Command Claude Code
Identify skills injected where not needed, propose regex and description tightening.
32 3d ago A 18 tokens
original MIT
32Stars on the repository
59Mods indexed here, across every type
3d agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown
announce
02Command Claude Code
Draft X/Twitter announcement post (or thread) for the latest plugin release.
32 3d ago A 17 tokens
original MIT
audit-plugin
03Command Claude Code
Deep quality audit of all skills, agents, and commands for inconsistencies, gaps, duplication, and token waste.
32 3d ago A 25 tokens
original MIT
Command Claude Code
Analyze negative-signal sessions for a skill, identify failure patterns, propose and apply fixes.
32 3d ago A 22 tokens
original MIT
eval-skills
05Command Claude Code
Eval all skills with sufficient data, rank by procedure-following score, identify candidates for optimization.
32 3d ago A 22 tokens
original MIT
evolve-skill
06Command Claude Code
Run the full skill evolution pipeline -- harvest sessions, discover signals, build golden dataset, eval baseline, evolve via DSPy, compare scores.
32 3d ago A 32 tokens
original MIT
Command Claude Code
Prune stale entries from the whetstone sync decision log.
32 3d ago A 17 tokens
original MIT
release
08Command Claude Code
Bump version, commit, push, mirror to ai-skills, and update local plugin.
32 3d ago A 20 tokens
original MIT
skillopt
09Command Claude Code
Run the SkillOpt process-skill optimizer (offline, local). Default prints the exact bare-terminal command (safe); --run executes it in-session (hardened + checkpointed).
32 3d ago C 40 tokens
original MIT
Command Claude Code
Analyze reference repos and recommend skill/agent/command improvements based on cross-repo patterns.
32 3d ago A 22 tokens
original MIT
triage-prs
11Command Claude Code
Triage all open PRs with parallel agents, label, group, and review one-by-one.
32 3d ago A 24 tokens
copy · 91% MIT
write-skill
12Command Claude Code
Author a new skill from scratch with paired trigger fixtures and full validation. Use when adding a skill that has no upstream skills.sh source (discipline, meta, or internal-pattern skills).
32 3d ago A 41 tokens
original MIT
Skill Claude CodeCodex
Fetches top-rated skills from skills.sh, analyzes them, and synthesizes one token-efficient skill combining the best elements. Use when the user asks to "distill skills for X", "find and combine skills for X", "synthesize skills", "merge skills", "make a skill for X from skills.sh", "update distilled skill", or…
32 3d ago A 91 tokens
original MIT
Instructions file CodexOpenCode
Instructions for iliaal/whetstone, covering whetstone, repository structure, working agreement, versioning and naming convention.
32 3d ago A 5,645 tokens
original MIT
Instructions file
Instructions for iliaal/whetstone, a project described as: AI-powered development tools. 19 agents, 22 commands, 32 skills, 1 hook, 1 MCP server for code review, research, design, and workflow automation.
32 3d ago A 3 tokens
copy · 100% MIT
code-review
16Skill Claude CodeCodex
Performs two-stage code reviews (spec compliance, then code quality) with severity-ranked findings. Use when asked to "review code", "review this PR", "check this diff", "review before merge", or mentions reviewing, auditing, or critiquing code changes, pull requests, or diffs.
32 3d ago A 65 tokens
original MIT
debugging
17Skill Claude CodeCodex
Systematic root-cause debugging: reproduce, investigate, hypothesize, fix with verification. Use when asked to "debug this", "fix this bug", "why is this failing", "troubleshoot", or mentions errors, stack traces, broken tests, flaky tests, regressions, or unexpected behavior.
32 3d ago A 65 tokens
original MIT
Skill Claude CodeCodex
Defensive Bash scripting for Linux: safe foundations, argument parsing, production patterns, ShellCheck compliance. Use when writing "bash script", "shell script", "linux automation", "system script", "cron job", "deployment script", "CLI tool in bash", or "automate with bash".
32 3d ago C 66 tokens
original MIT
md-docs
19Skill Claude CodeCodex
Manages project documentation: AGENTS.md, README.md, and CONTRIBUTING.md. Use when asked to "update README", "update agents", "init agents", "create AGENTS.md", "update AGENTS.md", "update CONTRIBUTING", "update context files", or "init context". Not for general markdown editing.
32 3d ago A 70 tokens
original MIT
Skill Claude CodeCodex
Enhanced reasoning patterns via slash commands (/think, /verify, /adversarial, /edge, /compare, /confidence, /budget, /constrain, /json, /flip, /assumptions, /tensions, /analyze, /trade) or natural language ("argue against", "what could break", "show reasoning", "deep review", "meta-prompts", "thinking modes"…
32 3d ago A 104 tokens
original MIT
Skill Claude CodeCodex
Node.js backend patterns: framework selection, layered architecture, TypeScript, validation, error handling, security, production deployment. Use when building REST APIs, Express/Fastify servers, microservices, or server-side TypeScript.
32 3d ago A 50 tokens
original MIT
php-laravel
22Skill Claude CodeCodex
Modern PHP 8.2+ and Laravel patterns: architecture, Eloquent, queues, Pest testing. Use when asked to "write PHP", "build a Laravel app", "fix Eloquent query", "add a queue job", "write a Pest test", or mentions PHP, Laravel, Eloquent, Blade, artisan, or migrations.
32 3d ago A 74 tokens
original MIT
pinescript
23Skill Claude CodeCodex
Pine Script v6 patterns: syntax rules, performance, debugging, backtesting, visualization. Use when asked to "write a Pine Script", "create an indicator", "build a strategy", "fix Pine code", or mentions PineScript, TradingView, indicator, strategy, or backtest.
32 3d ago A 64 tokens
original MIT
planning
24Skill Claude CodeCodex
Software implementation planning with file-based persistence (taskplan.md, findings.md, progress.md). Use when asked to "plan", "break down this feature", "implementation plan", or starting complex tasks needing >5 tool calls. Apply proactively before non-trivial coding.
32 3d ago A 55 tokens
original MIT
At most 3 mods per repository are shown here — the rest are on their repository pages: