[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6GCWZ36R03CSDVVSQ8C2PFR":3,"skill-same:01M6GCWZ36R03CSDVVSQ8C2PFR":76},{"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":39,"linkOnly":40,"markdownContent":41,"markdownBody":42,"frontMatter":43,"refName":54,"commitSha":55,"skillDirectory":56,"forksCount":57,"repositoryHtmlUrl":58,"repositoryHomepageUrl":6,"ownerHtmlUrl":59,"ownerBlogUrl":6,"ownerDescription":60,"updatedAt":61,"install":62,"resources":75},"01M6GCWZ36R03CSDVVSQ8C2PFR","pr-lens",null,"Draw code changes as animated architecture\u002Fdata-flow SVGs.","zapabob\u002FSkills","zapabob","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F130830376?v=4","01M6DBMYZAGRTFQDSQYW3W764P","峯岸 亮","01M6DBMZ3GKDSJ01NZ9XTZD7JD",2,"MIT","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Farchive\u002Fskill-md-reviewed\u002Fsha256\u002Fb1\u002Fb11e1eba1f74fd91d8b7c4d4462dde741b1883332c7059fcded88c986a1f19b5\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"pr lens","lens","pr","pull","requests","software-development","nous research","SVG","as","diagrams","data-flow","review","code-review","pull-requests","code","development","architecture","research","linux","github","2026-11-10 10:12:30",false,"---\nname: pr-lens\ndescription: \"Draw code changes as animated architecture\u002Fdata-flow SVGs.\"\nversion: 1.0.0\nauthor: Coldtea AI (adapted by Nous Research)\nlicense: MIT\nplatforms: [linux, macos]\nmetadata:\n  hermes:\n    tags: [diagrams, pull-requests, code-review, svg]\n    category: software-development\n    related_skills: []\n    upstream: https:\u002F\u002Fgithub.com\u002Fcoldteadotai\u002Fpr-lens (pinned 0993b4d)\n---\n\n# PR Lens Skill\n\nPR Lens draws code as visually rich animated diagrams: diffs, architecture, data flows. You describe the diff or codebase as one JSON document (lanes, nodes, edges, ordered flows) and the CLI renders it as animated SVGs. There is no findings lens — PR Lens is a comprehension layer, not a review bot. There is no field for a bug, risk, or security note, and a document that invents one is rejected.\n\n## When to Use\n\n- Asked to diagram, visualise, or explain a code change or a system.\n- A pull request should carry an architecture or data-flow diagram.\n- Keywords: PR Lens, diagram, architecture, data flow, visualise, pull request.\n\n## Prerequisites\n\n- Node.js with `npx` (the CLI runs via `npx @coldtea\u002Fpr-lens-cli@latest`; no install step).\n- `gh` (GitHub CLI) — optional, only for attaching diagrams to PRs.\n- Optional canvas publishing calls the third-party service prlens.dev (see step 4b).\n\n## How to Run\n\nRun all commands with the terminal tool from the repository root.\n\n1. **Read the diff.** When representing a code change: `git diff --find-renames \u003Cbase>...\u003Chead>`. The base is the merge base, not the tip of the base branch. If not expressing a diff, read the code to be visualised.\n\n2. **Write the document** to `.pr-lens\u002Fgraph.json`, following `references\u002Fgraph-document.md`. `references\u002Fexample.graph.json` is a valid reference with three lanes, all four delta states, a hero edge, a seven-step flow, a nested drill-down tree and a six-step walkthrough. Read it before writing your first document — quicker than reading the reference.\n\n3. **Validate, and fix.**\n\n   ```bash\n   npx @coldtea\u002Fpr-lens-cli@latest validate .pr-lens\u002Fgraph.json\n   ```\n\n   Fix every failure and run it again. Do not render an invalid document; do not \"work around\" a failure by deleting the element it names.\n\n4. **Render.**\n\n   ```bash\n   npx @coldtea\u002Fpr-lens-cli@latest render .pr-lens\u002Fgraph.json --theme light\n   ```\n\n   Render light by default unless the user requests another theme. The SVGs, the manifest and `drawn.graph.json` land in `.pr-lens\u002F`, which the CLI adds to the repository's .gitignore. Do not commit any of it — these files are rebuilt from the diff on demand. Each SVG is named after its view, theme and content hash; `manifest.json` lists them by lens and view.