debug
20401Skill Claude CodeCodex
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
not rated 4 7mo ago A 18 tokens
physlibsearch
20402Kernel-Science/physlibsearch-skill
Skill Claude CodeCodex
Semantic search over Physlib, a formal Lean 4 library of physics theorems and definitions. Use when asked to find Lean 4 declarations related to physics or mathematics, look up formal proofs, retrieve theorem signatures, or browse the Physlib module hierarchy.
not rated 4 5mo ago A 56 tokens
android-finance-spec
20403Skill Codex
Use when generating, reviewing, or refactoring Android Kotlin code for financial apps that require BigDecimal/String precision, RTL/i18n safety, Kotlin style discipline, and "do not reinvent existing project patterns" constraints.
not rated 4 3mo ago A 48 tokens
original MIT
constitution-skill
20404CUHK-Business-School-AI-Hub/coding_agent_constitution
Skill Codex
Turn unclear software requirements into reusable project docs and a bounded next task. Use when the user needs to clarify product scope, architecture, or interface agreements before implementation, or explicitly requests project governance files. Skip already-scoped code changes unless governance updates are requested.
not rated 4
changed 24d ago A 55 tokens
original MIT
mac-assed-mac-app
20405HunterHillegas/mac-assed-mac-app-skill
Skill Codex
Design, audit, and improve desktop macOS app UI: menus, windows, keyboard and selection behavior, native controls, UI text, and expressive identity. Use for AppKit, SwiftUI-on-Mac, Catalyst, or other Mac app surfaces; excludes iOS-only and web-only UI work.
not rated 4
changed 12d ago A 67 tokens
original MIT
deslop-code
20406Skill Claude CodeCodex
Removes AI-generated code slop (redundant comments, over-engineering, verbose names, boilerplate, dead defensive code) and normalizes style. Use when the user asks to clean up code, remove AI slop, de-slop, fix code style, refactor for readability, or make code more idiomatic.
not rated 4 1mo ago A 71 tokens
original MIT
swarm-mcp
20407MCP server Claude CodeCodexCursor +2
MCP server for Foursquare Swarm check-in data. Runs locally from the swarm-mcp Python package.
not rated 4 today A
tokens not measured
original MIT
repo-social-poster
20408daliaabbruciati/awesome-claude-skills-by-dalia
Skill Claude CodeCodex needs its repo
Automazione condivisibile che trasforma repository GitHub (starred o indicate a mano) in una bozza di post social, PARTENDO SEMPRE da un'intervista su 4 punti, repo da usare, tono del testo, se creare eventi calendario, e target/piattaforma di pubblicazione, pubblica SOLO dopo approvazione esplicita. Generica e…
not rated 4 1mo ago A 213 tokens
original MIT
RonasIT/open-webui-mcp-server-python
MCP server Claude CodeCodexCursor +2
MCP server "open-webui-knowledge-mcp-server" as configured in RonasIT/open-webui-mcp-server-python. Runs locally from the open-webui-knowledge-mcp-server Python package.
not rated 4 6mo ago A
tokens not measured
original MIT
pato-gonzalez/design-system-stack
Skill Claude CodeCodex
Applied workflow skill for producing Awwwards-caliber animated landing pages using Claude Design as the orchestrator, with motionsites.ai (animated backgrounds), higgsfield.io or Kling 3 (AI animation generation), Dribbble (component inspiration), shots.so (animation showcase/video edit), and land-book (landing page…
not rated 4 5mo ago A 157 tokens
gen3-mcp
20411MCP server Claude CodeCodexCursor +2
MCP server "gen3-mcp" as configured in delocalizer/gen3-mcp. Runs locally from the gen3-mcp Python package.
not rated 4 1y ago A
tokens not measured
original MIT
mcp-sandbox-toolkit
20412MCP server Claude CodeCodexCursor +2
A cross-platform sandboxed file system operations toolkit based on Model Context Protocol (MCP). Runs locally from the mcp-sandbox-toolkit Python package.
not rated 4 9mo ago A
tokens not measured
secret-shuttle
20413Skill Claude CodeCodex
Use when an AI coding agent must provision, inject, run, or rotate secrets without ever seeing their plaintext — you work with ss:// refs (like ss://stripe/prod/STRIPEWEBHOOKSECRET) while a local daemon resolves the real value at the last possible moment.
not rated 4 3mo ago A 60 tokens
original MIT
code-review
20414Skill Claude CodeCodex
Use when reviewing a code change or diff for correctness, security, missing tests, and convention violations before opening or approving a PR. Review independently and adversarially, then fix high-confidence issues.
not rated 4 today A 42 tokens
original MIT
python-engineer
20415Skill Claude CodeCodex
Use when writing Python code - covers typing, error handling, style, imports, and patterns.
not rated 4 4mo ago A 22 tokens
startup-kit
20416Skill Codex
Cross-agent full-stack startup kit for building skill UIs and shippable products. ALWAYS run onboarding FIRST — never scaffold or build until you have interviewed the user (product, scope, style, theme, background animations, architecture, data, auth, payments, launch, deploy) or loaded their stored answers, and…
not rated 4 4mo ago A 301 tokens
quality-check
20417Skill Claude CodeCodex needs its repo
A required pre-merge quality gate that runs local static checks, tests, and reviews. A merge is allowed only after the checks pass.
not rated 4
changed yesterday A SkillSpector: warn 82 tokens
original MIT
agent-cli-design
20418Skill Claude CodeCodex
A methodology for designing command-line tools for AI agents. A command-line tool is a program operated through typed commands; these rules focus on discoverable help, structured output, useful errors, safe operations, and reliable retries.
not rated 4 6mo ago A 51 tokens
original MIT
founders-playbook
20419zhangxiaoqiang1991/founders-playbook
Skill Claude CodeCodex
A guided navigation tool for founders building companies around artificial intelligence. It uses a founder-focused playbook to identify the situation and point to a relevant next step.
not rated 4 4mo ago A 134 tokens
original MIT
protected-commit
20420Skill Claude CodeCodex
Use when a commit is refused with "Protected state edit detected", or before editing AGENTS.md, CLAUDE.md, a lockfile, .forge/config.yaml, .github/workflows, lefthook.yml, .beads/, or a generated harness mirror. Do not use to find a way around the gate — there is no environment variable that authorizes a protected…
not rated 4 5d ago A 82 tokens
original MIT
uber-interpret
20421Skill Claude CodeCodex
Use when the user wants to "interpret results", "explain the solution", "what does this mean", "translate to business language", "present findings", "sensitivity analysis", "what-if analysis", "how robust is this", "visualize the result", "make a recommendation", or needs to translate a mathematical solution back into…
not rated 4 7mo ago A 104 tokens
original Apache-2.0
flog-inspect
20422Skill Codex
Use when a user asks an agent to inspect Flutter app logs, network traffic, SSE/WebSocket streams, current page state, screenshots, or debugging context through flog instead of copying from the TUI.
not rated 4 2mo ago A 45 tokens
original MIT
check-work
20423Skill Claude CodeCodex
Check your work with a verification subagent that reviews diffs, runs builds and tests, and evaluates correctness. Read this file for instructions. Use when asked to "check work", "verify changes", "self-verify", "/check-work", "/check", "/verify", or "/self-verify".
not rated 4 2mo ago A 64 tokens
copy · 100% Apache-2.0
english-assessment
20424Skill Claude CodeCodex
An English-level assessment assistant that tests university-level English from CEFR B1 to C2, where CEFR is a common scale for language ability.
not rated 4 3mo ago A 258 tokens
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: