[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75MP4SBQ72NCXTBN8NFNBP5":3,"skill-same:01M75MP4SBQ72NCXTBN8NFNBP5":45},{"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":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":30,"install":31,"resources":44},"01M75MP4SBQ72NCXTBN8NFNBP5","bump-version",null,"Collect current git changes, infer the next version number, update HARNESS_VERSION in src\u002Fharness.py, and prepend a changelog entry to CHANGELOG.md. Triggers on: bump version, version bump, collect changes and version, release version, new version, up version.","boringman21\u002Fhyp-harness","boringman21","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F30747973?v=4","01M75MP0R5HDFAHQ3SJK3B9CNB","Nghia P","01M75MP0S5Z9KTGZ2JNXZ00YK3",4,"MIT","https:\u002F\u002Fgithub.com\u002Fboringman21\u002Fhyp-harness\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fbump-version\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: bump-version\ndescription: \"Collect current git changes, infer the next version number, update HARNESS_VERSION in src\u002Fharness.py, and prepend a changelog entry to CHANGELOG.md. Triggers on: bump version, version bump, collect changes and version, release version, new version, up version.\"\n---\n\nBump the hyp-harness version based on the current uncommitted changes.\n\n## Steps\n\n### 0. Clean up junk files\n\nBefore anything else, remove known artifacts and stray files:\n\n```bash\n# Build\u002Ftest artifacts — always safe to delete\nrm -f .coverage\nrm -rf dashboard\u002Ftest-results\u002F\nrm -rf __pycache__ src\u002F__pycache__ tests\u002F__pycache__\n\n# Scratch files\nfind . -maxdepth 3 -name 'working*.md' -not -path '.\u002Fruns\u002F*' -delete\n\n# Root-level stray test files (belong in tests\u002F — if outside, they're scratch)\nfind . -maxdepth 1 -name 'test_*.py' -delete\n```\n\nThen check for files that need a judgment call — list them and ask the user before deleting:\n\n```bash\ngit status --short | grep '^??'\n```\n\nKnown-good untracked files — include in commit without asking:\n- `pyproject.toml` — pytest config (`[tool.pytest.ini_options]`), always keep\n- `tests\u002Ftest_*.py`, `tests\u002Ffixtures\u002F` — test suite, always keep\n- `dashboard\u002Fe2e\u002F`, `dashboard\u002Fplaywright.config.js` — e2e harness, always keep\n- `tools\u002F*.py` — harness tooling, always keep\n- `.claude\u002Fskills\u002F*\u002FSKILL.md` — canonical local skills, always keep\n- `.agents\u002Fskills\u002F*\u002FSKILL.md` — symlinks to canonical local skills, always keep\n\nFlag only truly ambiguous patterns (ask user before committing):\n- Any `*.md` not in `runs\u002F`, `docs\u002F`, `tests\u002F`, `.claude\u002Fskills\u002F`, or `.agents\u002Fskills\u002F` — might be scratch\n- Any root-level `.py` outside `src\u002F`, `tests\u002F`, `tools\u002F` — likely stray\n\nAlso check staged deletions — include them in the commit:\n```bash\ngit status --short | grep '^D '\n```\nThese are already-deleted files (e.g. removed quality module files) that need `git add -u` to stage properly.\n\n### 1. Collect changes\n\n```bash\ngit diff HEAD --stat\ngit diff HEAD\n```\n\nRead the diff carefully. Note every file changed and what was added\u002Fremoved.\n\n### 2. Determine current version\n\n```bash\ngrep 'HARNESS_VERSION' src\u002Fharness.py\n```\n\nThe value is the current version (e.g. `\"v4.3\"`). The next version is:\n- **minor bump** (X.Y → X.Y+1): default for any new features, fixes, or refactors\n- **major bump** (X.Y → X+1.0): only when the architecture changes significantly (new worker backend, new pipeline stage, breaking config format change)\n\n### 3. Summarize changes into a changelog entry\n\nWrite a concise changelog block following the existing style in `CHANGELOG.md`:\n\n```\n### v\u003CNEXT> — \u003CTODAY_DATE>\n- **\u003CFeature\u002FFix name>** (`\u003Cfile.py>`): \u003Cone sentence description>\n  - Sub-bullet for each distinct change in that file if needed\n- **\u003CNext feature>** ...