\n\n4b. **Canvas push — OPTIONAL, opt-in.** Only when the user explicitly asks for a shareable link. This publishes `.pr-lens\u002Fdrawn.graph.json` to the third-party service prlens.dev:\n\n   ```bash\n   npx @coldtea\u002Fpr-lens-cli@latest canvas push\n   ```\n\n   It prints three links. Give the user the **view link** (`https:\u002F\u002Fprlens.dev\u002Fc\u002F{id}`): the full-screen diagram, every view on one page, no login. The **edit link** (ending in `#w=…`) lets its holder overwrite the canvas — it is a secret: leave it out of the reply unless asked, never paste it anywhere public. The embed link serves the top view as an SVG for a README. Pushing the same file again updates the same canvas, so \"rename that node\" is: edit, validate, render, push — the link stays the same. If the push fails, say so and tell the user where the local SVGs are and which is the top view.\n\n5. **Attach to a PR, when there is one.** Upstream documents `gh pr create\u002Fedit\u002Fcomment --attach \u003Cpath>`, but `--attach` arrived in GitHub CLI 2.99 — check `gh --version` first (e.g. gh 2.97 does NOT have it). With gh ≥ 2.99: write the body with a Markdown image `![alt](.pr-lens\u002F\u003Cview>.svg)` (an HTML `\u003Cimg>` is left as written and the file appended at the bottom instead; alt text is the one-line caption a reader without images gets), then repeat `--attach \u003Cpath>` per referenced diagram:\n\n   ```bash\n   gh pr create --title \"…\" --body-file .pr-lens\u002Fbody.md --attach .pr-lens\u002Foverview-light-\u003Chash>.svg\n   ```\n\n   Without `--attach`, use a commit-free path:\n   - Upload the SVGs to a gist: `gh gist create .pr-lens\u002F\u003Cview>.svg`, then reference the raw gist URL in the PR body\u002Fcomment, or\n   - Publish via the canvas link (step 4b, with user consent) and link the view URL, or\n   - Note the local `.pr-lens\u002F` path in the PR body so reviewers can rebuild.\n\n   Once published somewhere durable, let the CLI compose the comment markdown:\n\n   ```bash\n   npx @coldtea\u002Fpr-lens-cli@latest comment \\\n     --graph .pr-lens\u002Fdrawn.graph.json \\\n     --manifest .pr-lens\u002Fmanifest.json \\\n     --asset-base-url \u003Cwhere you published the SVGs>\n   ```\n\n   `--graph` takes `drawn.graph.json`, not the document you wrote — the CLI refuses a document its manifest does not describe. Leave out `--asset-base-url` and the markdown points at local paths no reader can fetch. The markdown goes to stdout; posting it is your business.\n\n   Attach the views a reviewer needs and leave the rest in `.pr-lens\u002F`: the top architecture view first, then a data flow if the change has a sequence worth following. Two diagrams usually beat four.\n\n6. **Optional automation:** `npx @coldtea\u002Fpr-lens-cli@latest analyze --base \u003Cref>` does steps 1–2 by asking a provider (Gemini, OpenAI, or any `\u002Fchat\u002Fcompletions` endpoint) with a key of your own. That is the only path here that needs one; normally you author the document yourself.\n\n## What makes a document worth reading\n\n- **Include what did not change.** Unchanged neighbours a change touches are the context; mark them `delta: \"unchanged\"`.\n- **Lanes are the reader's mental model** (a runtime, a tier, a boundary), not the folder tree.\n- **One hero edge**, two at the outside: the connection the change is really about.\n- **Add a flow only when there is a sequence** worth animating. One good flow beats three thin ones.\n- **Attach file refs**: they become the permalinks a reviewer clicks.\n- Architecture views are a C4-inspired decision tree: system context → container → component, each child materially narrower. Skip empty or repetitive levels; keep data-flow views as separate roots; set `defaultOpen: true` on the highest useful architecture view.