MCP server and widget UI. Use when Codex needs to design tools, register UI resources, wire the MCP Apps bridge or ChatGPT compatibility APIs, apply Apps SDK metadata or CSP or domain settings, or produce a docs-aligned project scaffold. Prefer a docs-first workflow by invoking the openai-docs skill or OpenAI developer docs MCP tools before generating code.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1276,1279,1282,1285],{"name":1277,"slug":1278,"type":15},"Apps SDK","apps-sdk",{"name":1280,"slug":1281,"type":15},"ChatGPT","chatgpt",{"name":1283,"slug":1284,"type":15},"MCP","mcp",{"name":9,"slug":8,"type":15},"2026-04-12T05:07:05.468097",{"slug":1288,"name":1288,"fn":1289,"description":1290,"org":1291,"tags":1292,"stars":1267,"repoUrl":1268,"updatedAt":1302},"cli-creator","build CLIs from API docs","Build a composable CLI for Codex from API docs, an OpenAPI spec, existing curl examples, an SDK, a web app, an admin tool, or a local script. Use when the user wants Codex to create a command-line tool that can run from any repo, expose composable read\u002Fwrite commands, return stable JSON, manage auth, and pair with a companion skill.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1293,1296,1299],{"name":1294,"slug":1295,"type":15},"API Development","api-development",{"name":1297,"slug":1298,"type":15},"CLI","cli",{"name":1300,"slug":1301,"type":15},"Codex","codex","2026-04-12T05:07:04.132762",{"slug":1304,"name":1304,"fn":1305,"description":1306,"org":1307,"tags":1308,"stars":1267,"repoUrl":1268,"updatedAt":1319},"cloudflare-deploy","deploy projects to Cloudflare","Deploy applications and infrastructure to Cloudflare using Workers, Pages, and related platform services. Use when the user asks to deploy, host, publish, or set up a project on Cloudflare.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1309,1312,1315,1316],{"name":1310,"slug":1311,"type":15},"Cloudflare","cloudflare",{"name":1313,"slug":1314,"type":15},"Cloudflare Pages","cloudflare-pages",{"name":1157,"slug":1158,"type":15},{"name":1317,"slug":1318,"type":15},"Deployment","deployment","2026-04-12T05:07:14.275118",{"slug":1321,"name":1321,"fn":1322,"description":1323,"org":1324,"tags":1325,"stars":1267,"repoUrl":1268,"updatedAt":1338},"define-goal","define and set measurable project goals","Help the user define a concrete, measurable goal before starting work, especially when they ask to use the goal tool, create a goal, set an objective, clarify success criteria, or turn a fuzzy intention into a quantitative outcome. Use this skill for goal creation and goal refinement only; it does not manage durable snapshots, decision logs, or long-running execution artifacts.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1326,1329,1332,1335],{"name":1327,"slug":1328,"type":15},"Productivity","productivity",{"name":1330,"slug":1331,"type":15},"Project Management","project-management",{"name":1333,"slug":1334,"type":15},"Strategy","strategy",{"name":1336,"slug":1337,"type":15},"Task Management","task-management","2026-05-23T06:17:16.870838",{"slug":1340,"name":1340,"fn":1341,"description":1342,"org":1343,"tags":1344,"stars":1267,"repoUrl":1268,"updatedAt":1350},"figma","translate Figma designs into code","Use the Figma MCP server to fetch design context, screenshots, variables, and assets from Figma, and to translate Figma nodes into production code. Trigger when a task involves Figma URLs, node IDs, design-to-code implementation, or Figma MCP setup and troubleshooting.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1345,1346,1348,1349],{"name":1119,"slug":1120,"type":15},{"name":1347,"slug":1340,"type":15},"Figma",{"name":1176,"slug":1177,"type":15},{"name":1283,"slug":1284,"type":15},"2026-04-12T05:06:47.939943",{"slug":1352,"name":1352,"fn":1353,"description":1354,"org":1355,"tags":1356,"stars":1267,"repoUrl":1268,"updatedAt":1364},"figma-code-connect-components","connect Figma designs to code components","Connects Figma design components to code components using Code Connect mapping tools. Use when user says \"code connect\", \"connect this component to code\", \"map this component\", \"link component to code\", \"create code connect mapping\", or wants to establish mappings between Figma designs and code implementations. For canvas writes via `use_figma`, use `figma-use`.