[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75CDXH5FBMKPW2SFQJFYAQJ":3,"skill-same:01M75CDXH5FBMKPW2SFQJFYAQJ":48},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":30,"ownerHtmlUrl":31,"ownerBlogUrl":32,"ownerDescription":6,"updatedAt":33,"install":34,"resources":47},"01M75CDXH5FBMKPW2SFQJFYAQJ","commit-pr",null,"Apply when committing, pushing, opening a PR, writing a pull request, creating release notes, or updating a changelog. Enforces conventional commit format, mandatory release notes, 5-tier test suite, SHA-pinning for workflow changes, and correct PR body format.","agisota\u002Fold-one","agisota","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F121413592?v=4","01M75B4BRNT67EC1NDRT8QZEP2","01M75B4BS7QR9VP580MSCPTS3X",3,"MIT","https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one\u002Fblob\u002Fmain\u002Fskills\u002Fcommit-pr\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: commit-pr\ndescription: >\n  Apply when committing, pushing, opening a PR, writing a pull request, creating release\n  notes, or updating a changelog. Enforces conventional commit format, mandatory release\n  notes, 5-tier test suite, SHA-pinning for workflow changes, and correct PR body format.\neffort: medium\n---\n\n## Commit & PR Protocol\n\nFollow every step in order. Do not skip steps.\n\n### Step 1 — Format every commit message correctly\n\nUse `\u003Ctype>(\u003Cscope>): \u003Cdescription>` exactly:\n- Description must be **lowercase** and **not end with a period**\n- Scope is optional but encouraged\n- Allowed types: `feat`, `fix`, `perf`, `revert`, `docs`, `chore`, `refactor`, `test`, `ci`, `build`\n- For a breaking change, append `!` to the type (e.g. `feat!:`) or add a `BREAKING CHANGE:` footer\n\nValid: `feat(architect): add retry backoff to SME delegation`\nInvalid: `Fix stuff`, `feat: Add new feature.`, `feature: new thing`\n\n### Step 2 — Choose the correct PR title type\n\nThe PR title is the squash merge commit message. Choose based on primary change:\n- New capability → `feat` (minor bump)\n- Bug fix only → `fix` (patch bump)\n- Mixed feat + fix → use `feat` (minor subsumes patch)\n- `docs`\u002F`chore`\u002F`refactor`\u002F`test`\u002F`ci`\u002F`build` only → no version bump is triggered\n\n### Step 3 — Determine NEXT_VERSION and create the release notes file\n\n1. Read `.release-please-manifest.json` to find the current version\n2. Determine the bump from your commit type:\n   - `fix`, `perf`, `revert` → patch (e.g. `6.33.1` → `6.33.2`)\n   - `feat` → minor (e.g. `6.33.1` → `6.34.0`)\n   - breaking change (`!` or `BREAKING CHANGE:` footer) → major (e.g. `6.33.1` → `7.0.0`)\n   - `docs`, `chore`, `refactor`, `test`, `ci`, `build` → no bump; use the current version as NEXT_VERSION (still create the file)\n3. Create `docs\u002Freleases\u002Fv{NEXT_VERSION}.md` with freeform markdown covering:\n   - **What changed** — changes grouped by theme\n   - **Why** — motivation (bug report, feature request, hardening)\n   - **Migration steps** — if any API, config, or behavior changed\n   - **Breaking changes** — if any\n   - **Known caveats** — anything users should watch out for\n\nThis file is **mandatory on every PR, no exceptions**, including one-line fixes.\n\n### Step 4 — Never touch these files manually\n\nDo **not** edit `package.json` version field, `CHANGELOG.md`, or `.release-please-manifest.json`. Release-please manages them; manual edits cause merge conflicts and break the pipeline.\n\n### Step 5 — ⛔ MANDATORY: Run the full 5-tier test suite before pushing\n\n**This step is MANDATORY. It is not optional, skippable, or conditional.**\n\nEvery tier MUST be run in order, regardless of:\n- Whether the swarm's internal QA gates already ran lint\u002Fchecks (swarm scope ≠ CI scope)\n- Whether the change looks trivial or cosmetic\n- Whether tests passed locally in isolation\n- Whether you are in a hurry\n\nSkipping this step WILL cause CI failures that waste time and require a follow-up commit.\n\nRun every tier in order. Fix failures before proceeding.\n\n```bash\n# Tier 1 — quality\nbun run typecheck\nbunx biome ci .   # MUST run on the full project — never scope to modified files only.\n                  # CI runs it on all files; a scoped run will miss errors in files you\n                  # touched indirectly (e.g. reformatted by another tool, or modified via\n                  # biome --write on one file but not re-checked globally).\n                  #\n                  # If you ran `bunx biome check --write` to auto-fix formatting,\n                  # re-run `bunx biome ci .` afterwards and commit the auto-fixed files\n                  # BEFORE pushing — biome --write produces unstaged changes that will\n                  # cause the quality CI check to fail on the un-fixed commit.\n\n# Tier 2 — unit tests (use per-file loop for tools\u002Fservices\u002Fagents to avoid mock conflicts)\nfor f in tests\u002Funit\u002Ftools\u002F*.test.ts; do bun --smol test \"$f\" --timeout 30000; done\nfor f in tests\u002Funit\u002Fservices\u002F*.test.ts; do bun --smol test \"$f\" --timeout 30000; done\nfor f in tests\u002Funit\u002Fagents\u002F*.test.ts; do bun --smol test \"$f\" --timeout 30000; done\nbun --smol test tests\u002Funit\u002Fhooks tests\u002Funit\u002Fcli tests\u002Funit\u002Fcommands tests\u002Funit\u002Fconfig --timeout 120000\n\n# Tier 3 — integration tests\n# IMPORTANT: always run Tier 3 after fixing Tier 2 failures — the same root cause\n# often appears in integration test fixtures that unit tests don't cover.\nbun test tests\u002Fintegration .\u002Ftest --timeout 120000\n\n# Tier 4 — security and adversarial tests\nbun test tests\u002Fsecurity --timeout 120000\nbun test tests\u002Fadversarial --timeout 120000\n\n# Tier 5 — build + smoke (smoke requires a successful build first)\nbun run build\n# After building, commit any updated dist\u002F files if the repo tracks them.\n# CI runs a dist-check that diffs committed dist\u002F against a fresh build and fails\n# if they diverge. Check with: git status dist\u002F\n# If dist\u002F files are modified or new, stage and commit them before pushing:\n#   git add dist\u002F && git commit -m \"chore: update dist artifacts\"\nbun test tests\u002Fsmoke --timeout 120000\n```\n\n**Schema or field name changes: extra step required.**\nWhen you rename a field in a Zod schema, TypeScript interface, or serialized format (e.g. `task_id` → `taskId`):\n1. Grep for the old field name across ALL test files — unit AND integration:\n   ```bash\n   grep -rn \"old_field_name\" tests\u002F --include=\"*.ts\"\n   ```\n2. Update every test fixture that writes JSON with the old field name.\n3. Update every assertion that reads the old field name from parsed JSON.\n4. Run Tier 2 and Tier 3 together after fixing all fixtures.\n\nFailing to do this causes test fixtures to write stale-format JSON that passes Zod validation for the write but fails on the read path — a silent correctness hazard.\n\nIf a failure is pre-existing and unrelated to your changes, note it in the PR description — do not skip the other tiers.\n\n### Step 6 — SHA-pin any workflow changes\n\nIf you add or modify any file in `.github\u002Fworkflows\u002F`, every `uses:` reference to a third-party action must be pinned to a full 40-character commit SHA with the version as a comment:\n\n```yaml\n# Correct\n- uses: actions\u002Fcheckout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4\n\n# Wrong — will fail security tests\n- uses: actions\u002Fcheckout@v4\n- uses: actions\u002Fcheckout@main\n```\n\nFind the SHA for a tag:\n```bash\ngh api repos\u002F{owner}\u002F{repo}\u002Fgit\u002Fref\u002Ftags\u002F{tag} --jq '.object.sha'\n```\n\n### Step 7 — Squash to a single clean commit\n\nBefore pushing, collapse all interim commits into one. The PR must land as a single commit whose message is the canonical record of the change.\n\n```bash\n# See what you're about to squash (sanity check)\nBASE=$(git merge-base HEAD main)\ngit log --oneline $BASE..HEAD\n\n# Squash everything since branching from main\ngit reset --soft $BASE\ngit commit -m \"type(scope): description\"\n\n# Force-push with lease (never plain --force)\ngit push --force-with-lease -u origin \u003Cbranch-name>\n```\n\n**Rules:**\n- The squash commit message must match the PR title exactly — they are the same thing.\n- Use `--force-with-lease`, never `--force`. Lease rejects the push if the remote has commits you haven't seen.\n- If a review cycle is already in progress (reviewer comments reference specific commit SHAs), do **not** squash until all review threads are resolved — squashing rewrites history and orphans inline comments.\n- Any dist\u002F build artifact commits must be included in the squash (stage them before `git commit`).\n\n**Why:** Interim commits (`fix attempt 1`, `wip`, `address review`) are noise in the project history. A single well-named commit makes `git log`, `git bisect`, and release notes meaningful. The PR title doubles as the squash commit message — both must be correct conventional-commit format.\n\n### Step 8 — Open the PR with the correct body format\n\n```bash\ngh pr create --title \"\u003Ctype>(\u003Cscope>): \u003Cdescription>\" --body \"$(cat \u003C\u003C'EOF'\n## Summary\n- \u003Cbullet 1>\n- \u003Cbullet 2 if needed>\n- \u003Cbullet 3 if needed>\n\n## Test plan\n- [ ] \u003Cwhat you tested>\n- [ ] \u003Cadditional test step>\n\nEOF\n)\" --base main\n```\n\n`## Summary` must have 1–3 bullets explaining what and why. `## Test plan` must be a markdown checklist. Do not replace the body of an existing release-please PR — prepend only.\n\n### Step 9 — Pre-merge checklist\n\nVerify every item before asking for a merge:\n- [ ] Branch has exactly **one commit** — the squashed commit from Step 7 (`git log --oneline main..HEAD` shows one line)\n- [ ] That commit message matches the PR title exactly, and both follow `\u003Ctype>(\u003Cscope>): \u003Cdescription>`\n- [ ] `docs\u002Freleases\u002Fv{NEXT_VERSION}.md` exists with meaningful release notes\n- [ ] `package.json` version, `CHANGELOG.md`, `.release-please-manifest.json` are untouched\n- [ ] All 5 test tiers from Step 5 were actually run (not assumed — you must have the output in context), including `bunx biome ci .` on the full project (not scoped)\n- [ ] If the repo tracks `dist\u002F` files: `bun run build` was run and dist\u002F artifacts are included in the squash commit\n- [ ] All workflow `uses:` references are SHA-pinned (if workflows changed)\n- [ ] PR body has `## Summary` and `## Test plan`\n- [ ] All CI checks are green before merging\n","## Commit & PR Protocol\n\nFollow every step in order. Do not skip steps.\n\n### Step 1 — Format every commit message correctly\n\nUse `\u003Ctype>(\u003Cscope>): \u003Cdescription>` exactly:\n- Description must be **lowercase** and **not end with a period**\n- Scope is optional but encouraged\n- Allowed types: `feat`, `fix`, `perf`, `revert`, `docs`, `chore`, `refactor`, `test`, `ci`, `build`\n- For a breaking change, append `!` to the type (e.g. `feat!:`) or add a `BREAKING CHANGE:` footer\n\nValid: `feat(architect): add retry backoff to SME delegation`\nInvalid: `Fix stuff`, `feat: Add new feature.`, `feature: new thing`\n\n### Step 2 — Choose the correct PR title type\n\nThe PR title is the squash merge commit message. Choose based on primary change:\n- New capability → `feat` (minor bump)\n- Bug fix only → `fix` (patch bump)\n- Mixed feat + fix → use `feat` (minor subsumes patch)\n- `docs`\u002F`chore`\u002F`refactor`\u002F`test`\u002F`ci`\u002F`build` only → no version bump is triggered\n\n### Step 3 — Determine NEXT_VERSION and create the release notes file\n\n1. Read `.release-please-manifest.json` to find the current version\n2. Determine the bump from your commit type:\n   - `fix`, `perf`, `revert` → patch (e.g. `6.33.1` → `6.33.2`)\n   - `feat` → minor (e.g. `6.33.1` → `6.34.0`)\n   - breaking change (`!