[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M69903RG35A6K4N4KEGGXK2K":3,"skill-same:01M69903RG35A6K4N4KEGGXK2K":92},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":23,"publishedAt":46,"linkOnly":47,"markdownContent":48,"markdownBody":49,"frontMatter":50,"refName":54,"commitSha":55,"skillDirectory":56,"forksCount":57,"repositoryHtmlUrl":58,"repositoryHomepageUrl":59,"ownerHtmlUrl":60,"ownerBlogUrl":61,"ownerDescription":62,"updatedAt":63,"install":64,"resources":77},"01M69903RG35A6K4N4KEGGXK2K","align-recipe-pyproject",null,"Aligns a Python recipe's pyproject.toml with the repo's standards enforced by .github\u002Fworkflows\u002Fpython-validate-recipe.yml, plus one critical [build-system] presence check. Scope is pyproject.toml only — standalone ruff.toml \u002F .ruff.toml files (also forbidden in recipes) are caught by the CI workflow instead, not by this skill. Runs in two modes: a read-only --dry-run that reports what needs alignment, and an apply mode that rewrites pyproject.toml (and optionally manifest.yaml) using comment-preserving TOML\u002FYAML editors. Use when the user wants to \"align the recipe's pyproject.toml\", \"fix pyproject to match the repo standard\", \"check what needs changing in a recipe's pyproject\", or clean up a recipe before submitting a PR.","google\u002Fadk-recipes","google","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F1342004?v=4","01M698VYEFDM0VJBZDYYJ2T83S","Google","01M6990124CWS5627VKGSKJXRD",10626,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fadk-recipes\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Falign-recipe-pyproject\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,9,37,38,39,40,41,42,43,44,45],"align recipe pyproject","pyproject","recipe","align","files","when","mode","standalone","presence","scope","dry","critical","clean","alignment","up","only","fix","ci","workflows","workflow","github","python","2026-11-10 10:12:30",false,"---\nname: align-recipe-pyproject\ndescription: >\n  Aligns a Python recipe's pyproject.toml with the repo's standards enforced\n  by .github\u002Fworkflows\u002Fpython-validate-recipe.yml, plus one critical\n  [build-system] presence check. Scope is pyproject.toml only — standalone\n  ruff.toml \u002F .ruff.toml files (also forbidden in recipes) are caught by the\n  CI workflow instead, not by this skill. Runs in two modes: a read-only\n  --dry-run that reports what needs alignment, and an apply mode that\n  rewrites pyproject.toml (and optionally manifest.yaml) using\n  comment-preserving TOML\u002FYAML editors. Use when the user wants to \"align\n  the recipe's pyproject.toml\", \"fix pyproject to match the repo standard\",\n  \"check what needs changing in a recipe's pyproject\", or clean up a recipe\n  before submitting a PR.\nmetadata:\n  author: Google\n  license: Apache-2.0\n  version: 1.1.0\n---\n\n# Align Recipe pyproject.toml\n\nUse this skill to bring a Python recipe's `pyproject.toml` (and, when it disagrees, its `manifest.yaml` description) into conformance with the repo standard enforced by `.github\u002Fworkflows\u002Fpython-validate-recipe.yml`.\n\nScope: **`pyproject.toml` only**. Standalone `ruff.toml` \u002F `.ruff.toml` files are also forbidden in recipes but are enforced by the CI workflow (Check 7 in `python-validate-recipe.yml`) — outside this skill's concern.\n\n**Not in scope: `adk-major-current`.** The CI validator also emits a warn-only notice when a `core\u002F` recipe resolves to an older `google-adk` major. This skill deliberately does not implement it, and you should not add it. The mechanical fix — widening `\u003C2.0.0` to `\u003C3.0.0` and re-locking — produces a recipe importing a major it was never ported to, and that break surfaces at runtime rather than in any check. Crossing an ADK major is a code migration; this skill only rewrites metadata. If you are asked to \"fix the ADK notice\", port the recipe by hand.\n\n---\n\n## What This Skill Checks\n\nRuns `scripts\u002Falign_pyproject.py` against a recipe directory. Eight rules:\n\n| Rule ID | What it checks | Auto-fix |\n|---|---|---|\n| `no-local-ruff-config` | Recipe `pyproject.toml` must not declare any `[tool.ruff*]` table. Ruff config is centralized in the root `pyproject.toml`. | Yes — removes the tables. |\n| `python-version-floor` | `[project].requires-python` must **accept Python 3.11 exactly** — it must neither permit anything below (loose floors like `>=3.10`) nor exclude 3.11 by requiring higher (`>=3.12`, `~=3.12`, etc.). Per `AGENTS.md` \"Minimum python version: 3.11\" and CI in `.github\u002Fworkflows\u002Fpython-dependency-policy.yml`, which pins Python 3.11 and would otherwise emit a misleading \"lockfile is out of date\" error whose real cause is the interpreter mismatch. | Yes — rewrites the specifier so its lower bound is `>=3.11` while preserving every upper bound, exclusion, compatible-release (`~=`) ceiling, and pin (only pure `>=`\u002F`>` are dropped or replaced). Applies to BOTH failure modes (loose floors AND higher-than-min floors). If the result would still exclude 3.11 (e.g. `>=3.10,!=3.11` → `>=3.11,!=3.11`, or `~=3.12` → `>=3.11,~=3.12` == `>=3.12,\u003C4`), refuses to apply and returns `needs_input` for a human to resolve (typically: relax the ceiling, or raise the recipe with the maintainers to update CI's pinned interpreter). |\n| `project-name-matches-folder` | `[project].name` must equal the recipe's required name: the folder basename under `core\u002F`\u002F`contrib\u002F`, but `\u003Cvertical>-\u003Csolution>` under `plugins\u002F`, whose mandatory vertical namespace (`plugins\u002F\u003Cvertical>\u002F\u003Csolution>`) makes the basename non-unique — `plugins\u002Fretail\u002Fproduct-search` and `plugins\u002Fgrocery\u002Fproduct-search` would otherwise both claim `product-search`. | Yes — sets it. |\n| `description-matches-manifest` | If `[project].description` is set, it must equal `manifest.description`. Field is optional; skipped when absent. | Only with `--description-source={pyproject,manifest,delete}`. Refuses to touch description otherwise. |\n| `build-system-present` | `[build-system]` must have both `requires` and `build-backend`. Without it, `uv build` and `pip install .` fail. | **No** — backend choice is editorial. Reported for the human to fix. |\n| `default-pypi-index` | `[[tool.uv.index]]` must have an entry with `default = true` pointing at public PyPI (`https:\u002F\u002Fpypi.org\u002Fsimple[\u002F]`). Required so `uv sync` works on Google corp workstations without corp Airlock auth — see the block comment in the root `pyproject.toml` for the full rationale. | Yes when the block is entirely missing — appends it. **No** when a default entry exists but points elsewhere (custom private index, TestPyPI, mirror) — reported for the human to reconcile, since the divergence may be intentional. |\n| `stale-python-version-refs` | Scans **every text file in the recipe** for references to a Python version below the 3.11 floor. Raising `requires-python` is not a self-contained edit: the version is typically repeated in prose (`README.md`, `SKILL.md`) and in executable setup code. | **No** — report-only. Which references are stale and how to reword them is editorial. |\n| `runnability-test-in-testpaths` | If `[tool.pytest.ini_options].testpaths` is set, at least one entry must collect `tests\u002Ftest_runnability.py` (which `.github\u002Fpolicy.yml` requires every Python recipe to have). | **No** — report-only. Broadening `testpaths` changes what CI collects. |\n\n#### Why `stale-python-version-refs` exists\n\nA bootstrap script that picks an interpreter from an allowlist still\ncontaining the old floor will happily build a venv the recipe then refuses to\ninstall into:\n\n```bash\nfor py in python3.13 python3.12 python3.11 python3.10 python3; do\n# ...\n# ERROR: Package requires a different Python: 3.10.x not in '>=3.11'\n```\n\nThe scan requires a Python-ish context (`python 3.10`, `Python :: 3.10`,\n`>=3.10`) rather than matching bare digits, so a model name like\n`gemini-3.5-flash` is not a false positive. It skips lockfiles, virtualenvs,\ncaches, and binary files, and ignores `requires-python` in `pyproject.toml`\nitself (owned by `python-version-floor`, and still pre-rewrite in memory when\nthis check runs). Hits are capped at 40 in `details.hits`, but\n`details.files` always lists every affected file.\n\n### Edit safety\n\n- TOML edits go through **`tomlkit`** — comments, blank lines, and unrelated tables in `pyproject.toml` are preserved.\n- YAML edits (only when `--description-source=pyproject` overwrites `manifest.description`) go through **`ruamel.yaml`** — comments in `manifest.yaml` are preserved.\n- Files are only rewritten if at least one auto-fix actually ran. Otherwise on-disk bytes are untouched.\n- No files outside the recipe directory are ever modified. The workflow file, root `pyproject.toml`, and other recipes are safe.\n\n---\n\n## Rules for the Agent\n\n1. **Always use the script — never hand-edit `pyproject.toml` or `manifest.yaml` to perform these changes.** The script exists specifically so edits are style-preserving and reviewable via one report.\n\n2. **Ask for the recipe directory** if the user has not provided one. Do not guess. Recipe roots live under `core\u002Fpython\u002F\u003Cname>\u002F`, `contrib\u002Fpython\u002F\u003Cname>\u002F`, or `plugins\u002F\u003Cvertical>\u002F\u003Csolution>\u002F`.\n\n3. **Always start with `--dry-run`** unless the user has explicitly said \"apply\", \"fix it\", \"just do it\", or equivalent. Show them what would change before doing it.\n\n4. **Only report checks that need attention.** The script always returns every check's status, but the user does not need to see the ones that passed. Filter to `status != \"ok\"`.\n   - If **nothing** needs attention: reply with a single positive line (see the response format below). Don't list what's fine, don't build a table.\n   - If **something** needs attention: render only the non-ok checks.\n\n5. **If `description-matches-manifest` returns `needs_input`**, the descriptions in `pyproject.toml` and `manifest.yaml` disagree and the script cannot pick a winner. Present the two values side by side and ask the user to choose one of the three resolution options. Do not re-run the script until they choose.\n\n6. **If `build-system-present` returns `report_only`**, `[build-system]` is missing or incomplete. Tell the user the recipe cannot be built as a package until this is fixed, and offer them a hatchling or `uv_build` template snippet. Do **not** silently pick one.\n\n7. **If `default-pypi-index` returns `report_only`**, the recipe declares a default index that is NOT public PyPI (e.g. a private mirror, TestPyPI). The skill will not overwrite an intentional choice. Show the user the current `url` from `details.current_url` and ask whether it's deliberate. If yes, they can `# noqa`-comment it or update the repo standard; if no, they should change the URL to `https:\u002F\u002Fpypi.org\u002Fsimple\u002F`. Do not auto-rewrite.\n\n8. **If `stale-python-version-refs` returns `report_only`**, list the affected files from `details.files` and call out any **executable** ones first (`.sh`, `.py`, `Makefile`, CI YAML) — a stale interpreter allowlist in a bootstrap script is a live bug, not a docs nit, and it produces a confusing `requires a different Python` failure at install time. Prose files (`README.md`, `SKILL.md`) are lower priority but still inconsistent. Offer to update them; do not rewrite without asking, since some references are legitimately historical (\"dropped 3.10 support in v2\").\n\n9. **If `runnability-test-in-testpaths` returns `report_only`**, the recipe's `testpaths` excludes `tests\u002Ftest_runnability.py`, so a bare `uv run pytest` never runs it — the recipe looks tested while its import-smoke test silently never executes. Show `details.testpaths` and suggest adding `\"tests\"`. Do not auto-rewrite.\n\n10. **After apply mode succeeds**, remind the user to run `uv sync` in the recipe directory if the pyproject changes touched dependencies (the script emits this in `notes` when relevant).\n\n11. **Do not commit any changes.** Show the diff or file contents; let the user commit.\n\n---\n\n## Input\n\n| Field | Required | Description |\n|---|---|---|\n| `--recipe-dir` | Yes | Path to the recipe root (e.g. `core\u002Fpython\u002Fcross-session-memory`, `contrib\u002Fpython\u002Fmy-recipe`, `plugins\u002Fretail\u002Fstore-ops`). |\n| `--dry-run` | No | Report what would change without modifying any files. |\n| `--description-source` | Only when resolving a `description-matches-manifest` mismatch. Values: `pyproject`, `manifest`, `delete`. See below. | Chooses how to reconcile a description mismatch. |\n\n### `--description-source` semantics\n\n| Value | Effect |\n|---|---|\n| `pyproject` | Overwrite `manifest.description` with the value from `[project].description`. Use when pyproject is authoritative (e.g. it was updated more recently). |\n| `manifest` | Overwrite `[project].description` with the value from `manifest.description`. Use when the manifest is authoritative. |\n| `delete` | Remove `[project].description` from `pyproject.toml` entirely, so `manifest.description` becomes the single source of truth. Use when the recipe doesn't need a wheel-metadata description. |\n\nIf the descriptions already match, this flag is ignored.\n\n---\n\n## Run\n\n### Dry-run (read-only report — start here)\n\n```bash\nuv run --no-project --with tomlkit --with 'ruamel.yaml' --with packaging \\\n  python .agents\u002Fskills\u002Falign-recipe-pyproject\u002Fscripts\u002Falign_pyproject.py \\\n  --recipe-dir \u003CRECIPE_DIR> --dry-run\n```\n\nOutput: JSON on stdout. Every check produces one entry with `id`, `status` (`ok` \u002F `would_fix` \u002F `needs_input` \u002F `report_only` \u002F `error`), a human-readable `message`, and structured `details`. Exit code is always `0` in dry-run.\n\n### Apply (rewrite files)\n\n```bash\nuv run --no-project --with tomlkit --with 'ruamel.yaml' --with packaging \\\n  python .agents\u002Fskills\u002Falign-recipe-pyproject\u002Fscripts\u002Falign_pyproject.py \\\n  --recipe-dir \u003CRECIPE_DIR>\n```\n\nFixes everything the script can safely fix. Exits `0` if nothing is left unresolved, `1` otherwise (typically because `description-matches-manifest` needs `--description-source` or `build-system-present` needs a human).\n\n### Apply with description resolution\n\n```bash\nuv run --no-project --with tomlkit --with 'ruamel.yaml' --with packaging \\\n  python .agents\u002Fskills\u002Falign-recipe-pyproject\u002Fscripts\u002Falign_pyproject.py \\\n  --recipe-dir \u003CRECIPE_DIR> --description-source={pyproject|manifest|delete}\n```\n\n### Preview a description resolution (dry-run + `--description-source`)\n\n`--description-source` combines with `--dry-run`: the script reports the\n`would_fix` outcome of the chosen resolution **without writing any files**.\nUse this to show the user exactly what a given choice will do before you\napply it — the two flags are not mutually exclusive.\n\n```bash\nuv run --no-project --with tomlkit --with 'ruamel.yaml' --with packaging \\\n  python .agents\u002Fskills\u002Falign-recipe-pyproject\u002Fscripts\u002Falign_pyproject.py \\\n  --recipe-dir \u003CRECIPE_DIR> --dry-run \\\n  --description-source={pyproject|manifest|delete}\n```\n\n---\n\n## Respond\n\nFilter the report to checks with `status != \"ok\"`. Never list what's fine — the user is here to see what needs doing.\n\n### If everything passed\n\nReply with a single line, no table, no bullets. Something like:\n\n> ✓ `\u003CRECIPE_DIR>`'s pyproject.toml is fully aligned with the repo standard. No changes needed.\n\nThen stop. Do not run any further tools.\n\n### If there are things to report\n\nName the recipe directory once, then render **a single Markdown table** with these three columns:\n\n| Rule | Status | Details |\n|---|---|---|\n\n- **Rule** — the check `id`, in backticks (e.g. `` `no-local-ruff-config` ``).\n- **Status** — the raw status value (`would_fix`, `fixed`, `needs_input`, `report_only`, `error`). Do not add emoji unless the user has asked for them.\n- **Details** — a compact summary of both what's wrong and what will happen (or what the user must do), merged into one cell so the table stays 3 columns wide. Quote `from` → `to` values from `details` when present.\n\nInclude exactly one row per non-ok check. Do not include `ok` rows.\n\nStatus-specific guidance for what to put in the **Details** cell:\n\n- **`would_fix`** (dry-run) — describe the current-state problem, then say what apply would do. Include the `from` → `to` or the list of tables to be removed.\n- **`fixed`** (apply) — one-liner confirming the change (new value or list of removed tables).\n- **`needs_input`** (only `description-matches-manifest`) — the Details cell says something like `\"descriptions differ — needs --description-source={pyproject,manifest,delete}\"`. Do not put the two long descriptions inside the table. See \"Follow-up content\" below.\n- **`report_only`** (four rules can hit this: `build-system-present`, `default-pypi-index` when a non-PyPI default is declared, `stale-python-version-refs`, and `runnability-test-in-testpaths`) — the Details cell names what's missing or non-conforming (e.g. `\"[build-system] missing; recipe cannot be built as a package\"` or `\"default index is TestPyPI, not public PyPI\"`). Follow-up content goes below the table (see next section).\n- **`error`** — the Details cell shows the message verbatim; if it's very long, truncate with `…` and put the full text below.\n\n### Follow-up content below the table\n\nOnly for statuses that need extra context. Order: table first, then this content, then closing action.\n\n- **`needs_input` follow-up** — present `pyproject_description` and `manifest_description` from `details` side by side (a small nested table works well), then ask the user to pick one of `pyproject`, `manifest`, or `delete`. Do not re-run until they answer.\n- **`report_only` follow-up** — explain the impact (recipe cannot be built as a package) and paste both templates so the user can choose:\n\n  ```toml\n  # Hatchling (traditional Python packaging)\n  [build-system]\n  requires = [\"hatchling\"]\n  build-backend = \"hatchling.build\"\n\n  [tool.hatch.build.targets.wheel]\n  packages = [\"app\"]\n\n  # ---- OR ----\n\n  # uv_build (Astral's uv-native backend)\n  [build-system]\n  requires = [\"uv_build>=0.8.14,\u003C0.9.0\"]\n  build-backend = \"uv_build\"\n\n  [tool.uv.build-backend]\n  module-root = \"\"\n  module-name = \"app\"\n  ```\n\n- **`error` follow-up** — if the message was truncated in the table, print it verbatim in full below. Do not attempt to work around it.\n\n### Closing action\n\n- **Dry-run with at least one `would_fix` row** — **offer to apply the fixes yourself.** Do NOT paste the raw command as a copy-and-paste snippet for the user. Instead ask something like \"Want me to apply these fixes?\" (a yes\u002Fno question is fine; a question with clear options is nicer UX). If the user agrees, run apply mode yourself and render the result as another table (with `fixed` rows instead of `would_fix`). If the user declines, stop.\n\n- **Dry-run with only `needs_input` for `description-matches-manifest`** — after the table, show the two descriptions side by side and ask the user to pick one of `pyproject`, `manifest`, or `delete`. When they choose, run apply yourself with `--description-source=\u003Ctheir choice>` and render the resulting table. Do not offer generic \"apply\" — the flag is required.\n\n- **Dry-run with only `report_only`** (and no `would_fix` rows) — after the table, address the specific case:\n  - `build-system-present`: show the two `[build-system]` template snippets and stop. This is a manual edit; the skill does not auto-fix it.\n  - `default-pypi-index`: quote `details.current_url`, explain that this is not public PyPI, and ask whether it's intentional. If not, tell the user to change the URL to `https:\u002F\u002Fpypi.org\u002Fsimple\u002F`. Do not auto-rewrite.\n  - `stale-python-version-refs`: list `details.files`, executable files first, and offer to update them.\n  - `runnability-test-in-testpaths`: quote `details.testpaths` and suggest adding `\"tests\"`.\n\n- **Dry-run with only `error` rows** — do not offer to apply. Errors mean the script bailed before it could compute a fix; the user has to resolve the underlying issue first.\n\n- **Dry-run with a mix** (e.g. some `would_fix` + a `needs_input`) — offer to apply the fixable ones. The apply run will fix those and leave the others as-is; render the resulting table and then address the remaining statuses per the rules above.\n\n- **Apply mode with any `fixed` row** — end with the \"Next steps\" reminder (see below).\n\nDo NOT commit any changes yourself. Ever.\n\n### After apply mode\n\nIf any check has `status: fixed`, remind the user:\n\n```\nNext steps:\n  cd \u003CRECIPE_DIR> && uv sync    # if dependencies changed\n  git diff                       # review the edits before committing\n```\n\nThen stop. Do not commit. Do not run any further tools. End your turn.\n","# Align Recipe pyproject.toml\n\nUse this skill to bring a Python recipe's `pyproject.toml` (and, when it disagrees, its `manifest.yaml` description) into conformance with the repo standard enforced by `.github\u002Fworkflows\u002Fpython-validate-recipe.yml`.\n\nScope: **`pyproject.toml` only**. Standalone `ruff.toml` \u002F `.ruff.toml` files are also forbidden in recipes but are enforced by the CI workflow (Check 7 in `python-validate-recipe.yml`) — outside this skill's concern.\n\n**Not in scope: `adk-major-current`.** The CI validator also emits a warn-only notice when a `core\u002F` recipe resolves to an older `google-adk` major. This skill deliberately does not implement it, and you should not add it. The mechanical fix — widening `\u003C2.0.0` to `\u003C3.0.0` and re-locking — produces a recipe importing a major it was never ported to, and that break surfaces at runtime rather than in any check. Crossing an ADK major is a code migration; this skill only rewrites metadata. If you are asked to \"fix the ADK notice\", port the recipe by hand.\n\n---\n\n## What This Skill Checks\n\nRuns `scripts\u002Falign_pyproject.py` against a recipe directory. Eight rules:\n\n| Rule ID | What it checks | Auto-fix |\n|---|---|---|\n| `no-local-ruff-config` | Recipe `pyproject.toml` must not declare any `[tool.ruff*]` table. Ruff config is centralized in the root `pyproject.toml`. | Yes — removes the tables. |\n| `python-version-floor` | `[project].requires-python` must **accept Python 3.11 exactly** — it must neither permit anything below (loose floors like `>=3.10`) nor exclude 3.11 by requiring higher (`>=3.12`, `~=3.12`, etc.). Per `AGENTS.md` \"Minimum python version: 3.11\" and CI in `.github\u002Fworkflows\u002Fpython-dependency-policy.yml`, which pins Python 3.11 and would otherwise emit a misleading \"lockfile is out of date\" error whose real cause is the interpreter mismatch. | Yes — rewrites the specifier so its lower bound is `>=3.11` while preserving every upper bound, exclusion, compatible-release (`~=`) ceiling, and pin (only pure `>=`\u002F`>` are dropped or replaced). Applies to BOTH failure modes (loose floors AND higher-than-min floors). If the result would still exclude 3.11 (e.g. `>=3.10,!=3.11` → `>=3.11,!=3.11`, or `~=3.12` → `>=3.11,~=3.12` == `>=3.12,\u003C4`), refuses to apply and returns `needs_input` for a human to resolve (typically: relax the ceiling, or raise the recipe with the maintainers to update CI's pinned interpreter). |\n| `project-name-matches-folder` | `[project].name` must equal the recipe's required name: the folder basename under `core\u002F`\u002F`contrib\u002F`, but `\u003Cvertical>-\u003Csolution>` under `plugins\u002F`, whose mandatory vertical namespace (`plugins\u002F\u003Cvertical>\u002F\u003Csolution>`) makes the basename non-unique — `plugins\u002Fretail\u002Fproduct-search` and `plugins\u002Fgrocery\u002Fproduct-search` would otherwise both claim `product-search`. | Yes — sets it. |\n| `description-matches-manifest` | If `[project].description` is set, it must equal `manifest.description`. Field is optional; skipped when absent. | Only with `--description-source={pyproject,manifest,delete}`. Refuses to touch description otherwise. |\n| `build-system-present` | `[build-system]` must have both `requires` and `build-backend`. Without it, `uv build` and `pip install .` fail. | **No** — backend choice is editorial. Reported for the human to fix. |\n| `default-pypi-index` | `[[tool.uv.index]]` must have an entry with `default = true` pointing at public PyPI (`https:\u002F\u002Fpypi.org\u002Fsimple[\u002F]`). Required so `uv sync` works on Google corp workstations without corp Airlock auth — see the block comment in the root `pyproject.toml` for the full rationale. | Yes when the block is entirely missing — appends it. **No** when a default entry exists but points elsewhere (custom private index, TestPyPI, mirror) — reported for the human to reconcile, since the divergence may be intentional. |\n| `stale-python-version-refs` | Scans **every text file in the recipe** for references to a Python version below the 3.11 floor. Raising `requires-python` is not a self-contained edit: the version is typically repeated in prose (`README.md`, `SKILL.md`) and in executable setup code. | **No** — report-only. Which references are stale and how to reword them is editorial. |\n| `runnability-test-in-testpaths` | If `[tool.pytest.ini_options].testpaths` is set, at least one entry must collect `tests\u002Ftest_runnability.py` (which `.github\u002Fpolicy.yml` requires every Python recipe to have). | **No** — report-only. Broadening `testpaths` changes what CI collects. |\n\n#### Why `stale-python-version-refs` exists\n\nA bootstrap script that picks an interpreter from an allowlist still\ncontaining the old floor will happily build a venv the recipe then refuses to\ninstall into:\n\n```bash\nfor py in python3.13 python3.12 python3.11 python3.10 python3; do\n# ...\n# ERROR: Package requires a different Python: 3.10.x not in '>=3.11'\n```\n\nThe scan requires a Python-ish context (`python 3.10`, `Python :: 3.10`,\n`>=3.10`) rather than matching bare digits, so a model name like\n`gemini-3.5-flash` is not a false positive. It skips lockfiles, virtualenvs,\ncaches, and binary files, and ignores `requires-python` in `pyproject.toml`\nitself (owned by `python-version-floor`, and still pre-rewrite in memory when\nthis check runs). Hits are capped at 40 in `details.hits`, but\n`details.files` always lists every affected file.\n\n### Edit safety\n\n- TOML edits go through **`tomlkit`** — comments, blank lines, and unrelated tables in `pyproject.toml` are preserved.\n- YAML edits (only when `--description-source=pyproject` overwrites `manifest.description`) go through **`ruamel.yaml`** — comments in `manifest.yaml` are preserved.\n- Files are only rewritten if at least one auto-fix actually ran. Otherwise on-disk bytes are untouched.\n- No files outside the recipe directory are ever modified. The workflow file, root `pyproject.toml`, and other recipes are safe.\n\n---\n\n## Rules for the Agent\n\n1. **Always use the script — never hand-edit `pyproject.toml` or `manifest.yaml` to perform these changes.** The script exists specifically so edits are style-preserving and reviewable via one report.\n\n2. **Ask for the recipe directory** if the user has not provided one. Do not guess. Recipe roots live under `core\u002Fpython\u002F\u003Cname>\u002F`, `contrib\u002Fpython\u002F\u003Cname>\u002F`, or `plugins\u002F\u003Cvertical>\u002F\u003Csolution>\u002F`.\n\n3. **Always start with `--dry-run`** unless the user has explicitly said \"apply\", \"fix it\", \"just do it\", or equivalent. Show them what would change before doing it.\n\n4. **Only report checks that need attention.** The script always returns every check's status, but the user does not need to see the ones that passed. Filter to `status != \"ok\"`.\n   - If **nothing** needs attention: reply with a single positive line (see the response format below). Don't list what's fine, don't build a table.\n   - If **something** needs attention: render only the non-ok checks.\n\n5. **If `description-matches-manifest` returns `needs_input`**, the descriptions in `pyproject.toml` and `manifest.yaml` disagree and the script cannot pick a winner. Present the two values side by side and ask the user to choose one of the three resolution options. Do not re-run the script until they choose.\n\n6. **If `build-system-present` returns `report_only`**, `[build-system]` is missing or incomplete. Tell the user the recipe cannot be built as a package until this is fixed, and offer them a hatchling or `uv_build` template snippet. Do **not** silently pick one.\n\n7. **If `default-pypi-index` returns `report_only`**, the recipe declares a default index that is NOT public PyPI (e.g. a private mirror, TestPyPI). The skill will not overwrite an intentional choice. Show the user the current `url` from `details.current_url` and ask whether it's deliberate. If yes, they can `# noqa`-comment it or update the repo standard; if no, they should change the URL to `https:\u002F\u002Fpypi.org\u002Fsimple\u002F`. Do not auto-rewrite.\n\n8. **If `stale-python-version-refs` returns `report_only`**, list the affected files from `details.files` and call out any **executable** ones first (`.sh`, `.py`, `Makefile`, CI YAML) — a stale interpreter allowlist in a bootstrap script is a live bug, not a docs nit, and it produces a confusing `requires a different Python` failure at install time. Prose files (`README.md`, `SKILL.md`) are lower priority but still inconsistent. Offer to update them; do not rewrite without asking, since some references are legitimately historical (\"dropped 3.10 support in v2\").\n\n9. **If `runnability-test-in-testpaths` returns `report_only`**, the recipe's `testpaths` excludes `tests\u002Ftest_runnability.py`, so a bare `uv run pytest` never runs it — the recipe looks tested while its import-smoke test silently never executes. Show `details.testpaths` and suggest adding `\"tests\"`. Do not auto-rewrite.\n\n10. **After apply mode succeeds**, remind the user to run `uv sync` in the recipe directory if the pyproject changes touched dependencies (the script emits this in `notes` when relevant).\n\n11. **Do not commit any changes.** Show the diff or file contents; let the user commit.\n\n---\n\n## Input\n\n| Field | Required | Description |\n|---|---|---|\n| `--recipe-dir` | Yes | Path to the recipe root (e.g. `core\u002Fpython\u002Fcross-session-memory`, `contrib\u002Fpython\u002Fmy-recipe`, `plugins\u002Fretail\u002Fstore-ops`). |\n| `--dry-run` | No | Report what would change without modifying any files. |\n| `--description-source` | Only when resolving a `description-matches-manifest` mismatch. Values: `pyproject`, `manifest`, `delete`. See below. | Chooses how to reconcile a description mismatch. |\n\n### `--description-source` semantics\n\n| Value | Effect |\n|---|---|\n| `pyproject` | Overwrite `manifest.description` with the value from `[project].description`. Use when pyproject is authoritative (e.g. it was updated more recently). |\n| `manifest` | Overwrite `[project].description` with the value from `manifest.description`. Use when the manifest is authoritative. |\n| `delete` | Remove `[project].description` from `pyproject.toml` entirely, so `manifest.description` becomes the single source of truth. Use when the recipe doesn't need a wheel-metadata description. |\n\nIf the descriptions already match, this flag is ignored.\n\n---\n\n## Run\n\n### Dry-run (read-only report — start here)\n\n```bash\nuv run --no-project --with tomlkit --with 'ruamel.yaml' --with packaging \\\n  python .agents\u002Fskills\u002Falign-recipe-pyproject\u002Fscripts\u002Falign_pyproject.py \\\n  --recipe-dir \u003CRECIPE_DIR> --dry-run\n```\n\nOutput: JSON on stdout. Every check produces one entry with `id`, `status` (`ok` \u002F `would_fix` \u002F `needs_input` \u002F `report_only` \u002F `error`), a human-readable `message`, and structured `details`. Exit code is always `0` in dry-run.\n\n### Apply (rewrite files)\n\n```bash\nuv run --no-project --with tomlkit --with 'ruamel.yaml' --with packaging \\\n  python .agents\u002Fskills\u002Falign-recipe-pyproject\u002Fscripts\u002Falign_pyproject.py \\\n  --recipe-dir \u003CRECIPE_DIR>\n```\n\nFixes everything the script can safely fix. Exits `0` if nothing is left unresolved, `1` otherwise (typically because `description-matches-manifest` needs `--description-source` or `build-system-present` needs a human).\n\n### Apply with description resolution\n\n```bash\nuv run --no-project --with tomlkit --with 'ruamel.yaml' --with packaging \\\n  python .agents\u002Fskills\u002Falign-recipe-pyproject\u002Fscripts\u002Falign_pyproject.py \\\n  --recipe-dir \u003CRECIPE_DIR> --description-source={pyproject|manifest|delete}\n```\n\n### Preview a description resolution (dry-run + `--description-source`)\n\n`--description-source` combines with `--dry-run`: the script reports the\n`would_fix` outcome of the chosen resolution **without writing any files**.\nUse this to show the user exactly what a given choice will do before you\napply it — the two flags are not mutually exclusive.\n\n```bash\nuv run --no-project --with tomlkit --with 'ruamel.yaml' --with packaging \\\n  python .agents\u002Fskills\u002Falign-recipe-pyproject\u002Fscripts\u002Falign_pyproject.py \\\n  --recipe-dir \u003CRECIPE_DIR> --dry-run \\\n  --description-source={pyproject|manifest|delete}\n```\n\n---\n\n## Respond\n\nFilter the report to checks with `status != \"ok\"`. Never list what's fine — the user is here to see what needs doing.\n\n### If everything passed\n\nReply with a single line, no table, no bullets. Something like:\n\n> ✓ `\u003CRECIPE_DIR>`'s pyproject.toml is fully aligned with the repo standard. No changes needed.\n\nThen stop. Do not run any further tools.\n\n### If there are things to report\n\nName the recipe directory once, then render **a single Markdown table** with these three columns:\n\n| Rule | Status | Details |\n|---|---|---|\n\n- **Rule** — the check `id`, in backticks (e.g. `` `no-local-ruff-config` ``).\n- **Status** — the raw status value (`would_fix`, `fixed`, `needs_input`, `report_only`, `error`). Do not add emoji unless the user has asked for them.\n- **Details** — a compact summary of both what's wrong and what will happen (or what the user must do), merged into one cell so the table stays 3 columns wide. Quote `from` → `to` values from `details` when present.\n\nInclude exactly one row per non-ok check. Do not include `ok` rows.\n\nStatus-specific guidance for what to put in the **Details** cell:\n\n- **`would_fix`** (dry-run) — describe the current-state problem, then say what apply would do. Include the `from` → `to` or the list of tables to be removed.\n- **`fixed`** (apply) — one-liner confirming the change (new value or list of removed tables).\n- **`needs_input`** (only `description-matches-manifest`) — the Details cell says something like `\"descriptions differ — needs --description-source={pyproject,manifest,delete}\"`. Do not put the two long descriptions inside the table. See \"Follow-up content\" below.\n- **`report_only`** (four rules can hit this: `build-system-present`, `default-pypi-index` when a non-PyPI default is declared, `stale-python-version-refs`, and `runnability-test-in-testpaths`) — the Details cell names what's missing or non-conforming (e.g. `\"[build-system] missing; recipe cannot be built as a package\"` or `\"default index is TestPyPI, not public PyPI\"`). Follow-up content goes below the table (see next section).\n- **`error`** — the Details cell shows the message verbatim; if it's very long, truncate with `…` and put the full text below.