[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-juliusbrussee-caveman-commit-en":3,"guides-for-juliusbrussee-caveman-commit":503,"similar-k17bwzaz0dtqsqrjc1gqvqq22s86mcth-en":504},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":245,"isFallback":227,"parentExtension":250,"providers":305,"relations":309,"repo":310,"tags":500,"workflow":501},1778691765524.3743,"k17bwzaz0dtqsqrjc1gqvqq22s86mcth",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"Ultra-compressed commit message generator. Cuts noise from commit messages while preserving intent and reasoning. Conventional Commits format. Subject ≤50 chars, body only when \"why\" isn't obvious. Use when user says \"write a commit\", \"commit message\", \"generate commit\", \"/commit\", or invokes /caveman-commit. Auto-triggers when staging changes.\n",{"claudeCode":12},"juliusbrussee/caveman","caveman-commit","https://github.com/juliusbrussee/caveman",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":225,"workflow":243},1778691948611.4563,"kn72yfjrg27pq3ex8yjxbfzh4x86nsk5","en",{"checks":20,"evaluatedAt":193,"extensionSummary":194,"features":195,"nonGoals":201,"promptVersionExtension":206,"promptVersionScoring":207,"purpose":208,"rationale":209,"score":210,"summary":211,"tags":212,"targetMarket":218,"tier":219,"useCases":220},[21,26,29,32,36,39,44,48,51,54,58,62,65,69,72,75,78,81,84,87,91,95,99,104,108,111,114,117,121,124,127,130,133,136,139,143,147,151,154,158,161,164,167,170,174,177,180,183,186,190],{"category":22,"check":23,"severity":24,"summary":25},"Practical Utility","Problem relevance","pass","The description clearly identifies the problem of generating ultra-compressed commit messages that preserve intent and reasoning, and states the use case for conventional commits.",{"category":22,"check":27,"severity":24,"summary":28},"Unique selling proposition","The skill offers significant value over a simple prompt by strictly enforcing Conventional Commits format, character limits, and specific rules for body content, which goes beyond default LLM behavior.",{"category":22,"check":30,"severity":24,"summary":31},"Production readiness","The skill is production-ready as it focuses on generating commit messages, a well-defined task, and its output is a code block ready for use, without missing any crucial components for its stated purpose.",{"category":33,"check":34,"severity":24,"summary":35},"Scope","Single responsibility principle","The skill adheres to the single responsibility principle by focusing solely on generating commit messages based on diffs and user intent.",{"category":33,"check":37,"severity":24,"summary":38},"Description quality","The displayed description is concise, accurate, and clearly reflects the skill's functionality and invocation triggers.",{"category":40,"check":41,"severity":42,"summary":43},"Invocation","Scoped tools","not_applicable","This is a skill, not a tool-based extension, so the concept of scoped tools does not apply.",{"category":45,"check":46,"severity":42,"summary":47},"Documentation","Configuration & parameter reference","The skill does not expose configurable parameters or options beyond its core function, making this check not applicable.",{"category":33,"check":49,"severity":24,"summary":50},"Tool naming","The skill is invoked via natural language triggers and a `/caveman-commit` command, which are descriptive and contextually appropriate.",{"category":33,"check":52,"severity":24,"summary":53},"Minimal I/O surface","The skill takes implicit input (staged changes) and outputs a formatted commit message string, which is minimal and appropriate for the task.",{"category":55,"check":56,"severity":24,"summary":57},"License","License usability","The extension is licensed under the MIT license, which is a permissive open-source license, clearly stated in the LICENSE file.",{"category":59,"check":60,"severity":24,"summary":61},"Maintenance","Commit recency","The latest commit was on 2026-05-12, which is within the last 3 months, indicating active maintenance.",{"category":59,"check":63,"severity":42,"summary":64},"Dependency Management","The skill does not appear to use any third-party dependencies, so dependency management is not applicable.",{"category":66,"check":67,"severity":42,"summary":68},"Security","Secret Management","The skill does not handle any secrets or sensitive credentials.",{"category":66,"check":70,"severity":24,"summary":71},"Injection","The skill's logic for generating commit messages is based on interpreting diffs and explicit rules, not loading untrusted third-party data or instructions.",{"category":66,"check":73,"severity":24,"summary":74},"Transitive Supply-Chain Grenades","The skill operates on local diffs and generates text, with no runtime loading or execution of external code or data.",{"category":66,"check":76,"severity":24,"summary":77},"Sandbox Isolation","The skill only generates text output and does not interact with the file system or external resources, thus maintaining sandbox isolation.",{"category":66,"check":79,"severity":24,"summary":80},"Sandbox escape primitives","There are no detached process spawns or deny-retry loops as the skill is purely text generation.",{"category":66,"check":82,"severity":24,"summary":83},"Data Exfiltration","The skill does not perform any outbound calls or interact with confidential data.",{"category":66,"check":85,"severity":24,"summary":86},"Hidden Text Tricks","The bundled content is free of hidden-steering tricks and uses clean printable ASCII.",{"category":88,"check":89,"severity":24,"summary":90},"Hooks","Opaque code execution","The skill's logic is implemented in readable Markdown and does not involve obfuscated code or runtime fetching.",{"category":92,"check":93,"severity":24,"summary":94},"Portability","Structural Assumption","The skill assumes access to Git diffs but does not make assumptions about user project file layout beyond that.",{"category":96,"check":97,"severity":24,"summary":98},"Trust","Issues Attention","With 66 issues opened and 70 closed in the last 90 days, the closure rate is approximately 51%, indicating good maintainer engagement.",{"category":100,"check":101,"severity":102,"summary":103},"Versioning","Release Management","info","The project has a MIT License file, but no explicit versioning or changelog is detected in the SKILL.md or other manifests.",{"category":105,"check":106,"severity":42,"summary":107},"Code Execution","Validation","The skill's primary function is text generation based on LLM interpretation and fixed rules, not processing structured input requiring schema validation.",{"category":66,"check":109,"severity":24,"summary":110},"Unguarded Destructive Operations","The skill is purely analytical and does not perform any destructive operations.",{"category":105,"check":112,"severity":24,"summary":113},"Error Handling","The skill generates text and relies on the LLM's ability to handle errors; no explicit error paths requiring structured reporting are present.",{"category":105,"check":115,"severity":42,"summary":116},"Logging","As a read-only text generation skill, it does not perform actions or outbound calls that require local audit logging.",{"category":118,"check":119,"severity":42,"summary":120},"Compliance","GDPR","The skill does not operate on personal data; it processes code diffs.",{"category":118,"check":122,"severity":24,"summary":123},"Target market","The skill is language-agnostic and operates on code, making it globally applicable.",{"category":92,"check":125,"severity":24,"summary":126},"Runtime stability","The skill relies on standard LLM capabilities and markdown processing, making it platform-agnostic.",{"category":45,"check":128,"severity":24,"summary":129},"README","The README file clearly states the skill's purpose, how to invoke it, and provides examples.",{"category":33,"check":131,"severity":42,"summary":132},"Tool surface size","This is a skill with a single function triggered by natural language, not a collection of tools.",{"category":40,"check":134,"severity":42,"summary":135},"Overlapping near-synonym tools","As a single-function