\n- **Walkthroughs** (2–12 steps, aim 3–7): write one for anything non-trivial. Each step = one change (added\u002Fremoved\u002Fmoved), headline change first, overview last. Headings ≤48 chars built from change words; bodies ≤140 chars on behaviour, required. Write for a smart twelve-year-old; no \"leverages\"\u002F\"orchestrates\". Keep consecutive steps on the same stage. The walkthrough field needs CLI ≥ 0.4.0 (contract 0.1.1).\n- **Fixing a wrong map:** never edit the generated document — write corrections into `.github\u002Fpr-lens.yml` (see `references\u002Fconfig.md`), then validate it: `npx @coldtea\u002Fpr-lens-cli@latest validate .github\u002Fpr-lens.yml`. Prefer path globs over `id:` matches.\n\n## Quick Reference\n\n| Command | Purpose |\n| --- | --- |\n| `npx @coldtea\u002Fpr-lens-cli@latest validate .pr-lens\u002Fgraph.json` | validate the document (also validates `.github\u002Fpr-lens.yml`) |\n| `npx @coldtea\u002Fpr-lens-cli@latest render .pr-lens\u002Fgraph.json --theme light` | render SVGs + manifest into `.pr-lens\u002F` |\n| `npx @coldtea\u002Fpr-lens-cli@latest canvas push` | OPTIONAL: publish to prlens.dev (opt-in only) |\n| `npx @coldtea\u002Fpr-lens-cli@latest comment --graph … --manifest … --asset-base-url …` | compose PR comment markdown to stdout |\n| `npx @coldtea\u002Fpr-lens-cli@latest analyze --base \u003Cref>` | auto-author document via an LLM provider (needs API key) |\n\nValidator failure codes:\n\n| Code | What you did |\n| --- | --- |\n| `BROKEN_REFERENCE` | an edge, flow step, view or walkthrough step names an id you never declared |\n| `INVALID_DOCUMENT` | an invented field; the schemas are strict, unknown keys are rejected |\n| `DUPLICATE_ID` | two nodes, edges or views sharing an id |\n| `UNSUPPORTED_SCHEMA_VERSION` | `schemaVersion` is not the contract version installed |\n\n## Pitfalls\n\n- Six rules are parser-only, not in the JSON Schema (referential integrity, inverted line ranges, disagreeing `self` endpoints, identical patch commits, too many views for a manifest, flow-step focus on the wrong stage) — always run `validate`, structured output alone is not enough.\n- Do not commit anything in `.pr-lens\u002F`; it is regenerated and gitignored by the CLI.\n- The `--attach` gh flag needs gh ≥ 2.99; older gh silently lacks it — check before writing a body around it.\n- The canvas edit link (`#w=…`) is a write credential — never share it unprompted or paste it publicly.\n- A stored map never carries a walkthrough; a walkthrough tells the story of one change.\n- `pr-lens render` reports corrections in `.github\u002Fpr-lens.yml` that matched nothing — that is drift worth fixing, not an error.\n\n## Verification\n\nSmoke test (live-verified 2026-09-12 with `@coldtea\u002Fpr-lens-cli` via npx, node on Linux):\n\n```bash\ncp references\u002Fexample.graph.json ~\u002F.hermes\u002Fcache\u002Fscratch\u002Fprlens-smoke\u002F && cd ~\u002F.hermes\u002Fcache\u002Fscratch\u002Fprlens-smoke\nnpx -y @coldtea\u002Fpr-lens-cli@latest validate example.graph.json\n# ✓ example.graph.json — graph document · 3 lanes, 10 nodes, 13 edges, 1 flow · 6 walkthrough steps\nnpx -y @coldtea\u002Fpr-lens-cli@latest render example.graph.json --theme light\n# ✓ .pr-lens\u002Fmanifest.json — 4 SVGs across 4 diagrams\n```\n\nExpect exit 0 on both and four `*-light-\u003Chash>.svg` files plus `manifest.json` and `drawn.graph.json` in `.pr-lens\u002F`.\n\n---\n\nAdapted from [coldteadotai\u002Fpr-lens](https:\u002F\u002Fgithub.com\u002Fcoldteadotai\u002Fpr-lens) (packages\u002Fagent-skill, pinned 0993b4d), MIT License, Copyright (c) 2026 Coldtea AI. See LICENSE.txt.\n","# PR Lens Skill\n\nPR Lens draws code as visually rich animated diagrams: diffs, architecture, data flows. You describe the diff or codebase as one JSON document (lanes, nodes, edges, ordered flows) and the CLI renders it as animated SVGs. There is no findings lens — PR Lens is a comprehension layer, not a review bot. There is no field for a bug, risk, or security note, and a document that invents one is rejected.