\n```\n\nRules:\n- Group changes by logical feature, not by file\n- Bold the feature name, then file in backticks\n- Keep bullet text factual and specific — what changed and why (1-2 sentences max)\n- Deleted files: note what was removed and why\n- Test files: mention only if they cover a new public contract\n- Use today's date in `YYYY-MM-DD` format\n\n### 4. Update files\n\n**src\u002Fharness.py** — update `HARNESS_VERSION`:\n```python\nHARNESS_VERSION = \"v\u003CNEXT>\"\n```\n\n**CHANGELOG.md** — prepend the new entry immediately after the `# Changelog` heading (before the existing top entry). Do not modify any existing entries. (CLAUDE.md's `## Changelog` section just links here.)\n\n### 4b. Sync descriptive sections in CLAUDE.md\n\nCLAUDE.md has two kinds of content: append-only changelog, and **current-state descriptions** that must mirror the actual code. After writing the changelog entry, check each section below whose corresponding source files appear in the diff. For each affected section: read the actual current source, then rewrite only the stale parts.\n\n| Changed file(s) | CLAUDE.md section to check |\n|---|---|\n| `src\u002Fharness.py`, `src\u002Fpostproc.py` | `### Post-processor pipeline` — fixer count + numbered list must match `PostProcessor` class exactly |\n| `src\u002Fharness.py` | `## Architecture` (pipeline flow), `### Evaluator-optimizer` |\n| `src\u002Fevaluator.py` | `### Evaluator-optimizer` — rubric names, retry logic, READER_STYLES list |\n| `src\u002Fsynthesis.py` | `## Architecture` synthesis step, any synthesis retry description |\n| `src\u002Fharness.py` env vars | `## Env vars (harness tuning)` table — add\u002Fremove\u002Fchange defaults |\n| `dashboard\u002Fsrc\u002F` | `### Dashboard (\\`dashboard\u002F\\`)` — tabs, routes, features |\n| `src\u002Frender*.py` | `## Architecture` render step description |\n| `src\u002Fharness.py` DEFAULT_WRAPPER \u002F RETRY_WRAPPER | `## Kimi tool environment` notes on FetchURL, steps |\n| `src\u002Fharness.py` progress.log events | `## Architecture` progress.log API line |\n\n**How to update each section:**\n1. Read the relevant source file(s) to get the ground truth\n2. Read the current CLAUDE.md section\n3. Edit only the lines that are now wrong — preserve surrounding prose style\n4. Do not expand sections beyond what the diff touched — if a section is correct, leave it\n\n**Critical: `### Post-processor pipeline` fixer list**\nThis is the most commonly stale section. The numbered list must exactly match the fixers in `PostProcessor` (in `src\u002Fpostproc.py` or `harness.py`). Steps:\n```bash\ngrep -n '_fix_\\|_inject_\\|_autonumber_\\|_wrap_\\|_stream_\\|_fence_' src\u002Fpostproc.py | grep 'def '\n```\nCount the fixers, update the header count (\"21 safety-net fixers\"), and add\u002Fremove numbered entries to match.\n\n### 5. Sync check — find stale version refs\n\nAfter updating the two canonical files, scan for any other hardcoded version strings that are older than `\u003CNEXT>`:\n\n```bash\ngrep -rn 'v[0-9]\\+\\.[0-9]\\+' src\u002F --include='*.py' | grep -v 'HARNESS_VERSION\\|\\.pyc'\n```\n\nFor each hit, classify:\n\n| Pattern | Action |\n|---|---|\n| `HARNESS_VERSION = \"vX.Y\"` in any run copy (`runs\u002Fpoc-*\u002Fharness.py`) | **Skip** — run copies are frozen snapshots, never update |\n| `# mirrors harness.py vX.Y` or `# Prompt wrappers (mirrors …)` in `src\u002F` | **Update** the comment to `v\u003CNEXT>` if the surrounding code was changed in this diff; leave it if untouched |\n| `Extracted from harness.py vX.Y` in module docstring | **Leave as-is** — records extraction point, not current version |\n| Any other hardcoded version in `src\u002F*.py`, `dashboard\u002F`, `CLAUDE.md` intro | **Update** if it's meant to track current version |\n\nDashboard files (`dashboard\u002Fsrc\u002F`) read `HARNESS_VERSION` dynamically — no static sync needed.