skill, there are no overlapping tools or commands.",{"category":45,"check":137,"severity":24,"summary":138},"Phantom features","All features advertised in the README and SKILL.md, such as Conventional Commits formatting and specific rules, are implemented.",{"category":140,"check":141,"severity":24,"summary":142},"Install","Installation instruction","The README provides clear invocation instructions, including a direct command and natural language triggers.",{"category":144,"check":145,"severity":42,"summary":146},"Errors","Actionable error messages","The skill's primary output is a commit message; explicit error paths requiring user remediation are not applicable to its core function.",{"category":148,"check":149,"severity":42,"summary":150},"Execution","Pinned dependencies","The skill does not rely on external dependencies or scripts requiring pinning.",{"category":33,"check":152,"severity":42,"summary":153},"Dry-run preview","The skill is purely text generation and does not perform state-changing operations or outbound calls requiring a dry-run mode.",{"category":155,"check":156,"severity":42,"summary":157},"Protocol","Idempotent retry & timeouts","The skill performs a single text generation task and does not involve remote calls or state-changing operations.",{"category":118,"check":159,"severity":42,"summary":160},"Telemetry opt-in","The skill does not emit any telemetry.",{"category":40,"check":162,"severity":24,"summary":163},"Precise Purpose","The description clearly states the skill generates ultra-compressed, Conventional Commits formatted commit messages, specifies the subject length and body conditions, and lists explicit invocation triggers and boundaries.",{"category":40,"check":165,"severity":24,"summary":166},"Concise Frontmatter","The frontmatter is concise and effectively summarizes the core capability and triggers within a reasonable character limit.",{"category":45,"check":168,"severity":24,"summary":169},"Concise Body","The SKILL.md body is concise, under 500 lines, and focuses on rules and examples, delegating deeper material implicitly.",{"category":171,"check":172,"severity":24,"summary":173},"Context","Progressive Disclosure","The SKILL.md is concise and focuses on the core procedure, with links to examples and the full instruction set, indicating good progressive disclosure.",{"category":171,"check":175,"severity":42,"summary":176},"Forked exploration","This skill is a short-form generator and does not involve deep exploration or code review, making `context: fork` not applicable.",{"category":22,"check":178,"severity":24,"summary":179},"Usage examples","The SKILL.md and README provide clear, end-to-end examples for generating commit messages with both simple and breaking changes.",{"category":22,"check":181,"severity":24,"summary":182},"Edge cases","The SKILL.md documents failure modes such as the need for body content for breaking changes and reverts, and lists boundaries like not running `git commit`.",{"category":105,"check":184,"severity":42,"summary":185},"Tool Fallback","The skill does not rely on external tools like MCP servers; it operates internally.",{"category":187,"check":188,"severity":24,"summary":189},"Safety","Halt on unexpected state","The skill's instructions imply that it halts if it cannot process the diff or if explicit commands like 'stop caveman-commit' are given, maintaining a safe state.",{"category":92,"check":191,"severity":24,"summary":192},"Cross-skill coupling","The skill operates independently and does not implicitly rely on other skills.",1778691948499,"This skill generates commit messages in the Conventional Commits format, focusing on brevity and clarity. It enforces specific rules for subject lines and body content, only including a body when necessary for explanation, such as for breaking changes or complex reasoning. The skill operates based on code diffs and user intent, outputting the message as a code block ready for use.",[196,197,198,199,200],"Generates ultra-compressed commit messages","Enforces Conventional Commits format","Limits subject line length (≤50 chars)","Conditionally includes commit body (only when 'why' is non-obvious)","Auto-triggers on staging changes",[202,203,204,205],"Running `git commit` or staging files","Amending existing commits","Generating commit messages with AI attribution or verbose explanations","Using emoji unless project convention requires it","3.0.0","4.4.0","To streamline the commit process by generating terse, informative, and correctly formatted commit messages, saving developers time and improving code history quality.","The skill demonstrates exceptional quality across all aspects, with no critical or warning findings. Minor info findings related to versioning do not impact its overall high score.",98,"A highly polished and effective skill for generating concise, Conventional Commits-formatted commit messages.",[213,214,215,216,217],"git","commit","conventional-commits","developer-tools","code-generation","global","verified",[221,222,223,224],"Generating a commit message after staging changes","Creating commit messages that adhere to Conventional Commits standards","Writing commit messages that explain the 'why' behind a change, not just the 'what'","When a user requests to 'write a commit' or 'generate commit message'",{"codeQuality":226,"collectedAt":228,"documentation":229,"maintenance":232,"popularity":238,"security":239,"testCoverage":242},{"hasLockfile":227},false,1778691917445,{"descriptionLength":230,"readmeSize":231},347,10896,{"closedIssues90d":233,"forks":234,"hasChangelog":227,"openIssues90d":235,"pushedAt":236,"stars":237},70,3292,66,1778615088000,59509,{"npmDownloads":8},{"hasNpmPackage":240,"license":241,"smitheryVerified":227},true,"MIT",{"hasCi":240,"hasTests":240},{"updatedAt":244},1778691948611,{"basePath":246,"githubOwner":247,"githubRepo":248,"locale":18,"slug":13,"type":249},"skills/caveman-commit","juliusbrussee","caveman","skill",{"_creationTime":251,"_id":252,"community":253,"display":254,"identity":258,"parentExtension":261,"providers":292,"relations":300,"tags":301,"workflow":302},1778691765524.373,"k170g496f5ze5hv8xa2e7b91ex86mz9m",{"reviewCount":8},{"description":255,"installMethods":256,"name":257,"sourceUrl":14},"Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.",{"claudeCode":248},"Caveman",{"basePath":259,"githubOwner":247,"githubRepo":248,"locale":18,"slug":248,"type":260},"","plugin",{"_creationTime":262,"_id":263,"community":264,"display":265,"identity":268,"providers":270,"relations":285,"tags":287,"workflow":288},1778691765524.3728,"k17dcfwpwpzjc43zt2qawvft3h86mmse",{"reviewCount":8},{"description":266,"installMethods":267,"name":248,"sourceUrl":14},"Ultra-compressed communication mode for Claude Code. Cuts ~75% of tokens while keeping full technical accuracy.",{"claudeCode":12},{"basePath":259,"githubOwner":247,"githubRepo":248,"locale":18,"slug":248,"type":269},"marketplace",{"evaluate":271,"extract":279},{"promptVersionExtension":272,"promptVersionScoring":207,"score":273,"tags":274,"targetMarket":218,"tier":219},"3.1.0",92,[275,276,277,278,216],"compression","llm","productivity","token-reduction",{"commitSha":280,"marketplace":281,"plugin":283},"HEAD",{"name":248,"pluginCount":282},1,{"mcpCount":8,"provider":284,"skillCount":8},"classify",{"repoId":286},"kd7890f0sfy0ymf1pakpx7vqch86nmew",[275,216,276,277,278],{"evaluatedAt":289,"extractAt":290,"updatedAt":291},1778691801317,1778691765524,1778692173865,{"evaluate":293,"extract":297},{"promptVersionExtension":206,"promptVersionScoring":207,"score":294,"tags":295,"targetMarket":218,"tier":219},99,[275,276,296,216,277],"text",{"commitSha":280,"license":241,"plugin":298},{"mcpCount":8,"provider":284,"skillCount":299},6,{"parentExtensionId":263,"repoId":286},[275,216,276,277,296],{"evaluatedAt":303,"extractAt":290,"updatedAt":304},1778691819811,1778692174193,{"evaluate":306,"extract":308},{"promptVersionExtension":206,"promptVersionScoring":207,"score":210,"tags":307,"targetMarket":218,"tier":219},[213,214,215,216,217],{"commitSha":280},{"parentExtensionId":252,"repoId":286},{"_creationTime":311,"_id":286,"identity":312,"providers":313,"workflow":495},1778691760140.7458,{"githubOwner":247,"githubRepo":248,"sourceUrl":14},{"classify":314,"discover":479,"extract":482,"github":483,"npm":494},{"commitSha":280,"extensions":315},[316,326,337,381,390,398,423,432,438,447,456,468],{"basePath":317,"displayName":318,"installMethods":319,"rationale":320,"selectedPaths":321,"source":325,"sourceLanguage":18,"type":269},".agents/plugins","caveman-repo",{"claudeCode":12},"marketplace.json at .agents/plugins/marketplace.json",[322],{"path":323,"priority":324},"marketplace.json","mandatory","rule",{"basePath":259,"description":266,"displayName":248,"installMethods":327,"rationale":328,"selectedPaths":329,"source":325,"sourceLanguage":18,"type":269},{"claudeCode":12},"marketplace.json at .claude-plugin/marketplace.json",[330,332,334],{"path":331,"priority":324},".claude-plugin/marketplace.json",{"path":333,"priority":324},"README.md",{"path":335,"priority":336},"LICENSE","high",{"basePath":259,"description":255,"displayName":248,"installMethods":338,"rationale":339,"selectedPaths":340,"source":325,"sourceLanguage":18,"type":260},{"claudeCode":248},"plugin manifest at .claude-plugin/plugin.json (coalesced with duplicate plugin at plugins/caveman)",[341,343,344,345,348,350,352,354,356,358,360,362,364,366,369,371,373,375,377,379],{"path":342,"priority":324},".claude-plugin/plugin.json",{"path":333,"priority":324},{"path":335,"priority":336},{"path":346,"priority":347},"skills/cavecrew/SKILL.md","medium",{"path":349,"priority":347},"skills/caveman/SKILL.md",{"path":351,"priority":347},"skills/caveman-commit/SKILL.md",{"path":353,"priority":347},"skills/caveman-compress/SKILL.md",{"path":355,"priority":347},"skills/caveman-help/SKILL.md",{"path":357,"priority":347},"skills/caveman-review/SKILL.md",{"path":359,"priority":347},"skills/caveman-stats/SKILL.md",{"path":361,"priority":336},"agents/cavecrew-builder.md",{"path":363,"priority":336},"agents/cavecrew-investigator.md",{"path":365,"priority":336},"agents/cavecrew-reviewer.md",{"path":367,"priority":368},"bin/install.js","low",{"path":370,"priority":368},"bin/lib/openclaw.js",{"path":372,"priority":368},"bin/lib/settings.js",{"path":374,"priority":336},"commands/caveman-commit.toml",{"path":376,"priority":336},"commands/caveman-init.toml",{"path":378,"priority":336},"commands/caveman-review.toml",{"path":380,"priority":336},"commands/caveman.toml",{"basePath":382,"description":383,"displayName":384,"installMethods":385,"rationale":386,"selectedPaths":387,"source":325,"sourceLanguage":18,"type":249},".junie/skills/cavecrew","Decision guide for delegating to caveman-style subagents. Tells the main thread WHEN to spawn `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit), or `cavecrew-reviewer` (diff review) instead of doing the work inline or using vanilla `Explore`. Subagent output is caveman-compressed so the tool-result injected back into main context is ~60% smaller — main context lasts longer across long sessions. Trigger: \"delegate to subagent\", \"use cavecrew\", \"spawn investigator/builder/reviewer\", \"save context\", \"compressed agent output\".\n","cavecrew",{"claudeCode":12},"SKILL.md frontmatter at .junie/skills/cavecrew/SKILL.md (coalesced with duplicate skill at .agents/skills/cavecrew, skills/cavecrew, .roo/skills/cavecrew, .kiro/skills/cavecrew, plugins/caveman/skills/cavecrew)",[388],{"path":389,"priority":324},"SKILL.md",{"basePath":391,"description":392,"displayName":248,"installMethods":393,"rationale":394,"selectedPaths":395,"source":325,"sourceLanguage":18,"type":249},"skills/caveman","Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says \"caveman mode\", \"talk like caveman\", \"use caveman\", \"less tokens\", \"be brief\", or invokes /caveman. Also auto-triggers when token efficiency is requested.