\n\n## When to Use\n\n- Asked to diagram, visualise, or explain a code change or a system.\n- A pull request should carry an architecture or data-flow diagram.\n- Keywords: PR Lens, diagram, architecture, data flow, visualise, pull request.\n\n## Prerequisites\n\n- Node.js with `npx` (the CLI runs via `npx @coldtea\u002Fpr-lens-cli@latest`; no install step).\n- `gh` (GitHub CLI) — optional, only for attaching diagrams to PRs.\n- Optional canvas publishing calls the third-party service prlens.dev (see step 4b).\n\n## How to Run\n\nRun all commands with the terminal tool from the repository root.\n\n1. **Read the diff.** When representing a code change: `git diff --find-renames \u003Cbase>...\u003Chead>`. The base is the merge base, not the tip of the base branch. If not expressing a diff, read the code to be visualised.\n\n2. **Write the document** to `.pr-lens\u002Fgraph.json`, following `references\u002Fgraph-document.md`. `references\u002Fexample.graph.json` is a valid reference with three lanes, all four delta states, a hero edge, a seven-step flow, a nested drill-down tree and a six-step walkthrough. Read it before writing your first document — quicker than reading the reference.\n\n3. **Validate, and fix.**\n\n   ```bash\n   npx @coldtea\u002Fpr-lens-cli@latest validate .pr-lens\u002Fgraph.json\n   ```\n\n   Fix every failure and run it again. Do not render an invalid document; do not \"work around\" a failure by deleting the element it names.\n\n4. **Render.**\n\n   ```bash\n   npx @coldtea\u002Fpr-lens-cli@latest render .pr-lens\u002Fgraph.json --theme light\n   ```\n\n   Render light by default unless the user requests another theme. The SVGs, the manifest and `drawn.graph.json` land in `.pr-lens\u002F`, which the CLI adds to the repository's .gitignore. Do not commit any of it — these files are rebuilt from the diff on demand. Each SVG is named after its view, theme and content hash; `manifest.json` lists them by lens and view.\n\n4b. **Canvas push — OPTIONAL, opt-in.** Only when the user explicitly asks for a shareable link. This publishes `.pr-lens\u002Fdrawn.graph.json` to the third-party service prlens.dev:\n\n   ```bash\n   npx @coldtea\u002Fpr-lens-cli@latest canvas push\n   ```\n\n   It prints three links. Give the user the **view link** (`https:\u002F\u002Fprlens.dev\u002Fc\u002F{id}`): the full-screen diagram, every view on one page, no login. The **edit link** (ending in `#w=…`) lets its holder overwrite the canvas — it is a secret: leave it out of the reply unless asked, never paste it anywhere public. The embed link serves the top view as an SVG for a README. Pushing the same file again updates the same canvas, so \"rename that node\" is: edit, validate, render, push — the link stays the same. If the push fails, say so and tell the user where the local SVGs are and which is the top view.\n\n5. **Attach to a PR, when there is one.** Upstream documents `gh pr create\u002Fedit\u002Fcomment --attach \u003Cpath>`, but `--attach` arrived in GitHub CLI 2.99 — check `gh --version` first (e.g. gh 2.97 does NOT have it). With gh ≥ 2.99: write the body with a Markdown image `![alt](.pr-lens\u002F\u003Cview>.svg)` (an HTML `\u003Cimg>` is left as written and the file appended at the bottom instead; alt text is the one-line caption a reader without images gets), then repeat `--attach \u003Cpath>` per referenced diagram:\n\n   ```bash\n   gh pr create --title \"…\" --body-file .pr-lens\u002Fbody.md --attach .pr-lens\u002Foverview-light-\u003Chash>.svg\n   ```\n\n   Without `--attach`, use a commit-free path:\n   - Upload the SVGs to a gist: `gh gist create .pr-lens\u002F\u003Cview>.svg`, then reference the raw gist URL in the PR body\u002Fcomment, or\n   - Publish via the canvas link (step 4b, with user consent) and link the view URL, or\n   - Note the local `.pr-lens\u002F` path in the PR body so reviewers can rebuild.