[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7CP4HDJGS2TM7H7X6ZSA9BH":3,"skill-same:01M7CP4HDJGS2TM7H7X6ZSA9BH":53},{"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":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M7CP4HDJGS2TM7H7X6ZSA9BH","bs-score",null,"Use when auditing a repo, PR, branch, PR review, AI skill, agent config, or one or more prompts for claims vs truth and real defects: follow the canonical bs-score SKILL.md, emit findings JSON, then run bs-score (higher = more bullshit).","alexhawat\u002Fbs-score","alexhawat","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F1254687?v=4","01M79RKRMA3JJ8JZFXZ1YBDT0D","Alex Hawat","01M7CP49ZJC0G6B7DBP5AG9CB9",3,"MIT","https:\u002F\u002Fgithub.com\u002Falexhawat\u002Fbs-score\u002Fblob\u002Fmain\u002Fagents\u002Fclaude\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: bs-score\ndescription: >-\n  Use when auditing a repo, PR, branch, PR review, AI skill, agent config, or one\n  or more prompts for claims vs truth and real defects: follow the canonical\n  bs-score SKILL.md, emit findings JSON, then run bs-score (higher = more\n  bullshit).\nallowed-tools: Read, Grep, Glob, Bash\nlicense: MIT\n---\n\n# Bullshit Score (`bs-score`) — Claude Code\n\n## Install\n\nTwo pieces: the skill files, and the `bs-score` command that scores them.\n\n**The skill** — clone the repository into Claude Code's skills folder, so the root\n`SKILL.md` and the `checklists\u002F` it links to land together:\n\n```bash\ngit clone --depth 1 https:\u002F\u002Fgithub.com\u002Falexhawat\u002Fbs-score ~\u002F.claude\u002Fskills\u002Fbs-score   # personal\ngit clone --depth 1 https:\u002F\u002Fgithub.com\u002Falexhawat\u002Fbs-score .claude\u002Fskills\u002Fbs-score   # project\n```\n\n`~\u002F.claude\u002Fskills\u002Fbs-score` applies to every project; `.claude\u002Fskills\u002Fbs-score` is checked into one\nrepository. Keep the folder name `bs-score` — it is the skill's name.\n\n**The command** — one line, and nothing here vendors it:\n\n```bash\nuv tool install git+https:\u002F\u002Fgithub.com\u002Falexhawat\u002Fbs-score   # puts bs-score on PATH\n```\n\n## Canonical pack\n\nThis wrapper belongs to [alexhawat\u002Fbs-score](https:\u002F\u002Fgithub.com\u002Falexhawat\u002Fbs-score).\n\n1. Read **`SKILL.md` at the repository root** — the two-pass workflow, the\n   per-review-type checklists, and the hard rules live there.\n2. Emit findings JSON matching `findings.schema.json` (no `score` \u002F `points`).\n3. Score it:\n\n```bash\nbs-score findings.json --repo-root .          # installed\nuv run bs-score findings.json --repo-root .   # from a clone of the repo\n```\n\nEvery install option is in the\n[repository README](https:\u002F\u002Fgithub.com\u002Falexhawat\u002Fbs-score#install).\n\nQuotes are verified against the files they name before anything is scored, so\n`--repo-root` must point at the tree you audited. For prompts and review bodies,\nadd `--sources` (`bs-score` below is the same command):\n\n```bash\nbs-score findings.json --sources prompts\u002F                    # prompt audit\nbs-score findings.json --repo-root . --sources review.json   # review audit\n```\n\nFrom a clone, `python3 score.py findings.json` and `uv run bs-score …` do the same thing.\n\n## What it audits\n\n| `target_kind` | Scope | Weight profile |\n|---------------|-------|----------------|\n| `repo` | Docs claims **and** deep code | baseline |\n| `pr` \u002F `branch` | The diff and its callers | landing defects weigh more |\n| `review` | A PR review vs the diff | false claims and misses weigh more |\n| `skill` | Skill MD + the code it names | unimplemented claims weigh more |\n| `agent` | Agent \u002F persona configs | unsafe instructions weigh most |\n| `prompt` | One or more prompts | injection and secrets weigh most |\n| `docs` | One document, claims only | wrong claims weigh most |\n\n## Fixture examples\n\nRun from a clone of the repo:\n\n```bash\nuv run bs-score examples\u002Ffindings.valid.json  --repo-root examples\u002Ffixture-repo   # 17\nuv run bs-score examples\u002Ffindings.review.json --repo-root examples\u002Ffixture-repo \\\n    --sources examples\u002Ffixture-review\u002Freview.json                                # 10\nuv run bs-score examples\u002Ffindings.skill.json  --repo-root examples\u002Ffixture-repo   # 7\nuv run bs-score examples\u002Ffindings.agent.json  --repo-root examples\u002Ffixture-repo   # 6\nuv run bs-score examples\u002Ffindings.prompt.json --sources examples\u002Ffixture-prompts  # 18\nuv run bs-score examples\u002Ffindings.hallucinated.json \\\n    --repo-root examples\u002Ffixture-repo                                            # 0\n```\n\nThat last one is the point: a fabricated audit scores zero because none of its\nquotes exist.\n\nNever invent the score — report only what `bs-score` printed.\n","# Bullshit Score (`bs-score`) — Claude Code\n\n## Install\n\nTwo pieces: the skill files, and the `bs-score` command that scores them.\n\n**The skill** — clone the repository into Claude Code's skills folder, so the root\n`SKILL.md` and the `checklists\u002F` it links to land together:\n\n```bash\ngit clone --depth 1 https:\u002F\u002Fgithub.com\u002Falexhawat\u002Fbs-score ~\u002F.claude\u002Fskills\u002Fbs-score   # personal\ngit clone --depth 1 https:\u002F\u002Fgithub.com\u002Falexhawat\u002Fbs-score .claude\u002Fskills\u002Fbs-score   # project\n```\n\n`~\u002F.claude\u002Fskills\u002Fbs-score` applies to every project; `.claude\u002Fskills\u002Fbs-score` is checked into one\nrepository. Keep the folder name `bs-score` — it is the skill's name.\n\n**The command** — one line, and nothing here vendors it:\n\n```bash\nuv tool install git+https:\u002F\u002Fgithub.com\u002Falexhawat\u002Fbs-score   # puts bs-score on PATH\n```\n\n## Canonical pack\n\nThis wrapper belongs to [alexhawat\u002Fbs-score](https:\u002F\u002Fgithub.com\u002Falexhawat\u002Fbs-score).\n\n1. Read **`SKILL.md` at the repository root** — the two-pass workflow, the\n   per-review-type checklists, and the hard rules live there.\n2. Emit findings JSON matching `findings.schema.json` (no `score` \u002F `points`).\n3. Score it:\n\n```bash\nbs-score findings.json --repo-root .          # installed\nuv run bs-score findings.json --repo-root .   # from a clone of the repo\n```\n\nEvery install option is in the\n[repository README](https:\u002F\u002Fgithub.com\u002Falexhawat\u002Fbs-score#install).\n\nQuotes are verified against the files they name before anything is scored, so\n`--repo-root` must point at the tree you audited. For prompts and review bodies,\nadd `--sources` (`bs-score` below is the same command):\n\n```bash\nbs-score findings.json --sources prompts\u002F                    # prompt audit\nbs-score findings.json --repo-root . --sources review.json   # review audit\n```\n\nFrom a clone, `python3 score.py findings.json` and `uv run bs-score …` do the same thing.\n\n## What it audits\n\n| `target_kind` | Scope | Weight profile |\n|---------------|-------|----------------|\n| `repo` | Docs claims **and** deep code | baseline |\n| `pr` \u002F `branch` | The diff and its callers | landing defects weigh more |\n| `review` | A PR review vs the diff | false claims and misses weigh more |\n| `skill` | Skill MD + the code it names | unimplemented claims weigh more |\n| `agent` | Agent \u002F persona configs | unsafe instructions weigh most |\n| `prompt` | One or more prompts | injection and secrets weigh most |\n| `docs` | One