\n",{"claudeCode":12},"SKILL.md frontmatter at skills/caveman/SKILL.md (coalesced with duplicate skill at plugins/caveman/skills/caveman)",[396,397],{"path":389,"priority":324},{"path":333,"priority":336},{"basePath":399,"description":400,"displayName":401,"installMethods":402,"rationale":403,"selectedPaths":404,"source":325,"sourceLanguage":18,"type":249},"skills/caveman-compress","Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens. Preserves all technical substance, code, URLs, and structure. Compressed version overwrites the original file. Human-readable backup saved as FILE.original.md. Trigger: /caveman-compress FILEPATH or \"compress memory file\"\n","caveman-compress",{"claudeCode":12},"SKILL.md frontmatter at skills/caveman-compress/SKILL.md (coalesced with duplicate skill at plugins/caveman/skills/caveman-compress)",[405,406,407,409,411,413,415,417,419,421],{"path":389,"priority":324},{"path":333,"priority":336},{"path":408,"priority":347},"SECURITY.md",{"path":410,"priority":368},"scripts/__init__.py",{"path":412,"priority":368},"scripts/__main__.py",{"path":414,"priority":368},"scripts/benchmark.py",{"path":416,"priority":368},"scripts/cli.py",{"path":418,"priority":368},"scripts/compress.py",{"path":420,"priority":368},"scripts/detect.py",{"path":422,"priority":368},"scripts/validate.py",{"basePath":424,"description":425,"displayName":426,"installMethods":427,"rationale":428,"selectedPaths":429,"source":325,"sourceLanguage":18,"type":249},"skills/caveman-stats","Show real token usage and estimated savings for the current session. Reads directly from the Claude Code session log — no AI estimation. Triggers on /caveman-stats. Output is injected by the mode-tracker hook; the model itself does not compute the numbers.\n","caveman-stats",{"claudeCode":12},"SKILL.md frontmatter at skills/caveman-stats/SKILL.md (coalesced with duplicate skill at plugins/caveman/skills/caveman-stats)",[430,431],{"path":389,"priority":324},{"path":333,"priority":336},{"basePath":246,"description":10,"displayName":13,"installMethods":433,"rationale":434,"selectedPaths":435,"source":325,"sourceLanguage":18,"type":249},{"claudeCode":12},"SKILL.md frontmatter at skills/caveman-commit/SKILL.md",[436,437],{"path":389,"priority":324},{"path":333,"priority":336},{"basePath":439,"description":440,"displayName":441,"installMethods":442,"rationale":443,"selectedPaths":444,"source":325,"sourceLanguage":18,"type":249},"skills/caveman-help","Quick-reference card for all caveman modes, skills, and commands. One-shot display, not a persistent mode. Trigger: /caveman-help, \"caveman help\", \"what caveman commands\", \"how do I use caveman\".\n","caveman-help",{"claudeCode":12},"SKILL.md frontmatter at skills/caveman-help/SKILL.md",[445,446],{"path":389,"priority":324},{"path":333,"priority":336},{"basePath":448,"description":449,"displayName":450,"installMethods":451,"rationale":452,"selectedPaths":453,"source":325,"sourceLanguage":18,"type":249},"skills/caveman-review","Ultra-compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment is one line: location, problem, fix. Use when user says \"review this PR\", \"code review\", \"review the diff\", \"/review\", or invokes /caveman-review. Auto-triggers when reviewing pull requests.\n","caveman-review",{"claudeCode":12},"SKILL.md frontmatter at skills/caveman-review/SKILL.md",[454,455],{"path":389,"priority":324},{"path":333,"priority":336},{"basePath":259,"description":457,"displayName":458,"installMethods":459,"license":241,"rationale":460,"selectedPaths":461,"source":325,"sourceLanguage":18,"type":467},"Caveman installer — detects your AI coding agents and installs caveman for each one.","caveman-installer",{"npm":458},"cli ecosystem detected at /",[462,464,465,466],{"path":463,"priority":324},"package.json",{"path":333,"priority":324},{"path":335,"priority":336},{"path":367,"priority":347},"cli",{"basePath":469,"description":470,"displayName":471,"installMethods":472,"license":241,"rationale":473,"selectedPaths":474,"source":325,"sourceLanguage":18,"type":467},"src/mcp-servers/caveman-shrink","MCP proxy that compresses prose fields (tool descriptions, etc.) using caveman rules. Same accuracy, fewer context tokens.","caveman-shrink",{"npm":471},"cli ecosystem detected at src/mcp-servers/caveman-shrink",[475,476,477],{"path":463,"priority":324},{"path":333,"priority":324},{"path":478,"priority":347},"index.js",{"sources":480},[481],"manual",{"npmPackage":458},{"closedIssues90d":233,"description":484,"forks":234,"homepage":485,"license":241,"openIssues90d":235,"pushedAt":236,"readmeSize":231,"stars":237,"topics":486},"🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman","https://getcaveman.dev/",[487,488,248,489,490,276,491,492,249,493],"ai","anthropic","claude","claude-code","meme","prompt-engineering","tokens",{"downloads":8},{"classifiedAt":496,"discoverAt":497,"extractAt":498,"githubAt":498,"npmAt":499,"updatedAt":496},1778691765329,1778691760140,1778691762475,1778691764072,[217,214,215,216,213],{"evaluatedAt":244,"extractAt":290,"updatedAt":502},1778692175229,[],[505,532,562,587,611,638],{"_creationTime":506,"_id":507,"community":508,"display":509,"identity":515,"providers":519,"relations":526,"tags":528,"workflow":529},1778695021936.555,"k1715rn9402s29yge55y9nt0x986n2tf",{"reviewCount":8},{"description":510,"installMethods":511,"name":513,"sourceUrl":514},"Build a composable CLI for Codex from API docs, an OpenAPI spec, existing curl examples, an SDK, a web app, an admin tool, or a local script. Use when the user wants Codex to create a command-line tool that can run from any repo, expose composable read/write commands, return stable JSON, manage auth, and pair with a companion skill.",{"claudeCode":512},"openai/skills","cli-creator","https://github.com/openai/skills",{"basePath":516,"githubOwner":517,"githubRepo":518,"locale":18,"slug":513,"type":249},"skills/.curated/cli-creator","openai","skills",{"evaluate":520,"extract":525},{"promptVersionExtension":206,"promptVersionScoring":207,"score":521,"tags":522,"targetMarket":218,"tier":219},100,[467,217,216,523,524],"codex","automation",{"commitSha":280},{"repoId":527},"kd75n2zj3yh472p25zffgycved86mnpx",[524,467,217,523,216],{"evaluatedAt":530,"extractAt":531,"updatedAt":530},1778695068759,1778695021936,{"_creationTime":533,"_id":534,"community":535,"display":536,"identity":542,"providers":547,"relations":554,"tags":557,"workflow":558},1778693661691.4363,"k178pmb87re7z9as1b8ky4h9m586ncf7",{"reviewCount":8},{"description":537,"installMethods":538,"name":540,"sourceUrl":541},"Rewrites commit messages so they sound like a careful human engineer wrote them. Strips AI/marketing slop (\"comprehensive solution\", \"robust implementation\", \"leverage\", \"enhance\", \"seamlessly\", \"This commit...\"). Keeps Conventional Commits format. Subject ≤72 chars (aim ≤50), imperative mood. Body only when \"why\" isn't obvious from the subject. Use when user says \"humanize commit\", \"de-slop commit message\", \"make this commit sound human\", \"/unslop-commit\", \"/commit\", \"write a commit\", or pastes a draft commit to clean up. Auto-triggers when staging changes.\n",{"claudeCode":539},"MohamedAbdallah-14/unslop","Unslop Commit","https://github.com/MohamedAbdallah-14/unslop",{"basePath":543,"githubOwner":544,"githubRepo":545,"locale":18,"slug":546,"type":249},"skills/unslop-commit","MohamedAbdallah-14","unslop","unslop-commit",{"evaluate":548,"extract":553},{"promptVersionExtension":206,"promptVersionScoring":207,"score":521,"tags":549,"targetMarket":218,"tier":219},[550,215,213,551,552],"commit-message","ai-writing","natural-language-processing",{"commitSha":280,"license":241},{"parentExtensionId":555,"repoId":556},"k177fsagh49r77m9y4755zc1mn86m1jm","kd727xcarpnqcat3wd68ms466s86mwkb",[551,550,215,213,552],{"evaluatedAt":559,"extractAt":560,"updatedAt":561},1778693755963,1778693661691,1778693924021,{"_creationTime":563,"_id":564,"community":565,"display":566,"identity":572,"providers":576,"relations":581,"tags":583,"workflow":584},1778696993586.706,"k1779v5xzekjg54smcwht7v0ys86n8gr",{"reviewCount":8},{"description":567,"installMethods":568,"name":570,"sourceUrl":571},"Create a git commit with a good message. Use when the user says \"commit\", \"save changes\", \"commit this\", or asks to create a commit after making code changes.",{"claudeCode":569},"SeifBenayed/claude-code-sdk","Git Commit","https://github.com/SeifBenayed/claude-code-sdk",{"basePath":573,"githubOwner":574,"githubRepo":575,"locale":18,"slug":214,"type":249},".claude/skills/commit","SeifBenayed","claude-code-sdk",{"evaluate":577,"extract":580},{"promptVersionExtension":206,"promptVersionScoring":207,"score":294,"tags":578,"targetMarket":218,"tier":219},[213,214,579,216,524],"code-review",{"commitSha":280,"license":241},{"repoId":582},"kd78s53c1852h5p7c3qem663xs86njab",[524,579,214,216,213],{"evaluatedAt":585,"extractAt":586,"updatedAt":585},1778697041232,1778696993586,{"_creationTime":588,"_id":589,"community":590,"display":591,"identity":597,"providers":601,"relations":605,"tags":607,"workflow":608},1778683644393.5747,"k173tvrre4r831n5s7459dt1kh86mahx",{"reviewCount":8},{"description":592,"installMethods":593,"name":595,"sourceUrl":596},"Helps write Git commit messages following the Conventional Commits specification. Use this skill when the user asks to commit changes, write commit messages, format commits, or mentions git commits.",{"claudeCode":594},"charon-fan/agent-playbook","commit-helper","https://github.com/charon-fan/agent-playbook",{"basePath":598,"githubOwner":599,"githubRepo":600,"locale":18,"slug":595,"type":249},"skills/commit-helper","charon-fan","agent-playbook",{"evaluate":602,"extract":604},{"promptVersionExtension":206,"promptVersionScoring":207,"score":294,"tags":603,"targetMarket":218,"tier":219},[213,214,215,216,277],{"commitSha":280},{"repoId":606},"kd7cf5d43dzccs0fw9c2rp131n86mrv4",[214,215,216,213,277],{"evaluatedAt":609,"extractAt":610,"updatedAt":609},1778683806742,1778683644393,{"_creationTime":612,"_id":613,"community":614,"display":615,"identity":621,"providers":625,"relations":631,"tags":634,"workflow":635},1778695548458.34,"k179qx0fzfrr8fgyqbnjvdsx2186nr79",{"reviewCount":8},{"description":616,"installMethods":617,"name":619,"sourceUrl":620},"Stage, commit, and amend changes with conventional commit messages. Covers reviewing changes, selective staging, writing descriptive commit messages using HEREDOC format, and verifying commit history. Use when saving a logical unit of work to version control, creating a commit with a conventional message, amending the most recent commit, or reviewing staged changes before committing.\n",{"claudeCode":618},"pjt222/agent-almanac","commit-changes","https://github.com/pjt222/agent-almanac",{"basePath":622,"githubOwner":623,"githubRepo":624,"locale":18,"slug":619,"type":249},"skills/commit-changes","pjt222","agent-almanac",{"evaluate":626,"extract":630},{"promptVersionExtension":206,"promptVersionScoring":207,"score":627,"tags":628,"targetMarket":218,"tier":219},97,[213,214,215,629,216],"version-control",{"commitSha":280},{"parentExtensionId":632,"repoId":633},"k170h0janaa9kwn7cfgfz2ykss86mmh9","kd7aryv63z61j39n2td1aeqkvh86mh12",[214,215,216,213,629],{"evaluatedAt":636,"extractAt":637,"updatedAt":636},1778696671599,1778695548458,{"_creationTime":639,"_id":640,"community":641,"display":642,"identity":647,"providers":651,"relations":656,"tags":659,"workflow":660},1778694480889.9531,"k17d8ykyvwpw9fz315jnqkzmbd86nhcq",{"reviewCount":8},{"description":643,"installMethods":644,"name":214,"sourceUrl":646},"Create well-formatted commits with conventional commit messages and emoji",{"claudeCode":645},"NeoLabHQ/context-engineering-kit","https://github.com/NeoLabHQ/context-engineering-kit",{"basePath":648,"githubOwner":649,"githubRepo":650,"locale":18,"slug":214,"type":249},"plugins/git/skills/commit","NeoLabHQ","context-engineering-kit",{"evaluate":652,"extract":655},{"promptVersionExtension":206,"promptVersionScoring":207,"score":653,"tags":654,"targetMarket":218,"tier":219},95,[213,214,215,216,524],{"commitSha":280},{"parentExtensionId":657,"repoId":658},"k178tq0e3kachgtfxf8zq5k2xn86nzb7","kd7a3rj13ezgx1wgm0jfh08hsx86n0sz",[524,214,215,216,213],{"evaluatedAt":661,"extractAt":662,"updatedAt":661},1778695081832,1778694480890]