\n\n   Once published somewhere durable, let the CLI compose the comment markdown:\n\n   ```bash\n   npx @coldtea\u002Fpr-lens-cli@latest comment \\\n     --graph .pr-lens\u002Fdrawn.graph.json \\\n     --manifest .pr-lens\u002Fmanifest.json \\\n     --asset-base-url \u003Cwhere you published the SVGs>\n   ```\n\n   `--graph` takes `drawn.graph.json`, not the document you wrote — the CLI refuses a document its manifest does not describe. Leave out `--asset-base-url` and the markdown points at local paths no reader can fetch. The markdown goes to stdout; posting it is your business.\n\n   Attach the views a reviewer needs and leave the rest in `.pr-lens\u002F`: the top architecture view first, then a data flow if the change has a sequence worth following. Two diagrams usually beat four.\n\n6. **Optional automation:** `npx @coldtea\u002Fpr-lens-cli@latest analyze --base \u003Cref>` does steps 1–2 by asking a provider (Gemini, OpenAI, or any `\u002Fchat\u002Fcompletions` endpoint) with a key of your own. That is the only path here that needs one; normally you author the document yourself.\n\n## What makes a document worth reading\n\n- **Include what did not change.** Unchanged neighbours a change touches are the context; mark them `delta: \"unchanged\"`.\n- **Lanes are the reader's mental model** (a runtime, a tier, a boundary), not the folder tree.\n- **One hero edge**, two at the outside: the connection the change is really about.\n- **Add a flow only when there is a sequence** worth animating. One good flow beats three thin ones.\n- **Attach file refs**: they become the permalinks a reviewer clicks.\n- Architecture views are a C4-inspired decision tree: system context → container → component, each child materially narrower. Skip empty or repetitive levels; keep data-flow views as separate roots; set `defaultOpen: true` on the highest useful architecture view.\n- **Walkthroughs** (2–12 steps, aim 3–7): write one for anything non-trivial. Each step = one change (added\u002Fremoved\u002Fmoved), headline change first, overview last. Headings ≤48 chars built from change words; bodies ≤140 chars on behaviour, required. Write for a smart twelve-year-old; no \"leverages\"\u002F\"orchestrates\". Keep consecutive steps on the same stage. The walkthrough field needs CLI ≥ 0.4.0 (contract 0.1.1).\n- **Fixing a wrong map:** never edit the generated document — write corrections into `.github\u002Fpr-lens.yml` (see `references\u002Fconfig.md`), then validate it: `npx @coldtea\u002Fpr-lens-cli@latest validate .github\u002Fpr-lens.yml`. Prefer path globs over `id:` matches.\n\n## Quick Reference\n\n| Command | Purpose |\n| --- | --- |\n| `npx @coldtea\u002Fpr-lens-cli@latest validate .pr-lens\u002Fgraph.json` | validate the document (also validates `.github\u002Fpr-lens.yml`) |\n| `npx @coldtea\u002Fpr-lens-cli@latest render .pr-lens\u002Fgraph.json --theme light` | render SVGs + manifest into `.pr-lens\u002F` |\n| `npx @coldtea\u002Fpr-lens-cli@latest canvas push` | OPTIONAL: publish to prlens.dev (opt-in only) |\n| `npx @coldtea\u002Fpr-lens-cli@latest comment --graph … --manifest … --asset-base-url …` | compose PR comment markdown to stdout |\n| `npx @coldtea\u002Fpr-lens-cli@latest analyze --base \u003Cref>` | auto-author document via an LLM provider (needs API key) |\n\nValidator failure codes:\n\n| Code | What you did |\n| --- | --- |\n| `BROKEN_REFERENCE` | an edge, flow step, view or walkthrough step names an id you never declared |\n| `INVALID_DOCUMENT` | an invented field; the schemas are strict, unknown keys are rejected |\n| `DUPLICATE_ID` | two nodes, edges or views sharing an id |\n| `UNSUPPORTED_SCHEMA_VERSION` | `schemaVersion` is not the contract version installed |\n\n## Pitfalls\n\n- Six rules are parser-only, not in the JSON Schema (referential integrity, inverted line ranges, disagreeing `self` endpoints, identical patch commits, too many views for a manifest, flow-step focus on the wrong stage) — always run `validate`, structured output alone is not enough.\n- Do not commit anything in `.pr-lens\u002F`; it is regenerated and gitignored by the CLI.\n- The `--attach` gh flag needs gh ≥ 2.99; older gh silently lacks it — check before writing a body around it.\n- The canvas edit link (`#w=…`) is a write credential — never share it unprompted or paste it publicly.\n- A stored map never carries a walkthrough; a walkthrough tells the story of one change.\n- `pr-lens render` reports corrections in `.github\u002Fpr-lens.yml` that matched nothing — that is drift worth fixing, not an error.\n\n## Verification\n\nSmoke test (live-verified 2026-09-12 with `@coldtea\u002Fpr-lens-cli` via npx, node on Linux):\n\n```bash\ncp references\u002Fexample.graph.json ~\u002F.hermes\u002Fcache\u002Fscratch\u002Fprlens-smoke\u002F && cd ~\u002F.hermes\u002Fcache\u002Fscratch\u002Fprlens-smoke\nnpx -y @coldtea\u002Fpr-lens-cli@latest validate example.graph.json\n# ✓ example.graph.json — graph document · 3 lanes, 10 nodes, 13 edges, 1 flow · 6 walkthrough steps\nnpx -y @coldtea\u002Fpr-lens-cli@latest render example.graph.json --theme light\n# ✓ .pr-lens\u002Fmanifest.json — 4 SVGs across 4 diagrams\n```\n\nExpect exit 0 on both and four `*-light-\u003Chash>.svg` files plus `manifest.json` and `drawn.graph.json` in `.pr-lens\u002F`.\n\n---\n\nAdapted from [coldteadotai\u002Fpr-lens](https:\u002F\u002Fgithub.com\u002Fcoldteadotai\u002Fpr-lens) (packages\u002Fagent-skill, pinned 0993b4d), MIT License, Copyright (c) 2026 Coldtea AI. See LICENSE.txt.\n",{"name":5,"author":44,"license":15,"version":45,"metadata":46,"platforms":52,"description":7},"Coldtea AI (adapted by Nous Research)","1.0.0",{"hermes":47},{"tags":48,"category":24,"upstream":50,"related_skills":51},[28,32,31,49],"svg","https:\u002F\u002Fgithub.com\u002Fcoldteadotai\u002Fpr-lens (pinned 0993b4d)",[],[37,53],"macos","main","0d1434f89f4bc6b07e9d272accd8c1013768820f","archive\u002Fskill-md-reviewed\u002Fsha256\u002Fb1\u002Fb11e1eba1f74fd91d8b7c4d4462dde741b1883332c7059fcded88c986a1f19b5",0,"https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills","https:\u002F\u002Fgithub.com\u002Fzapabob","The Open University of JAPAN　2019-now\r\n\r\nTokyo University of Science　2007-2010","2026-10-26 16:29:01",{"source":8,"skillName":5,"commands":63,"prompt":73,"zipAvailable":74},[64,67,70],{"tool":65,"command":66},"npx","npx skills add zapabob\u002FSkills --skill pr-lens",{"tool":68,"command":69},"bunx","bunx skills add zapabob\u002FSkills --skill pr-lens",{"tool":71,"command":72},"pnpm","pnpm dlx skills add zapabob\u002FSkills --skill pr-lens","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Farchive\u002Fskill-md-reviewed\u002Fsha256\u002Fb1\u002Fb11e1eba1f74fd91d8b7c4d4462dde741b1883332c7059fcded88c986a1f19b5\u002FSKILL.md",true,[],[77,112,143,170,197,214],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":96,"publishedAt":39},"01M6GJTE1GESGGF9K028Y7753E","xurl","X\u002FTwitter via xurl CLI: post, search, DM, media, v2 API.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fxurl\u002Fvariants\u002Fhermes-agent\u002FSKILL.md",[83,88,91],{"categoryNo":84,"categoryName":85,"taxonomyType":86,"taxonomyTypeDesc":87},"01JBSEEDCAT000000000000010","后端与接口","SCENARIO","使用场景",{"categoryNo":89,"categoryName":90,"taxonomyType":86,"taxonomyTypeDesc":87},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":92,"categoryName":93,"taxonomyType":94,"taxonomyTypeDesc":95},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[79,97,53,98,38,37,99,100,101,102,103,104,105,106,107,108,54,109,110,111],"openclaw","cli","windows","official","search","https","social-media","api","Media","hermes","hermes agent","twitter","social","via","post",{"skillNo":113,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":116,"categories":117,"keywords":129,"publishedAt":39},"01M6GJT8S1PXQ8WPXT1HSNBWH2","writing-plans","Write implementation plans: bite-sized tasks, paths, code.