` or `BREAKING CHANGE:` footer) → major (e.g. `6.33.1` → `7.0.0`)\n   - `docs`, `chore`, `refactor`, `test`, `ci`, `build` → no bump; use the current version as NEXT_VERSION (still create the file)\n3. Create `docs\u002Freleases\u002Fv{NEXT_VERSION}.md` with freeform markdown covering:\n   - **What changed** — changes grouped by theme\n   - **Why** — motivation (bug report, feature request, hardening)\n   - **Migration steps** — if any API, config, or behavior changed\n   - **Breaking changes** — if any\n   - **Known caveats** — anything users should watch out for\n\nThis file is **mandatory on every PR, no exceptions**, including one-line fixes.\n\n### Step 4 — Never touch these files manually\n\nDo **not** edit `package.json` version field, `CHANGELOG.md`, or `.release-please-manifest.json`. Release-please manages them; manual edits cause merge conflicts and break the pipeline.\n\n### Step 5 — ⛔ MANDATORY: Run the full 5-tier test suite before pushing\n\n**This step is MANDATORY. It is not optional, skippable, or conditional.**\n\nEvery tier MUST be run in order, regardless of:\n- Whether the swarm's internal QA gates already ran lint\u002Fchecks (swarm scope ≠ CI scope)\n- Whether the change looks trivial or cosmetic\n- Whether tests passed locally in isolation\n- Whether you are in a hurry\n\nSkipping this step WILL cause CI failures that waste time and require a follow-up commit.\n\nRun every tier in order. Fix failures before proceeding.\n\n```bash\n# Tier 1 — quality\nbun run typecheck\nbunx biome ci .   # MUST run on the full project — never scope to modified files only.\n                  # CI runs it on all files; a scoped run will miss errors in files you\n                  # touched indirectly (e.g. reformatted by another tool, or modified via\n                  # biome --write on one file but not re-checked globally).\n                  #\n                  # If you ran `bunx biome check --write` to auto-fix formatting,\n                  # re-run `bunx biome ci .` afterwards and commit the auto-fixed files\n                  # BEFORE pushing — biome --write produces unstaged changes that will\n                  # cause the quality CI check to fail on the un-fixed commit.\n\n# Tier 2 — unit tests (use per-file loop for tools\u002Fservices\u002Fagents to avoid mock conflicts)\nfor f in tests\u002Funit\u002Ftools\u002F*.test.ts; do bun --smol test \"$f\" --timeout 30000; done\nfor f in tests\u002Funit\u002Fservices\u002F*.test.ts; do bun --smol test \"$f\" --timeout 30000; done\nfor f in tests\u002Funit\u002Fagents\u002F*.test.ts; do bun --smol test \"$f\" --timeout 30000; done\nbun --smol test tests\u002Funit\u002Fhooks tests\u002Funit\u002Fcli tests\u002Funit\u002Fcommands tests\u002Funit\u002Fconfig --timeout 120000\n\n# Tier 3 — integration tests\n# IMPORTANT: always run Tier 3 after fixing Tier 2 failures — the same root cause\n# often appears in integration test fixtures that unit tests don't cover.\nbun test tests\u002Fintegration .\u002Ftest --timeout 120000\n\n# Tier 4 — security and adversarial tests\nbun test tests\u002Fsecurity --timeout 120000\nbun test tests\u002Fadversarial --timeout 120000\n\n# Tier 5 — build + smoke (smoke requires a successful build first)\nbun run build\n# After building, commit any updated dist\u002F files if the repo tracks them.\n# CI runs a dist-check that diffs committed dist\u002F against a fresh build and fails\n# if they diverge. Check with: git status dist\u002F\n# If dist\u002F files are modified or new, stage and commit them before pushing:\n#   git add dist\u002F && git commit -m \"chore: update dist artifacts\"\nbun test tests\u002Fsmoke --timeout 120000\n```\n\n**Schema or field name changes: extra step required.**\nWhen you rename a field in a Zod schema, TypeScript interface, or serialized format (e.g. `task_id` → `taskId`):\n1. Grep for the old field name across ALL test files — unit AND integration:\n   ```bash\n   grep -rn \"old_field_name\" tests\u002F --include=\"*.ts\"\n   ```\n2. Update every test fixture that writes JSON with the old field name.\n3. Update every assertion that reads the old field name from parsed JSON.\n4. Run Tier 2 and Tier 3 together after fixing all fixtures.\n\nFailing to do this causes test fixtures to write stale-format JSON that passes Zod validation for the write but fails on the read path — a silent correctness hazard.\n\nIf a failure is pre-existing and unrelated to your changes, note it in the PR description — do not skip the other tiers.\n\n### Step 6 — SHA-pin any workflow changes\n\nIf you add or modify any file in `.github\u002Fworkflows\u002F`, every `uses:` reference to a third-party action must be pinned to a full 40-character commit SHA with the version as a comment:\n\n```yaml\n# Correct\n- uses: actions\u002Fcheckout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4\n\n# Wrong — will fail security tests\n- uses: actions\u002Fcheckout@v4\n- uses: actions\u002Fcheckout@main\n```\n\nFind the SHA for a tag:\n```bash\ngh api repos\u002F{owner}\u002F{repo}\u002Fgit\u002Fref\u002Ftags\u002F{tag} --jq '.object.sha'\n```\n\n### Step 7 — Squash to a single clean commit\n\nBefore pushing, collapse all interim commits into one. The PR must land as a single commit whose message is the canonical record of the change.\n\n```bash\n# See what you're about to squash (sanity check)\nBASE=$(git merge-base HEAD main)\ngit log --oneline $BASE..HEAD\n\n# Squash everything since branching from main\ngit reset --soft $BASE\ngit commit -m \"type(scope): description\"\n\n# Force-push with lease (never plain --force)\ngit push --force-with-lease -u origin \u003Cbranch-name>\n```\n\n**Rules:**\n- The squash commit message must match the PR title exactly — they are the same thing.\n- Use `--force-with-lease`, never `--force`. Lease rejects the push if the remote has commits you haven't seen.\n- If a review cycle is already in progress (reviewer comments reference specific commit SHAs), do **not** squash until all review threads are resolved — squashing rewrites history and orphans inline comments.\n- Any dist\u002F build artifact commits must be included in the squash (stage them before `git commit`).\n\n**Why:** Interim commits (`fix attempt 1`, `wip`, `address review`) are noise in the project history. A single well-named commit makes `git log`, `git bisect`, and release notes meaningful. The PR title doubles as the squash commit message — both must be correct conventional-commit format.\n\n### Step 8 — Open the PR with the correct body format\n\n```bash\ngh pr create --title \"\u003Ctype>(\u003Cscope>): \u003Cdescription>\" --body \"$(cat \u003C\u003C'EOF'\n## Summary\n- \u003Cbullet 1>\n- \u003Cbullet 2 if needed>\n- \u003Cbullet 3 if needed>\n\n## Test plan\n- [ ] \u003Cwhat you tested>\n- [ ] \u003Cadditional test step>\n\nEOF\n)\" --base main\n```\n\n`## Summary` must have 1–3 bullets explaining what and why. `## Test plan` must be a markdown checklist. Do not replace the body of an existing release-please PR — prepend only.\n\n### Step 9 — Pre-merge checklist\n\nVerify every item before asking for a merge:\n- [ ] Branch has exactly **one commit** — the squashed commit from Step 7 (`git log --oneline main..HEAD` shows one line)\n- [ ] That commit message matches the PR title exactly, and both follow `\u003Ctype>(\u003Cscope>): \u003Cdescription>`\n- [ ] `docs\u002Freleases\u002Fv{NEXT_VERSION}.md` exists with meaningful release notes\n- [ ] `package.json` version, `CHANGELOG.md`, `.release-please-manifest.json` are untouched\n- [ ] All 5 test tiers from Step 5 were actually run (not assumed — you must have the output in context), including `bunx biome ci .` on the full project (not scoped)\n- [ ] If the repo tracks `dist\u002F` files: `bun run build` was run and dist\u002F artifacts are included in the squash commit\n- [ ] All workflow `uses:` references are SHA-pinned (if workflows changed)\n- [ ] PR body has `## Summary` and `## Test plan`\n- [ ] All CI checks are green before merging\n",{"name":5,"effort":23,"description":24},"medium","Apply when committing, pushing, opening a PR, writing a pull request, creating release notes, or updating a changelog. Enforces conventional commit format, mandatory release notes, 5-tier test suite, SHA-pinning for workflow changes, and correct PR body format.