Skill Claude CodeCodex
Autonomous fix-verify loop that keeps fixing violations until the file reaches Grade A (90+).
not rated 4
+1 7d ago A 27 tokens
original MIT
avvarre:garden
170Skill Claude CodeCodex
Audit .avvarre/ project memory for context drift, stale tasks, and conventions mismatches.
not rated 4
+1 7d ago A 25 tokens
original MIT
avvarre
171Skill Claude CodeCodex
Analyze code quality against Google style guides for 21 languages/formats. Fix-verify loops, compressed task sync, workspace heatmaps.
not rated 4
+1 7d ago A 31 tokens
original MIT
sakost/review-prod-ready-skill
Skill Claude CodeCodex
Use when comprehensive production-readiness code review is needed after implementation — dispatches up to 7 specialized parallel reviewers covering tests, plan completeness, architecture, complexity, DRY violations, suppressed warnings, and production readiness.
not rated 3 4mo ago A 46 tokens
original Apache-2.0
Skill Claude CodeCodex
Use when the user presents a vague, ambiguous, or underspecified task. Conducts structured multi-turn dialogue to extract true requirements with 95% clarity before any code is written.
not rated 3 2mo ago A 41 tokens
original MIT
Skill Claude CodeCodex
Use before starting any code generation task. Reads Hermes Agent's SOUL.md to dynamically adapt code style, comment tone, documentation voice, and architectural decisions to match the agent's defined persona.
not rated 3 2mo ago A 43 tokens
original MIT
skill-curator
175Skill Claude CodeCodex
Use after completing a complex task, fixing a tricky error, or discovering a reusable workflow. Analyzes the execution record, proposes skill improvements, and feeds into Hermes Agent's self-learning loop — the meta-skill that makes all other skills better.
not rated 3 2mo ago A 54 tokens
original MIT
harden
176Calvin-LLC/agentic-hardening-skill
Skill Claude CodeCodex
Evidence-driven codebase hardening. Audits security (OWASP Top 10:2025), supply chain (inventory vs SBOM vs SLSA v1.2), reliability (OTel + operational limits), tests (sandboxed tiers), and accessibility (WCAG 2.2 AA). Every finding is quoted, matrix-scored, and cited. Does not fix. Reports with file:line and a…
not rated 3 6d ago A 117 tokens
original MIT
scalpel
177Skill Claude CodeCodex
Surgical AI for your codebase. Plugs into any project, performs a 12-dimension diagnostic scan (git forensics, architecture, tech debt, security, infrastructure), delivers a Codebase Vitals health score, then assembles and manages an adaptive AI surgical team calibrated to YOUR project. Pendrive architecture — plug…
not rated 2 5mo ago A 98 tokens
original MIT
undercover
178Skill Claude CodeCodex
Strip AI signatures from staged files and commit messages before pushing. Removes verbose comments, AI-phrasing, emoji, placeholder TODOs, and passive commit subjects.
not rated 2 5mo ago A 35 tokens
original MIT
api-layer
179Skill Claude CodeCodex
API client architecture for React and Next.js — typed fetch wrappers, interceptors, retry with backoff, request cancellation, pagination patterns, file uploads, and Next.js API route handlers. Use when building API clients, data fetching layers, or integrating with backends.
not rated 2 4mo ago A 56 tokens
original MIT
core-web-vitals
180Skill Claude CodeCodex
Deep-dive into Core Web Vitals — LCP, INP, CLS diagnosis and fix recipes for React/Next.js. Specific patterns for each metric with measurement tools, thresholds, and real-world fixes. Use when pages are slow, Lighthouse scores are low, or search ranking is affected by performance.
not rated 2 4mo ago A 66 tokens
original MIT
seo-fundamentals
181Skill Claude CodeCodex
Frontend SEO for React and Next.js — Metadata API, meta tags, canonical URLs, Open Graph, Twitter cards, robots.txt, sitemap, SSR/SSG/ISR rendering strategy, heading hierarchy, and crawlability. Use when building pages, setting up metadata, or optimizing for search visibility.
not rated 2 4mo ago A 65 tokens
original MIT
phase-build
182Skill Claude CodeCodex
Orchestrate a full CADENCE phase build end-to-end — worktree isolation, wave-based subagent dispatch from the approved DRAFT, an independent reviewer per task, main-thread re-verification of every completion claim, a whole-branch review, the single-commit settle, and a PR carrying its changeset. Use when a DRAFT is…
not rated 2 7d ago A 103 tokens
original MIT
pr-land
183Skill Claude CodeCodex
Land a branch through cadence's protected-main pipeline — local preflight, commit hygiene, push, PR, ci-success babysitting with the known-flake protocol, consent-gated squash merge, and post-merge sync. Use when work is ready to land, the user says "land this", "open a PR", "merge when green", or a PR is sitting on…
not rated 2 7d ago A 80 tokens
original MIT
release-cut
184Skill Claude CodeCodex
Cut and verify a CADENCE release end-to-end — inventory unreleased phases, audit changesets, lockstep version bump, a full doc-sync verification pass (automated doc tests + manual stale-version-reference sweep), release PR, operator-triggered Release workflow, and independent npm/tag/GitHub verification. Use when the…
not rated 2 7d ago A 92 tokens
original MIT
omaromar9091/clean-architecture-skill
Skill Claude CodeCodex
Apply Robert C. Martin's Clean Architecture, SOLID, and component-decoupling principles when designing, reviewing, or refactoring code — scaled correctly to the size of the task so trivial changes don't get over-engineered. Use this whenever the user asks to design a new feature/service, review code for architectural…
not rated 2 1mo ago A 174 tokens
original MIT
bumfuzzle
186Skill Claude CodeCodex
Load it when working with Bumfuzzle, or when project has Bumfuzzle import. When you asked to create new rule, or trigger any validation or verification after task is done.
not rated 2 21d ago A 41 tokens
original MIT
Skill Claude CodeCodex
Audit professionnel complet d'un projet logiciel couvrant architecture, code mort, dette technique, dépendances, API, authentification, autorisation, sécurité applicative, CI/CD, performance, production et validation finale.
not rated 2 12d ago A 50 tokens
original MIT
aegis
188Skill Claude CodeCodex
Contract-driven, design-first quality guardrails for AI-assisted full-stack development. Prevents project chaos at scale by enforcing a five-layer protection system: Design → Contract → Implementation → Verification → PM. Use when: starting a new full-stack project, planning a non-trivial feature, dispatching…
not rated 2 5mo ago A 137 tokens
original MIT
aegis
189Skill Claude CodeCodex
AI Development Quality Guardian — contract-driven, design-first quality guardrails for AI-assisted full-stack development. Five-layer defense: Design → Contract → Implementation → Verification → PM. Prevents project chaos at scale. Activate when: starting a feature, setting up a project, dispatching coding tasks…
not rated 2 5mo ago A 89 tokens
original MIT
Skill Claude CodeCodex
Use when Claude Code receives a code-review request, 'review', 'code review', 'quick review', 'native review', or a fast code check. Runs native (< 30 s) line-by-line analysis with adversarial pass, assumptions list, syntax-checker-verified syntax findings, and an optional ready-to-apply Refactored Patch. In Codex…
not rated 2 6d ago A 88 tokens
caveman-commit
191Skill Claude CodeCodex
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.…
not rated 2 1mo ago A 79 tokens
copy · 89% MIT
caveman
192Skill Claude CodeCodex
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…
not rated 2 1mo ago A 98 tokens
copy · 86% MIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: