[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7DAKHKEQBKSCMSTD7993K5G":3,"skill-same:01M7DAKHKEQBKSCMSTD7993K5G":47},{"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":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":32,"install":33,"resources":46},"01M7DAKHKEQBKSCMSTD7993K5G","code-check",null,"Lint Python code after changes. Use after editing .py files, when the user mentions lint errors, ruff warnings, import problems or code quality, or before commits and PRs. Auto-fixes the mechanical findings first, then surfaces the residue for hand-fixing.","LNSD\u002Florecraft","LNSD","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F3949095?v=4","01M7DAK7ETP75C8S8PT783SWSP","Lorenzo Delgado","01M7DAK7FBVXE30743ZG437MTN",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FLNSD\u002Florecraft\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fcode-check\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: code-check\ndescription: Lint Python code after changes. Use after editing .py files, when the user mentions lint errors, ruff warnings, import problems or code quality, or before commits and PRs. Auto-fixes the mechanical findings first, then surfaces the residue for hand-fixing.\ncompatibility: Requires the just task runner and uv. ruff is invoked through the project environment rather than a system install. Optionally uses JetBrains IDE diagnostics through the ide-index MCP server, which is not required.\nallowed-tools: Bash(just check *) Bash(just check-fix *) mcp__ide-index__ide_diagnostics\n---\n\n# Code Checking Skill\n\nLinting for this repository. Python has no compile step, so there is no `check` stage separate from\nthe linter: **ruff is the whole funnel**, and it runs over the entire repository in about a second.\n\nThat is the important difference from a compiled workspace. There is no per-package command to prefer\nand no blast-radius escalation to reason about, because the cheap command is already the complete\none. Lint everything, every time.\n\n## When to Use This Skill\n\nUse this skill when you need to:\n- Validate Python code after making changes\n- Surface unused imports, undefined names, import-order problems, or bugbear findings\n- Ensure code quality before a commit or PR\n\n## Command Selection: Two Passes\n\n```\nStage 0 (optional)              Stage 1 — mandatory\nIDE diagnostics            →    just check-fix    →    just check\n(mcp__ide-index__*)             (auto-apply)           (residue, hand-fix)\n```\n\nRun `check-fix` before `check`. Reversing them means reading a report of findings a tool was about to\nfix for you.\n\n## Stage 0 — IDE Diagnostics (Optional Fast Path)\n\nIf the session exposes the `ide-index` MCP server and the project is open in a JetBrains IDE,\n`mcp__ide-index__ide_diagnostics` returns diagnostics already computed in the background, per file.\nIt catches things ruff does not — unresolved attributes, type mismatches the annotations imply.\n\nProbe it once. If it errors or is unavailable, that is normal: skip to Stage 1 and do not treat the\nabsence as a failure. **Stage 0 is advisory and never terminal** — Stage 1 is mandatory regardless,\nbecause the IDE index may be stale and ruff enforces rules the IDE does not know about.\n\n## Available Commands\n\n### Check with auto-fix\n```bash\njust check-fix [EXTRA_FLAGS]\n```\nRuns `ruff check . --fix`, rewriting every finding ruff can fix safely — unused imports, import\nordering, and similar. This is the **first** pass.\n\n### Check without fixing\n```bash\njust check [EXTRA_FLAGS]\n```\nRuns `ruff check .`. This is the **residue** pass: whatever it reports after `--fix` needs a human\ndecision. It is also the gate the project treats as authoritative, so a clean result here is the\nfinish line.\n\nExamples:\n- `just check-fix` — standard first pass\n- `just check` — residue pass, and the gate\n- `just check --select UP` — preview a rule that is not in the select list, without enabling it\n- `just check --statistics` — count the findings per rule while iterating\n\nBoth recipes accept extra flags, which are passed straight through to ruff.