\n","main","f37de8f681f0c0ca0e0ebab6e5fddf764ca7553d","skills\u002Fcommit-pr",1,"https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one","https:\u002F\u002Fagisota.github.io\u002Fold-one\u002F","https:\u002F\u002Fgithub.com\u002Fagisota","pzd.world","2026-07-04 22:32:06",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add agisota\u002Fold-one --skill commit-pr",{"tool":40,"command":41},"bunx","bunx skills add agisota\u002Fold-one --skill commit-pr",{"tool":43,"command":44},"pnpm","pnpm dlx skills add agisota\u002Fold-one --skill commit-pr","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one\u002Fblob\u002Fmain\u002Fskills\u002Fcommit-pr\u002FSKILL.md",true,[],[49,56,63,72,79,86],{"skillNo":50,"name":51,"nameZh":6,"description":52,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":53,"categories":54,"keywords":55,"publishedAt":18},"01M75KRGZWQWE9JDBS6RX42NWV","zoom-out","Tell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a section of code or need to understand how it fits into the bigger picture.","https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one\u002Fblob\u002Fmain\u002Fskills\u002Fzoom-out\u002FSKILL.md",[],[],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":18},"01M75KRCZHKE0ZYAQFFYHS0YNP","zeroize-audit","Detects missing zeroization of sensitive data in source code and identifies zeroization removed by compiler optimizations, with assembly-level analysis, and control-flow verification. Use for auditing C\u002FC++\u002FRust code handling secrets, keys, passwords, or other sensitive data.","https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one\u002Fblob\u002Fmain\u002Fskills\u002Fzeroize-audit\u002FSKILL.md",[],[],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":67,"licenseFileUrl":68,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":18},"01M75KR94KYQ30DTE1P9WNDAE0","yeet","Use only when the user explicitly asks to stage, commit, push, and open a GitHub pull request in one flow using the GitHub CLI (`gh`).","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one\u002Fblob\u002Fmain\u002Fskills\u002Fyeet\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one\u002Fblob\u002Fmain\u002Fskills\u002Fyeet\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":18},"01M75KR3H13YJ9QHMD49818FA1","yara-rule-authoring","Guides authoring of high-quality YARA-X detection rules for malware identification. Use when writing, reviewing, or optimizing YARA rules. Covers naming conventions, string selection, performance optimization, migration from legacy YARA, and false positive reduction. Triggers on: YARA, YARA-X, malware detection, threat hunting, IOC, signature, crx module, dex module.","https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one\u002Fblob\u002Fmain\u002Fskills\u002Fyara-rule-authoring\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":18},"01M75KQMPY8A4Y8XTDD2DT0M9T","x-twitter-growth","X\u002FTwitter growth engine for building audience, crafting viral content, and analyzing engagement. Use when the user wants to grow on X\u002FTwitter, write tweets or threads, analyze their X profile, research competitors on X, plan a posting strategy, or optimize engagement. Complements social-content (generic multi-platform) with X-specific depth: algorithm mechanics, thread engineering, reply strategy, profile optimization, and competitive intelligence via web search.","https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one\u002Fblob\u002Fmain\u002Fskills\u002Fx-twitter-growth\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":18},"01M75KQHNZ0ANZNJGZY6M8MDAK","x-api","X\u002FTwitter API integration for posting tweets, threads, reading timelines, search, and analytics. Covers OAuth auth patterns, rate limits, and platform-native content posting. Use when the user wants to interact with X programmatically.","https:\u002F\u002Fgithub.com\u002Fagisota\u002Fold-one\u002Fblob\u002Fmain\u002Fskills\u002Fx-api\u002FSKILL.md",[],[]]