\n\n### Follow-up content below the table\n\nOnly for statuses that need extra context. Order: table first, then this content, then closing action.\n\n- **`needs_input` follow-up** — present `pyproject_description` and `manifest_description` from `details` side by side (a small nested table works well), then ask the user to pick one of `pyproject`, `manifest`, or `delete`. Do not re-run until they answer.\n- **`report_only` follow-up** — explain the impact (recipe cannot be built as a package) and paste both templates so the user can choose:\n\n  ```toml\n  # Hatchling (traditional Python packaging)\n  [build-system]\n  requires = [\"hatchling\"]\n  build-backend = \"hatchling.build\"\n\n  [tool.hatch.build.targets.wheel]\n  packages = [\"app\"]\n\n  # ---- OR ----\n\n  # uv_build (Astral's uv-native backend)\n  [build-system]\n  requires = [\"uv_build>=0.8.14,\u003C0.9.0\"]\n  build-backend = \"uv_build\"\n\n  [tool.uv.build-backend]\n  module-root = \"\"\n  module-name = \"app\"\n  ```\n\n- **`error` follow-up** — if the message was truncated in the table, print it verbatim in full below. Do not attempt to work around it.\n\n### Closing action\n\n- **Dry-run with at least one `would_fix` row** — **offer to apply the fixes yourself.** Do NOT paste the raw command as a copy-and-paste snippet for the user. Instead ask something like \"Want me to apply these fixes?\" (a yes\u002Fno question is fine; a question with clear options is nicer UX). If the user agrees, run apply mode yourself and render the result as another table (with `fixed` rows instead of `would_fix`). If the user declines, stop.\n\n- **Dry-run with only `needs_input` for `description-matches-manifest`** — after the table, show the two descriptions side by side and ask the user to pick one of `pyproject`, `manifest`, or `delete`. When they choose, run apply yourself with `--description-source=\u003Ctheir choice>` and render the resulting table. Do not offer generic \"apply\" — the flag is required.\n\n- **Dry-run with only `report_only`** (and no `would_fix` rows) — after the table, address the specific case:\n  - `build-system-present`: show the two `[build-system]` template snippets and stop. This is a manual edit; the skill does not auto-fix it.\n  - `default-pypi-index`: quote `details.current_url`, explain that this is not public PyPI, and ask whether it's intentional. If not, tell the user to change the URL to `https:\u002F\u002Fpypi.org\u002Fsimple\u002F`. Do not auto-rewrite.\n  - `stale-python-version-refs`: list `details.files`, executable files first, and offer to update them.\n  - `runnability-test-in-testpaths`: quote `details.testpaths` and suggest adding `\"tests\"`.\n\n- **Dry-run with only `error` rows** — do not offer to apply. Errors mean the script bailed before it could compute a fix; the user has to resolve the underlying issue first.\n\n- **Dry-run with a mix** (e.g. some `would_fix` + a `needs_input`) — offer to apply the fixable ones. The apply run will fix those and leave the others as-is; render the resulting table and then address the remaining statuses per the rules above.\n\n- **Apply mode with any `fixed` row** — end with the \"Next steps\" reminder (see below).\n\nDo NOT commit any changes yourself. Ever.\n\n### After apply mode\n\nIf any check has `status: fixed`, remind the user:\n\n```\nNext steps:\n  cd \u003CRECIPE_DIR> && uv sync    # if dependencies changed\n  git diff                       # review the edits before committing\n```\n\nThen stop. Do not commit. Do not run any further tools. End your turn.\n",{"name":5,"metadata":51,"description":53},{"author":12,"license":15,"version":52},"1.1.0","Aligns a Python recipe's pyproject.toml with the repo's standards enforced by .github\u002Fworkflows\u002Fpython-validate-recipe.yml, plus one critical [build-system] presence check. Scope is pyproject.toml only — standalone ruff.toml \u002F .ruff.toml files (also forbidden in recipes) are caught by the CI workflow instead, not by this skill. Runs in two modes: a read-only --dry-run that reports what needs alignment, and an apply mode that rewrites pyproject.toml (and optionally manifest.yaml) using comment-preserving TOML\u002FYAML editors. Use when the user wants to \"align the recipe's pyproject.toml\", \"fix pyproject to match the repo standard\", \"check what needs changing in a recipe's pyproject\", or clean up a recipe before submitting a PR.\n","main","665f7b2a181686f2ba3c6c942e9b30a084b12ec3",".agents\u002Fskills\u002Falign-recipe-pyproject",2962,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fadk-recipes","https:\u002F\u002Fadk.dev","https:\u002F\u002Fgithub.com\u002Fgoogle","https:\u002F\u002Fopensource.google\u002F","Google ❤️ Open Source","2026-11-14 04:01:32",{"source":8,"skillName":5,"commands":65,"prompt":75,"zipAvailable":76},[66,69,72],{"tool":67,"command":68},"npx","npx skills add google\u002Fadk-recipes --skill align-recipe-pyproject",{"tool":70,"command":71},"bunx","bunx skills add google\u002Fadk-recipes --skill align-recipe-pyproject",{"tool":73,"command":74},"pnpm","pnpm dlx skills add google\u002Fadk-recipes --skill align-recipe-pyproject","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fadk-recipes\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Falign-recipe-pyproject\u002FSKILL.md",true,[78,84,88],{"path":79,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":82,"sourceHtmlUrl":83},"scripts\u002Falign_pyproject.py","SCRIPT","脚本",59876,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fadk-recipes\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Falign-recipe-pyproject\u002Fscripts\u002Falign_pyproject.py",{"path":85,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":86,"sourceHtmlUrl":87},"tests\u002Fconftest.py",919,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fadk-recipes\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Falign-recipe-pyproject\u002Ftests\u002Fconftest.py",{"path":89,"resourceType":80,"resourceTypeDesc":81,"sizeBytes":90,"sourceHtmlUrl":91},"tests\u002Ftest_align_pyproject.py",12159,"https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fadk-recipes\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Falign-recipe-pyproject\u002Ftests\u002Ftest_align_pyproject.py",[93,115,147,171,188,209],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":106,"publishedAt":46},"01M6991EKEG8XEM3VWW4VGV0ZQ","retail-virtual-tryon","Creates