\n\n### 5b. Self-update this skill\n\nRead `.claude\u002Fskills\u002Fbump-version\u002FSKILL.md` (this file) and check if the diff introduces anything that makes its instructions stale. Update the skill if any of these changed:\n\n| What changed in diff | What to update in SKILL.md |\n|---|---|\n| New junk file pattern (e.g. new artifact dir, new scratch file type) | Add `rm` \u002F `find -delete` line to step 0 |\n| New \"review before committing\" file pattern | Add to the Flag list in step 0 |\n| New file added to `src\u002F` that carries version refs | Add row to sync table in step 5 |\n| New CLAUDE.md section added | Add row to mapping table in step 4b |\n| New env var added to `harness.py` | No change needed — step 4b already covers env vars table |\n| `HARNESS_VERSION` moved to a different file | Update step 2 grep and step 4 edit instruction |\n| Commit message convention changed | Update step 8 format string |\n\nEdit only the lines that are now wrong. Do not rewrite the whole skill.\n\n```bash\ngrep 'HARNESS_VERSION' src\u002Fharness.py\ngrep -B 1 -A 3 '^### v' CHANGELOG.md | head -8\n```\n\nConfirm the version matches and the new entry is at the top of the changelog.\n\n### 7. Report\n\nPrint a summary:\n```\nBumped v\u003CPREV> → v\u003CNEXT>: \u003CN> files changed — \u003Cheadline of what changed>\nSynced: \u003Clist of files updated beyond harness.py + CLAUDE.md, or \"none\">\nSkipped (historical): \u003Clist of stale refs intentionally left, or \"none\">\n```\n\n### 8. Commit and push\n\nStage all changes — modified tracked files plus any deletions from step 0:\n\n```bash\ngit add -u                                       # stages all modifications + deletions to tracked files\ngit add src\u002F dashboard\u002F CLAUDE.md CHANGELOG.md   # catches any untracked files in these dirs that should be included\n# Do NOT use git add . — avoids pulling in confirmed-junk untracked files\n```\n\nCommit with message format `release: vX.Y — \u003Cheadline>`:\n```bash\ngit commit -m \"release: v\u003CNEXT> — \u003Cone-line headline of main change>\"\n```\n\nThen push:\n```bash\ngit push\n```\n\nReport the commit hash and confirm push succeeded.\n\n## Version bump heuristics\n\n| Change type | Bump |\n|---|---|\n| New evaluator\u002Frubric, new retry loop, new pipeline stage | minor |\n| Bug fix, fixer added, verify check added, dashboard UI | minor |\n| Refactor \u002F cleanup \u002F test only | minor |\n| New worker backend, new CLI, breaking problem.yaml format | major |\n| Docs \u002F CLAUDE.md only | skip (no bump needed) |\n\n## File locations\n\n| File | What to update |\n|---|---|\n| `src\u002Fharness.py` | `HARNESS_VERSION = \"vX.Y\"` constant (canonical) |\n| `CHANGELOG.md` | prepend new entry at top |\n| `src\u002F*.py` inline comments | Only if code around them changed in this diff |\n| `runs\u002Fpoc-*\u002Fharness.py` | Never — frozen run copies |\n| `dashboard\u002Fsrc\u002F` | Never — reads version dynamically at runtime |\n\n## Skill file locations\n\nCanonical skill: `.claude\u002Fskills\u002Fbump-version\u002FSKILL.md` — edit this file.\nSymlink: `.agents\u002Fskills\u002Fbump-version\u002FSKILL.md` → canonical.\n\nKhi step 5b detect skill cần update: chỉ edit `.claude\u002Fskills\u002Fbump-version\u002FSKILL.md`.\n","Bump the hyp-harness version based on the current uncommitted changes.\n\n## Steps\n\n### 0. Clean up junk files\n\nBefore anything else, remove known artifacts and stray files:\n\n```bash\n# Build\u002Ftest artifacts — always safe to delete\nrm -f .coverage\nrm -rf dashboard\u002Ftest-results\u002F\nrm -rf __pycache__ src\u002F__pycache__ tests\u002F__pycache__\n\n# Scratch files\nfind . -maxdepth 3 -name 'working*.md' -not -path '.\u002Fruns\u002F*' -delete\n\n# Root-level stray test files (belong in tests\u002F — if outside, they're scratch)\nfind . -maxdepth 1 -name 'test_*.py' -delete\n```\n\nThen check for files that need a judgment call — list them and ask the user before deleting:\n\n```bash\ngit status --short | grep '^??'