document, claims only | wrong claims weigh most |\n\n## Fixture examples\n\nRun from a clone of the repo:\n\n```bash\nuv run bs-score examples\u002Ffindings.valid.json  --repo-root examples\u002Ffixture-repo   # 17\nuv run bs-score examples\u002Ffindings.review.json --repo-root examples\u002Ffixture-repo \\\n    --sources examples\u002Ffixture-review\u002Freview.json                                # 10\nuv run bs-score examples\u002Ffindings.skill.json  --repo-root examples\u002Ffixture-repo   # 7\nuv run bs-score examples\u002Ffindings.agent.json  --repo-root examples\u002Ffixture-repo   # 6\nuv run bs-score examples\u002Ffindings.prompt.json --sources examples\u002Ffixture-prompts  # 18\nuv run bs-score examples\u002Ffindings.hallucinated.json \\\n    --repo-root examples\u002Ffixture-repo                                            # 0\n```\n\nThat last one is the point: a fabricated audit scores zero because none of its\nquotes exist.\n\nNever invent the score — report only what `bs-score` printed.\n",{"name":5,"license":15,"description":7,"allowed-tools":24},"Read, Grep, Glob, Bash","main","ef548f3930ccbbf26b37cfb5d93c9096e791b3a0","agents\u002Fclaude",0,"https:\u002F\u002Fgithub.com\u002Falexhawat\u002Fbs-score","https:\u002F\u002Fgithub.com\u002Falexhawat","AI-native engineer in Amsterdam. Building exclusively with agentic AI.","2026-11-14 14:17:15",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add alexhawat\u002Fbs-score --skill bs-score",{"tool":39,"command":40},"bunx","bunx skills add alexhawat\u002Fbs-score --skill bs-score",{"tool":42,"command":43},"pnpm","pnpm dlx skills add alexhawat\u002Fbs-score --skill bs-score","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Falexhawat\u002Fbs-score\u002Fblob\u002Fmain\u002Fagents\u002Fclaude\u002FSKILL.md",true,[47],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"README.md","REFERENCE","参考文档",741,"https:\u002F\u002Fgithub.com\u002Falexhawat\u002Fbs-score\u002Fblob\u002Fmain\u002Fagents\u002Fclaude\u002FREADME.md",[54,61,67,72,77,82],{"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},"01M7CP5CJ9YWBGHSNN2BEJ48DP","demo-deploy","Fixture skill whose documentation does not match its script.","https:\u002F\u002Fgithub.com\u002Falexhawat\u002Fbs-score\u002Fblob\u002Fmain\u002Fexamples\u002Ffixture-repo\u002Fskills\u002Fdemo-deploy\u002FSKILL.md",[],[],{"skillNo":62,"name":63,"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":64,"categories":65,"keywords":66,"publishedAt":19},"01M7CP5AP1HXHJSTC5SFKM0FWT","checklists","https:\u002F\u002Fgithub.com\u002Falexhawat\u002Fbs-score\u002Fblob\u002Fmain\u002Fchecklists\u002Fskill.md",[],[],{"skillNo":68,"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":69,"categories":70,"keywords":71,"publishedAt":19},"01M7CP57CWM7V2K96MHVGEKP7R","https:\u002F\u002Fgithub.com\u002Falexhawat\u002Fbs-score\u002Fblob\u002Fmain\u002Fagents\u002Fopencode\u002FSKILL.md",[],[],{"skillNo":73,"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":74,"categories":75,"keywords":76,"publishedAt":19},"01M7CP53XRESW01BSV4SPE4R5M","https:\u002F\u002Fgithub.com\u002Falexhawat\u002Fbs-score\u002Fblob\u002Fmain\u002Fagents\u002Fopenclaw\u002FSKILL.md",[],[],{"skillNo":78,"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":79,"categories":80,"keywords":81,"publishedAt":19},"01M7CP50RSG8RBAK3JNZRQ947C","https:\u002F\u002Fgithub.com\u002Falexhawat\u002Fbs-score\u002Fblob\u002Fmain\u002Fagents\u002Fhermes\u002FSKILL.md",[],[],{"skillNo":83,"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":84,"categories":85,"keywords":86,"publishedAt":19},"01M7CP4X3AJ0TFTXQEW2420Y3K","https:\u002F\u002Fgithub.com\u002Falexhawat\u002Fbs-score\u002Fblob\u002Fmain\u002Fagents\u002Fgrok\u002FSKILL.md",[],[]]