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1357,1358,1361,1362,1363],{"name":1119,"slug":1120,"type":15},{"name":1359,"slug":1360,"type":15},"Design System","design-system",{"name":1347,"slug":1340,"type":15},{"name":1176,"slug":1177,"type":15},{"name":1185,"slug":1186,"type":15},"2026-05-10T05:59:52.971881",{"slug":1366,"name":1366,"fn":1367,"description":1368,"org":1369,"tags":1370,"stars":1267,"repoUrl":1268,"updatedAt":1378},"figma-create-design-system-rules","generate design system rules from Figma","Generates custom design system rules for the user's codebase. Use when user says \"create design system rules\", \"generate rules for my project\", \"set up design rules\", \"customize design system guidelines\", or wants to establish project-specific conventions for Figma-to-code workflows. Requires Figma MCP server connection.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1371,1372,1373,1376,1377],{"name":1119,"slug":1120,"type":15},{"name":1359,"slug":1360,"type":15},{"name":1374,"slug":1375,"type":15},"Documentation","documentation",{"name":1347,"slug":1340,"type":15},{"name":1176,"slug":1177,"type":15},"2026-05-16T06:07:47.821474",{"slug":1380,"name":1380,"fn":1381,"description":1382,"org":1383,"tags":1384,"stars":1267,"repoUrl":1268,"updatedAt":1390},"figma-implement-design","translate Figma designs into application code","Translates Figma designs into production-ready application code with 1:1 visual fidelity. Use when implementing UI code from Figma files, when user mentions \"implement design\", \"generate code\", \"implement component\", provides Figma URLs, or asks to build components matching Figma specs. For Figma canvas writes via `use_figma`, use `figma-use`.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1385,1386,1387,1388,1389],{"name":1119,"slug":1120,"type":15},{"name":1347,"slug":1340,"type":15},{"name":1176,"slug":1177,"type":15},{"name":1185,"slug":1186,"type":15},{"name":1265,"slug":1266,"type":15},"2026-05-16T06:07:40.583615",{"slug":1392,"name":1392,"fn":1393,"description":1394,"org":1395,"tags":1396,"stars":1267,"repoUrl":1268,"updatedAt":1405},"hatch-pet","create animated pets for Codex","Create, repair, validate, visually QA, and package Codex-compatible animated pets and pet spritesheets from character art, generated images, company or prospect brand cues, or visual references. Use when a user wants a lightweight-worker Codex pet workflow, a non-pixel custom pet style, a prospect or company mascot pet, or a full 8x9 animated pet atlas with transparent unused cells, QA contact sheets, and pet.json packaging. This skill composes the installed $imagegen system skill for visual generation and uses bundled scripts for deterministic spritesheet assembly.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1397,1400,1401,1404],{"name":1398,"slug":1399,"type":15},"Animation","animation",{"name":1300,"slug":1301,"type":15},{"name":1402,"slug":1403,"type":15},"Creative","creative",{"name":1119,"slug":1120,"type":15},"2026-05-02T05:31:48.48485",{"slug":1407,"name":1407,"fn":1408,"description":1409,"org":1410,"tags":1411,"stars":1267,"repoUrl":1268,"updatedAt":1421},"imagegen","generate and edit raster images","Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output should be a bitmap asset rather than repo-native code or vector. Do not use when the task is better handled by editing existing SVG\u002Fvector\u002Fcode-native assets, extending an established icon or logo system, or building the visual directly in HTML\u002FCSS\u002Fcanvas.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1412,1413,1414,1417,1420],{"name":1402,"slug":1403,"type":15},{"name":1119,"slug":1120,"type":15},{"name":1415,"slug":1416,"type":15},"Image Generation","image-generation",{"name":1418,"slug":1419,"type":15},"Images","images",{"name":9,"slug":8,"type":15},"2026-05-15T06:23:24.312127",675]