\n```\n\nKnown-good untracked files — include in commit without asking:\n- `pyproject.toml` — pytest config (`[tool.pytest.ini_options]`), always keep\n- `tests\u002Ftest_*.py`, `tests\u002Ffixtures\u002F` — test suite, always keep\n- `dashboard\u002Fe2e\u002F`, `dashboard\u002Fplaywright.config.js` — e2e harness, always keep\n- `tools\u002F*.py` — harness tooling, always keep\n- `.claude\u002Fskills\u002F*\u002FSKILL.md` — canonical local skills, always keep\n- `.agents\u002Fskills\u002F*\u002FSKILL.md` — symlinks to canonical local skills, always keep\n\nFlag only truly ambiguous patterns (ask user before committing):\n- Any `*.md` not in `runs\u002F`, `docs\u002F`, `tests\u002F`, `.claude\u002Fskills\u002F`, or `.agents\u002Fskills\u002F` — might be scratch\n- Any root-level `.py` outside `src\u002F`, `tests\u002F`, `tools\u002F` — likely stray\n\nAlso check staged deletions — include them in the commit:\n```bash\ngit status --short | grep '^D '\n```\nThese are already-deleted files (e.g. removed quality module files) that need `git add -u` to stage properly.\n\n### 1. Collect changes\n\n```bash\ngit diff HEAD --stat\ngit diff HEAD\n```\n\nRead the diff carefully. Note every file changed and what was added\u002Fremoved.\n\n### 2. Determine current version\n\n```bash\ngrep 'HARNESS_VERSION' src\u002Fharness.py\n```\n\nThe value is the current version (e.g. `\"v4.3\"`). The next version is:\n- **minor bump** (X.Y → X.Y+1): default for any new features, fixes, or refactors\n- **major bump** (X.Y → X+1.0): only when the architecture changes significantly (new worker backend, new pipeline stage, breaking config format change)\n\n### 3. Summarize changes into a changelog entry\n\nWrite a concise changelog block following the existing style in `CHANGELOG.md`:\n\n```\n### v\u003CNEXT> — \u003CTODAY_DATE>\n- **\u003CFeature\u002FFix name>** (`\u003Cfile.py>`): \u003Cone sentence description>\n  - Sub-bullet for each distinct change in that file if needed\n- **\u003CNext feature>** ...\n```\n\nRules:\n- Group changes by logical feature, not by file\n- Bold the feature name, then file in backticks\n- Keep bullet text factual and specific — what changed and why (1-2 sentences max)\n- Deleted files: note what was removed and why\n- Test files: mention only if they cover a new public contract\n- Use today's date in `YYYY-MM-DD` format\n\n### 4. Update files\n\n**src\u002Fharness.py** — update `HARNESS_VERSION`:\n```python\nHARNESS_VERSION = \"v\u003CNEXT>\"\n```\n\n**CHANGELOG.md** — prepend the new entry immediately after the `# Changelog` heading (before the existing top entry). Do not modify any existing entries. (CLAUDE.md's `## Changelog` section just links here.)\n\n### 4b. Sync descriptive sections in CLAUDE.md\n\nCLAUDE.md has two kinds of content: append-only changelog, and **current-state descriptions** that must mirror the actual code. After writing the changelog entry, check each section below whose corresponding source files appear in the diff. For each affected section: read the actual current source, then rewrite only the stale parts.\n\n| Changed file(s) | CLAUDE.md section to check |\n|---|---|\n| `src\u002Fharness.py`, `src\u002Fpostproc.py` | `### Post-processor pipeline` — fixer count + numbered list must match `PostProcessor` class exactly |\n| `src\u002Fharness.py` | `## Architecture` (pipeline flow), `### Evaluator-optimizer` |\n| `src\u002Fevaluator.py` | `### Evaluator-optimizer` — rubric names, retry logic, READER_STYLES list |\n| `src\u002Fsynthesis.py` | `## Architecture` synthesis step, any synthesis retry description |\n| `src\u002Fharness.py` env vars | `## Env vars (harness tuning)` table — add\u002Fremove\u002Fchange defaults |\n| `dashboard\u002Fsrc\u002F` | `### Dashboard (\\`dashboard\u002F\\`)` — tabs, routes, features |\n| `src\u002Frender*.py` | `## Architecture` render step description |\n| `src\u002Fharness.py` DEFAULT_WRAPPER \u002F RETRY_WRAPPER | `## Kimi tool environment` notes on FetchURL, steps |\n| `src\u002Fharness.py` progress.log events | `## Architecture` progress.log API line |\n\n**How to update each section:**\n1. Read the relevant source file(s) to get the ground truth\n2. Read the current CLAUDE.md section\n3. Edit only the lines that are now wrong — preserve surrounding prose style\n4. Do not expand sections beyond what the diff touched — if a section is correct, leave it\n\n**Critical: `### Post-processor pipeline` fixer list**\nThis is the most commonly stale section. The numbered list must exactly match the fixers in `PostProcessor` (in `src\u002Fpostproc.py` or `harness.py`). Steps:\n```bash\ngrep -n '_fix_\\|_inject_\\|_autonumber_\\|_wrap_\\|_stream_\\|_fence_' src\u002Fpostproc.py | grep 'def '\n```\nCount the fixers, update the header count (\"21 safety-net fixers\"), and add\u002Fremove numbered entries to match.\n\n### 5. Sync check — find stale version refs\n\nAfter updating the two canonical files, scan for any other hardcoded version strings that are older than `\u003CNEXT>`:\n\n```bash\ngrep -rn 'v[0-9]\\+\\.[0-9]\\+' src\u002F --include='*.py' | grep -v 'HARNESS_VERSION\\|\\.pyc'\n```\n\nFor each hit, classify:\n\n| Pattern | Action |\n|---|---|\n| `HARNESS_VERSION = \"vX.Y\"` in any run copy (`runs\u002Fpoc-*\u002Fharness.py`) | **Skip** — run copies are frozen snapshots, never update |\n| `# mirrors harness.py vX.Y` or `# Prompt wrappers (mirrors …)` in `src\u002F` | **Update** the comment to `v\u003CNEXT>` if the surrounding code was changed in this diff; leave it if untouched |\n| `Extracted from harness.py vX.Y` in module docstring | **Leave as-is** — records extraction point, not current version |\n| Any other hardcoded version in `src\u002F*.py`, `dashboard\u002F`, `CLAUDE.md` intro | **Update** if it's meant to track current version |\n\nDashboard files (`dashboard\u002Fsrc\u002F`) read `HARNESS_VERSION` dynamically — no static sync needed.\n\n### 5b. Self-update this skill\n\nRead `.claude\u002Fskills\u002Fbump-version\u002FSKILL.md` (this file) and check if the diff introduces anything that makes its instructions stale. Update the skill if any of these changed:\n\n| What changed in diff | What to update in SKILL.md |\n|---|---|\n| New junk file pattern (e.g. new artifact dir, new scratch file type) | Add `rm` \u002F `find -delete` line to step 0 |\n| New \"review before committing\" file pattern | Add to the Flag list in step 0 |\n| New file added to `src\u002F` that carries version refs | Add row to sync table in step 5 |\n| New CLAUDE.md section added | Add row to mapping table in step 4b |\n| New env var added to `harness.py` | No change needed — step 4b already covers env vars table |\n| `HARNESS_VERSION` moved to a different file | Update step 2 grep and step 4 edit instruction |\n| Commit message convention changed | Update step 8 format string |\n\nEdit only the lines that are now wrong. Do not rewrite the whole skill.\n\n```bash\ngrep 'HARNESS_VERSION' src\u002Fharness.py\ngrep -B 1 -A 3 '^### v' CHANGELOG.md | head -8\n```\n\nConfirm the version matches and the new entry is at the top of the changelog.\n\n### 7. Report\n\nPrint a summary:\n```\nBumped v\u003CPREV> → v\u003CNEXT>: \u003CN> files changed — \u003Cheadline of what changed>\nSynced: \u003Clist of files updated beyond harness.py + CLAUDE.md, or \"none\">\nSkipped (historical): \u003Clist of stale refs intentionally left, or \"none\">\n```\n\n### 8. Commit and push\n\nStage all changes — modified tracked files plus any deletions from step 0:\n\n```bash\ngit add -u                                       # stages all modifications + deletions to tracked files\ngit add src\u002F dashboard\u002F CLAUDE.md CHANGELOG.md   # catches any untracked files in these dirs that should be included\n# Do NOT use git add . — avoids pulling in confirmed-junk untracked files\n```\n\nCommit with message format `release: vX.Y — \u003Cheadline>`:\n```bash\ngit commit -m \"release: v\u003CNEXT> — \u003Cone-line headline of main change>\"\n```\n\nThen push:\n```bash\ngit push\n```\n\nReport the commit hash and confirm push succeeded.