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fwriting-plans\u002Fvariants\u002Fhermes-agent\u002FSKILL.md",[118,121,124,125,126],{"categoryNo":119,"categoryName":120,"taxonomyType":86,"taxonomyTypeDesc":87},"01JBSEEDCAT000000000000015","视觉设计",{"categoryNo":122,"categoryName":123,"taxonomyType":86,"taxonomyTypeDesc":87},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":89,"categoryName":90,"taxonomyType":86,"taxonomyTypeDesc":87},{"categoryNo":92,"categoryName":93,"taxonomyType":94,"taxonomyTypeDesc":95},{"categoryNo":127,"categoryName":128,"taxonomyType":94,"taxonomyTypeDesc":95},"01JBSEEDCAT000000000000036","内容创作者",[130,131,132,133,53,30,37,134,99,135,136,34,33,137,31,138,139,140,141,142],"writing","writing plans","plans","design","workflow","documentation","tasks","planning","subagent","write","superpowers","paths","test-driven-development",{"skillNo":144,"name":145,"nameZh":6,"description":146,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":147,"categories":148,"keywords":152,"publishedAt":39},"01M6GJST0H5X7WHBJ3BZK0DVKH","whisper","OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual ASR.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fwhisper\u002Fvariants\u002Fhermes-agent-optional\u002FSKILL.md",[149],{"categoryNo":150,"categoryName":151,"taxonomyType":86,"taxonomyTypeDesc":87},"01JBSEEDCAT000000000000016","图像与多媒体",[145,53,37,153,154,155,156,157,158,159,160,161,162,163,164,165,166,167,168,169],"openai","speech","multimodal","Transformers","ASR","Audio","text","model","speech recognition","use","general","multilingual","translation","english","identification","processing","Audio Processing",{"skillNo":171,"name":172,"nameZh":6,"description":173,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":174,"categories":175,"keywords":179,"publishedAt":39},"01M6GJSMRQ8EETZTYMG72P70EA","weights-and-biases","W&B: log ML experiments, sweeps, model registry, dashboards.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fweights-and-biases\u002Fvariants\u002Fhermes-agent\u002FSKILL.md",[176],{"categoryNo":177,"categoryName":178,"taxonomyType":86,"taxonomyTypeDesc":87},"01JBSEEDCAT000000000000013","分析与可视化",[180,53,181,182,99,183,184,185,186,187,188,160,189,190,191,192,193,194,195,196],"weights and biases","tensorflow","experiments","pytorch","visualization","registry","real-time","tuning","dashboards","experiment","log","time","Experiment Tracking","Model Registry","Hyperparameter Tuning","WandB","Real-Time Visualization",{"skillNo":198,"name":199,"nameZh":6,"description":200,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":201,"categories":202,"keywords":204,"publishedAt":39},"01M6GJS19KDPRY112JTR326S06","watchers","Poll RSS, JSON APIs, and GitHub with watermark dedup.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fwatchers\u002Fvariants\u002Fhermes-agent-optional\u002FSKILL.md",[203],{"categoryNo":89,"categoryName":90,"taxonomyType":86,"taxonomyTypeDesc":87},[199,53,205,38,37,206,207,208,209,210,211,106,107,212,213],"terminal","automation","http","monitoring","cron","json","rss","devops","with",{"skillNo":215,"name":216,"nameZh":6,"description":217,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":218,"categories":219,"keywords":222,"publishedAt":39},"01M6GJRHJD2A6Q830SWF9W48BC","serving-llms-vllm","vLLM: high-throughput LLM serving, OpenAI API, quantization.","https:\u002F\u002Fgithub.com\u002Fzapabob\u002FSkills\u002Fblob\u002Fmain\u002Fregistry\u002Fskills\u002Fvllm\u002Fvariants\u002Fhermes-agent\u002FSKILL.md",[220,221],{"categoryNo":84,"categoryName":85,"taxonomyType":86,"taxonomyTypeDesc":87},{"categoryNo":92,"categoryName":93,"taxonomyType":94,"taxonomyTypeDesc":95},[223,224,225,37,36,153,226,227,228,156,229,104,230,231,232,233,234,235,236,237],"llms","vLLM","serving llms vllm","openai api","tensor","Inference Serving","Production","llm serving","High Throughput","PagedAttention","Continuous Batching","Quantization","Tensor Parallelism","high-throughput","throughput"]