\n\n### What is actually enabled\n\nThe select list is deliberately narrow: `E` (pycodestyle), `F` (pyflakes), `I` (isort ordering),\n`B` (bugbear), and `D` (pydocstyle, Google convention, with the exemptions\n`pyproject.toml` declares, each with its reason beside it). `D` checks a docstring's layout,\nnever its Markdown. **There is no type checker in this repository** — no mypy, no pyright, no pre-commit\nhook. An annotation is a claim nothing verifies, so a wrong one survives every gate here and must be\ncaught by review.\n\nSeveral rule families are named as the designated enforcement for a convention a code rule in `docs\u002Fcode\u002F`\nstates, but are **not enabled** — `TRY400` and `S110`\u002F`S112` for error handling, among others.\nRunning `just check --select \u003Crule>` to see what a family would report is useful; concluding from a\nclean `just check` that those rules hold is not.\n\n## Notes\n\n### MANDATORY: Lint After Changes\n\nRun this skill after code changes. Before a task is complete, `just check` must be clean.\n\nA finding you cannot fix takes `# noqa: RULE — reason`, naming both. A bare `# noqa` hides which rule\nwas suppressed and why, and it silently keeps hiding the next rule that fires on that line.\n\n### Example Workflow\n\n1. Format first: `\u002Fcode-format`.\n2. **Stage 0** — probe `mcp__ide-index__ide_diagnostics` if available; fix what it reports in the\n   files you edited.\n3. **Stage 1** — `just check-fix`, then `just check`.\n4. Hand-fix the residue. Re-run `just check` until clean.\n5. Re-run `\u002Fcode-format` if `--fix` rewrote source.\n6. Done when `just check` reports `All checks passed!`.\n\n## Common Mistakes to Avoid\n\n### Anti-patterns\n- **Never run `ruff check` directly** — use `just check`, which applies the project's env handling.\n- **Never run the residue pass first** — `check-fix` before `check`.\n- **Never silence a finding with a bare `# noqa`** — name the rule and the reason.\n- **Never add a `# noqa` for a rule that is not in the select list** — it suppresses nothing and reads\n  like enforcement that is not there. Delete it.\n- **Never reorder imports by hand** — `--fix` owns import order, and a hand-sort is a diff ruff will\n  redo.\n- **Never conclude that a rule holds because `just check` is clean** — it only ran `E`, `F`, `I`, `B`.\n\n### Best practices\n- Format before linting, and again after `--fix` changes source.\n- Fix findings rather than suppressing them; a suppression is a decision that needs a reason.\n- Use `--select` to preview an unenabled rule family before proposing that it be turned on.\n- Run the full pass when you finish a coherent chunk of work, and before committing.\n\n## Next Steps\n\nAfter lint is clean:\n1. **Regenerate the generated files, when the change touches what they are rendered from** → use `\u002Fcode-gen`\n2. **Run targeted tests** → use `\u002Fcode-test`\n3. **Check the changeset against the code rules** → use `\u002Fcode-rules-check`\n4. **Commit** → only once lint is green\n","# Code Checking Skill\n\nLinting for this repository. Python has no compile step, so there is no `check` stage separate from\nthe linter: **ruff is the whole funnel**, and it runs over the entire repository in about a second.\n\nThat is the important difference from a compiled workspace. There is no per-package command to prefer\nand no blast-radius escalation to reason about, because the cheap command is already the complete\none. Lint everything, every time.\n\n## When to Use This Skill\n\nUse this skill when you need to:\n- Validate Python code after making changes\n- Surface unused imports, undefined names, import-order problems, or bugbear findings\n- Ensure code quality before a commit or PR\n\n## Command Selection: Two Passes\n\n```\nStage 0 (optional)              Stage 1 — mandatory\nIDE diagnostics            →    just check-fix    →    just check\n(mcp__ide-index__*)             (auto-apply)           (residue, hand-fix)\n```\n\nRun `check-fix` before `check`. Reversing them means reading a report of findings a tool was about to\nfix for you.\n\n## Stage 0 — IDE Diagnostics (Optional Fast Path)\n\nIf the session exposes the `ide-index` MCP server and the project is open in a JetBrains IDE,\n`mcp__ide-index__ide_diagnostics` returns diagnostics already computed in the background, per file.\nIt catches things ruff does not — unresolved attributes, type mismatches the annotations imply.\n\nProbe it once. If it errors or is unavailable, that is normal: skip to Stage 1 and do not treat the\nabsence as a failure. **Stage 0 is advisory and never terminal** — Stage 1 is mandatory regardless,\nbecause the IDE index may be stale and ruff enforces rules the IDE does not know about.\n\n## Available Commands\n\n### Check with auto-fix\n```bash\njust check-fix [EXTRA_FLAGS]\n```\nRuns `ruff check . --fix`, rewriting every finding ruff can fix safely — unused imports, import\nordering, and similar. This is the **first** pass.\n\n### Check without fixing\n```bash\njust check [EXTRA_FLAGS]\n```\nRuns `ruff check .`. This is the **residue** pass: whatever it reports after `--fix` needs a human\ndecision. It is also the gate the project treats as authoritative, so a clean result here is the\nfinish line.\n\nExamples:\n- `just check-fix` — standard first pass\n- `just check` — residue pass, and the gate\n- `just check --select UP` — preview a rule that is not in the select list, without enabling it\n- `just check --statistics` — count the findings per rule while iterating\n\nBoth recipes accept extra flags, which are passed straight through to ruff.\n\n### What is actually enabled\n\nThe select list is deliberately narrow: `E` (pycodestyle), `F` (pyflakes), `I` (isort ordering),\n`B` (bugbear), and `D` (pydocstyle, Google convention, with the exemptions\n`pyproject.toml` declares, each with its reason beside it). `D` checks a docstring's layout,\nnever its Markdown. **There is no type checker in this repository** — no mypy, no pyright, no pre-commit\nhook. An annotation is a claim nothing verifies, so a wrong one survives every gate here and must be\ncaught by review.\n\nSeveral rule families are named as the designated enforcement for a convention a code rule in `docs\u002Fcode\u002F`\nstates, but are **not enabled** — `TRY400` and `S110`\u002F`S112` for error handling, among others.\nRunning `just check --select \u003Crule>` to see what a family would report is useful; concluding from a\nclean `just check` that those rules hold is not.\n\n## Notes\n\n### MANDATORY: Lint After Changes\n\nRun this skill after code changes. Before a task is complete, `just check` must be clean.\n\nA finding you cannot fix takes `# noqa: RULE — reason`, naming both. A bare `# noqa` hides which rule\nwas suppressed and why, and it silently keeps hiding the next rule that fires on that line.\n\n### Example Workflow\n\n1. Format first: `\u002Fcode-format`.\n2. **Stage 0** — probe `mcp__ide-index__ide_diagnostics` if available; fix what it reports in the\n   files you edited.\n3. **Stage 1** — `just check-fix`, then `just check`.\n4. Hand-fix the residue. Re-run `just check` until clean.\n5. Re-run `\u002Fcode-format` if `--fix` rewrote source.\n6. Done when `just check` reports `All checks passed!`.\n\n## Common Mistakes to Avoid\n\n### Anti-patterns\n- **Never run `ruff check` directly** — use `just check`, which applies the project's env handling.\n- **Never run the residue pass first** — `check-fix` before `check`.\n- **Never silence a finding with a bare `# noqa`** — name the rule and the reason.\n- **Never add a `# noqa` for a rule that is not in the select list** — it suppresses nothing and reads\n  like enforcement that is not there. Delete it.\n- **Never reorder imports by hand** — `--fix` owns import order, and a hand-sort is a diff ruff will\n  redo.\n- **Never conclude that a rule holds because `just check` is clean** — it only ran `E`, `F`, `I`, `B`.\n\n### Best practices\n- Format before linting, and again after `--fix` changes source.\n- Fix findings rather than suppressing them; a suppression is a decision that needs a reason.\n- Use `--select` to preview an unenabled rule family before proposing that it be turned on.\n- Run the full pass when you finish a coherent chunk of work, and before committing.\n\n## Next Steps\n\nAfter lint is clean:\n1. **Regenerate the generated files, when the change touches what they are rendered from** → use `\u002Fcode-gen`\n2. **Run targeted tests** → use `\u002Fcode-test`\n3. **Check the changeset against the code rules** → use `\u002Fcode-rules-check`\n4. **Commit** → only once lint is green\n",{"name":5,"description":7,"allowed-tools":24,"compatibility":25},"Bash(just check *) Bash(just check-fix *) mcp__ide-index__ide_diagnostics","Requires the just task runner and uv. ruff is invoked through the project environment rather than a system install. Optionally uses JetBrains IDE diagnostics through the ide-index MCP server, which is not required.","main","d2f3a5835a8673ccf134ae62f0a5e84104ff7098",".agents\u002Fskills\u002Fcode-check",1,"https:\u002F\u002Fgithub.com\u002FLNSD\u002Florecraft","https:\u002F\u002Fgithub.com\u002FLNSD","2026-11-10 04:14:00",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add LNSD\u002Florecraft --skill code-check",{"tool":39,"command":40},"bunx","bunx skills add LNSD\u002Florecraft --skill code-check",{"tool":42,"command":43},"pnpm","pnpm dlx skills add LNSD\u002Florecraft --skill code-check","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FLNSD\u002Florecraft\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fcode-check\u002FSKILL.md",true,[],[48,55,60,65,70,75],{"skillNo":49,"name":50,"nameZh":6,"description":51,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":52,"categories":53,"keywords":54,"publishedAt":19},"01M7DASA0R4R68AVTZJFJJBYDB","review","Review a change. Use when asked to review.","https:\u002F\u002Fgithub.com\u002FLNSD\u002Florecraft\u002Fblob\u002Fmain\u002Ftests\u002Fit\u002Frule_cases\u002FLC504\u002Ftrigger\u002Freference-link-to-parent-skill-file\u002Froot\u002F.agents\u002Fskills\u002Freview\u002FSKILL.md",[],[],{"skillNo":56,"name":50,"nameZh":6,"description":51,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":19},"01M7DAS1YXJQ8FGABR8BGX9FAT","https:\u002F\u002Fgithub.com\u002FLNSD\u002Florecraft\u002Fblob\u002Fmain\u002Ftests\u002Fit\u002Frule_cases\u002FLC504\u002Fnear_miss\u002Fclimb-that-stays-inside-and-document-climb\u002Froot\u002F.agents\u002Fskills\u002Freview\u002FSKILL.md",[],[],{"skillNo":61,"name":50,"nameZh":6,"description":51,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":19},"01M7DAS0TCKQFF2YJ5VY9SWHV2","https:\u002F\u002Fgithub.com\u002FLNSD\u002Florecraft\u002Fblob\u002Fmain\u002Ftests\u002Fit\u002Frule_cases\u002FLC503\u002Ftrigger\u002Fskill-reference-link-read-from-skill-root\u002Froot\u002F.agents\u002Fskills\u002Freview\u002FSKILL.md",[],[],{"skillNo":66,"name":50,"nameZh":6,"description":51,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":19},"01M7DARZNA9QGXHAY17142R8YT","https:\u002F\u002Fgithub.com\u002FLNSD\u002Florecraft\u002Fblob\u002Fmain\u002Ftests\u002Fit\u002Frule_cases\u002FLC503\u002Fnear_miss\u002Fskill-link-climbing-above-skill-root\u002Froot\u002F.agents\u002Fskills\u002Freview\u002FSKILL.md",[],[],{"skillNo":71,"name":50,"nameZh":6,"description":51,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":19},"01M7DARYHB7WBR44AJXFJSZQ7X","https:\u002F\u002Fgithub.com\u002FLNSD\u002Florecraft\u002Fblob\u002Fmain\u002Ftests\u002Fit\u002Frule_cases\u002FLC502\u002Ftrigger\u002Fskill-fragment-in-file-without-headings\u002Froot\u002F.agents\u002Fskills\u002Freview\u002FSKILL.md",[],[],{"skillNo":76,"name":50,"nameZh":6,"description":51,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":19},"01M7DARXCTFKMH92FHVV8H30MM","https:\u002F\u002Fgithub.com\u002FLNSD\u002Florecraft\u002Fblob\u002Fmain\u002Ftests\u002Fit\u002Frule_cases\u002FLC501\u002Ftrigger\u002Fskill-link-starting-with-slash\u002Froot\u002F.agents\u002Fskills\u002Freview\u002FSKILL.md",[],[]]