virtual try-on agents supporting image and video (catwalk animation) try-ons on Google Cloud (Gemini image models and Veo on Gemini Enterprise Agent Platform). Handles resource setup, user photo uploading, image\u002Fvideo generation pipelines, local testing, and evaluation.","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fadk-recipes\u002Fblob\u002Fmain\u002Fplugins\u002Fretail\u002Fskills\u002Fvirtual-tryon\u002FSKILL.md",[99,102,105],{"categoryNo":100,"categoryName":101,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":103,"categoryName":104,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[107,108,109,9,110,111,112,113,114],"retail virtual tryon","google cloud","image","testing","gemini","genai","adk","gemini enterprise agent platform",{"skillNo":116,"name":117,"nameZh":6,"description":118,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":119,"categories":120,"keywords":130,"publishedAt":46},"01M6991ABTZW7FCPREXY8GD4RG","retail-product-search","Creates product search agents with semantic search and RAG on Google Cloud (Vector Search on Gemini Enterprise Agent Platform, BigQuery, embeddings). Use when the user wants to \"build a product search agent\", \"create an e-commerce search\", \"make a shopping assistant\", \"set up semantic catalog discovery\", \"ingest products into Vector Search\", or \"deploy a retail RAG agent\". Handles the full pipeline: catalog data ingestion to BigQuery, Gemini Enterprise Agent Platform Vector Search collection setup, ADK agent scaffolding, evaluation, and Cloud Run deployment.","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fadk-recipes\u002Fblob\u002Fmain\u002Fplugins\u002Fretail\u002Fskills\u002Fproduct-search\u002FSKILL.md",[121,124,125],{"categoryNo":122,"categoryName":123,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000011","运维与部署",{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":126,"categoryName":127,"taxonomyType":128,"taxonomyTypeDesc":129},"01JBSEEDCAT000000000000031","产品经理","PROFESSION","适用职业",[131,132,133,114,113,111,134,9,108,135,29,136,137,138,38,139,140,141,142,143,144,145,146],"retail product search","product","search","assistant","pipeline","commerce","scaffolding","shopping","ingestion","collection","SET","vector","apache","run","create","rag",{"skillNo":148,"name":149,"nameZh":6,"description":150,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":151,"categories":152,"keywords":154,"publishedAt":46},"01M69918HZCYZHD7K9Y9ZSD287","routines","Use for a recurring unattended task (cron; pull data, open a PR, post a digest), or to test\u002Fdry-run a routine first. Explains authoring and testing via the routine tool.","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fadk-recipes\u002Fblob\u002Fmain\u002Fcore\u002Fpython\u002Flong-horizon-harness\u002Fhorizon\u002Fbuiltin_skills\u002Froutines\u002FSKILL.md",[153],{"categoryNo":100,"categoryName":101,"taxonomyType":21,"taxonomyTypeDesc":22},[149,34,155,156,157,158,159,160,161,162,163,164,165,166,167,168,144,169,110,170],"routine","for","post","via","authoring","digest","task","use","recurring","pr","tool","open","first","pull","test","data",{"skillNo":172,"name":173,"nameZh":6,"description":174,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":175,"categories":176,"keywords":177,"publishedAt":46},"01M699178ZDFDXEZ11DG1Y9CTF","policy","Inspect the per-workspace tool-policy overlay (.lha\u002Fpolicies.jsonl) that gates destructive or sensitive tool calls, and tell the user what to change if they want a rule added or removed.","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fadk-recipes\u002Fblob\u002Fmain\u002Fcore\u002Fpython\u002Flong-horizon-harness\u002Fhorizon\u002Fbuiltin_skills\u002Fpolicy\u002FSKILL.md",[],[173,178,179,180,181,182,183,184,185,186,165,187],"gates","overlay","tool calls","inspect","calls","jsonl","rule","user","workspace","change",{"skillNo":189,"name":190,"nameZh":6,"description":191,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":192,"categories":193,"keywords":194,"publishedAt":46},"01M69915F8591SQBA1ZHK6NDA7","google-workspace","Read\u002Fwrite Google Drive, Docs, Sheets, Gmail, Calendar, Chat, Tasks, Slides via the `gws` CLI. Needs an OAuth client or service account configured first. Use for any Google Workspace task.","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fadk-recipes\u002Fblob\u002Fmain\u002Fcore\u002Fpython\u002Flong-horizon-harness\u002Fhorizon\u002Fbuiltin_skills\u002Fgoogle-workspace\u002FSKILL.md",[],[186,195,9,196,162,197,198,199,167,200,201,202,203,204,161,156,205,206,158,207,208],"google workspace","calendar","write","read","slides","OAuth","tasks","docs","cli","gmail","sheets","client","chat","gws",{"skillNo":210,"name":211,"nameZh":6,"description":212,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":213,"categories":214,"keywords":216,"publishedAt":46},"01M69914416KTZ6Z0WD425YYJ0","find-skills","Discover\u002Finstall NEW agent skills from external sources (skills.sh). Use for capabilities you lack, e.g. \"find a skill for X\". Do NOT use to list skills you already have; see `\u003Cavailable_skills>`.","https:\u002F\u002Fgithub.com\u002Fgoogle\u002Fadk-recipes\u002Fblob\u002Fmain\u002Fcore\u002Fpython\u002Flong-horizon-harness\u002Fhorizon\u002Fbuiltin_skills\u002Ffind-skills\u002FSKILL.md",[215],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[217,218,156,219,220,221,222,223,162,224,225,226,227],"find skills","find","you","sources","discover","new agent","do","install","list","list skills","capabilities"]