\n\n## Version bump heuristics\n\n| Change type | Bump |\n|---|---|\n| New evaluator\u002Frubric, new retry loop, new pipeline stage | minor |\n| Bug fix, fixer added, verify check added, dashboard UI | minor |\n| Refactor \u002F cleanup \u002F test only | minor |\n| New worker backend, new CLI, breaking problem.yaml format | major |\n| Docs \u002F CLAUDE.md only | skip (no bump needed) |\n\n## File locations\n\n| File | What to update |\n|---|---|\n| `src\u002Fharness.py` | `HARNESS_VERSION = \"vX.Y\"` constant (canonical) |\n| `CHANGELOG.md` | prepend new entry at top |\n| `src\u002F*.py` inline comments | Only if code around them changed in this diff |\n| `runs\u002Fpoc-*\u002Fharness.py` | Never — frozen run copies |\n| `dashboard\u002Fsrc\u002F` | Never — reads version dynamically at runtime |\n\n## Skill file locations\n\nCanonical skill: `.claude\u002Fskills\u002Fbump-version\u002FSKILL.md` — edit this file.\nSymlink: `.agents\u002Fskills\u002Fbump-version\u002FSKILL.md` → canonical.\n\nKhi step 5b detect skill cần update: chỉ edit `.claude\u002Fskills\u002Fbump-version\u002FSKILL.md`.\n",{"name":5,"description":7},"main","88b355d57344f30f2c69c98db24270c91b7a427b",".claude\u002Fskills\u002Fbump-version",0,"https:\u002F\u002Fgithub.com\u002Fboringman21\u002Fhyp-harness","https:\u002F\u002Fgithub.com\u002Fboringman21","2026-06-12 21:40:36",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add boringman21\u002Fhyp-harness --skill bump-version",{"tool":37,"command":38},"bunx","bunx skills add boringman21\u002Fhyp-harness --skill bump-version",{"tool":40,"command":41},"pnpm","pnpm dlx skills add boringman21\u002Fhyp-harness --skill bump-version","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fboringman21\u002Fhyp-harness\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fbump-version\u002FSKILL.md",true,[],[46,54,61,66],{"skillNo":47,"name":48,"nameZh":6,"description":49,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":50,"sourceHtmlUrl":51,"categories":52,"keywords":53,"publishedAt":19},"01M75MPDFGJ32J1DW8FDBGJ2KW","pretty-mermaid","Render beautiful Mermaid diagrams as SVG or ASCII art using the beautiful-mermaid library.\nSupports 15+ themes, 5 diagram types (flowchart, sequence, state, class, ER), and ultra-fast rendering.\n\nUse this skill when:\n1. User asks to \"render a mermaid diagram\" or provides .mmd files\n2. User requests \"create a flowchart\u002Fsequence diagram\u002Fstate diagram\"\n3. User wants to \"apply a theme\" or \"beautify a diagram\"\n4. User needs to \"batch process multiple diagrams\"\n5. User mentions \"ASCII diagram\" or \"terminal-friendly diagram\"\n6. User wants to visualize architecture, workflows, or data models","https:\u002F\u002Fgithub.com\u002Fboringman21\u002Fhyp-harness\u002Fblob\u002Fmain\u002Ftools\u002Fpretty-mermaid\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fboringman21\u002Fhyp-harness\u002Fblob\u002Fmain\u002Ftools\u002Fpretty-mermaid\u002FSKILL.md",[],[],{"skillNo":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":19},"01M75MP8S0QC4N0ETY4V3W6HGB","hyp-harness","Multi-model fan-out harness: given a problem.yaml spec, fans out N parallel workers (kimi CLI or Claude Code CLI) each writing one research task as markdown, runs evaluator-optimizer quality gate, synthesizes all outputs into a final report, renders to dark-theme HTML. Triggers on: harness, kimi harness, claude harness, run harness, fan-out tasks, poc harness, long running task, parallel research, parallel workers, deep research.","https:\u002F\u002Fgithub.com\u002Fboringman21\u002Fhyp-harness\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fhyp-harness\u002FSKILL.md",[],[],{"skillNo":62,"name":56,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":19},"01M75MP3K8EKFXPWDY3A7T554B","https:\u002F\u002Fgithub.com\u002Fboringman21\u002Fhyp-harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fhyp-harness\u002FSKILL.md",[],[],{"skillNo":67,"name":5,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":19},"01M75MP2KV3PB8Y0ZEPQ6HRH9S","https:\u002F\u002Fgithub.com\u002Fboringman21\u002Fhyp-harness\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbump-version\u002FSKILL.md",[],[]]