python-debugging
961Skill Claude CodeCodex
Use this skill when fixing failing Python tests.
not rated 2 19d ago A 0 tokens
Skill Claude CodeCodex
Use when debugging, verifying, or investigating backend runtime behavior — HTTP 500s, wrong responses, slow endpoints, suspected N+1 or duplicate queries, "why did this request do that" — in a project running under rewynd. Reads the actual recorded request trace (SQL with params, outbound calls, logs, exceptions…
not rated 2 3mo ago C 88 tokens
original MIT
harness-fe
963Skill Claude Code
Debug, inspect, and drive any frontend app that has the Harness-FE Vite/Webpack plugin installed. Use this when the user reports a UI bug, asks "why is this happening on the page", wants to inspect runtime state, drive an automated browser test, or needs to correlate browser behavior with source files (especially in…
not rated 2 12d ago A 79 tokens
original MIT
astrolabe
964Skill Codex
Use when inspecting a running mobile app UI or reviewing whether an implementation matches supplied design references.
not rated 2
changed 7d ago A 22 tokens
original Apache-2.0
doctor
965Skill Claude CodeCodex
Run health diagnostics on the amem memory database. Use when the user wants to check memory health, embedding coverage, stale memories, or diagnose issues.
not rated 2 4mo ago A 32 tokens
original MIT
docs-search
966Skill Claude CodeCodex
Search local framework documentation (Svelte 5, FastAPI, Tailwind, Tauri, Next.js, Supabase) and AI Models documentation (Claude 3.7/3.5, GPT-4.5/o1/o3, Gemini 2.0/3.0, DeepSeek V3/R1, Qwen 2.5 Coder, benchmarks, pricing, routing) via agents-docs MCP before guessing API methods or hallucinating stale model knowledge.
not rated 2 20d ago A 101 tokens
original MIT
Skill Claude CodeCodex
Map documented and inferred exposure paths, horizons, and counterfactors.
not rated 2 1mo ago A 21 tokens
original MIT
Fred-In-tech/learn-as-you-build
Skill Claude CodeCodex
Turns every coding or creative session into a teaching session. Explains the WHY behind decisions, surfaces the tradeoff that was made, names the pattern being applied, and flags what transfers to other problems — without slowing the work down. Use continuously in any build, debug, design, or content session.
not rated 2 26d ago A 65 tokens
original MIT
Skill Codex
Default workflow for durable local, SSH, Slurm, Apple-signing, or GitHub publishing work through RunBeacon. Use whenever Codex needs to call a remote host, securely save or select SSH/GitHub credentials, run or recover a long task, monitor training, publish commits, wait without model polling, cancel a remote process…
not rated 2
+1 3d ago A 104 tokens
original MIT
worktrees
970agallardol/zcode-git-worktrees
Skill Claude Code
Create and manage git worktrees for parallel, isolated work on one repository — multiple tasks at once without stashing or switching branches, risky experiments, PR review checkouts. Use when the user wants to work on several things at once, isolate a task, mentions worktrees or parallel branches/tasks/agents, or…
not rated 2
+1 23d ago A 75 tokens
original MIT
hronaut
971Skill Claude CodeCodex
Use the Hronaut desktop Browser MCP for visible, persistent web workflows in isolated agent workspaces. Use for authenticated browser QA with human handoff, localhost or responsive testing, accessibility and performance diagnosis, or tasks that should survive one agent session while the user watches or takes over.
not rated 2
+1
changed 4d ago A 59 tokens
Skill Claude CodeCodex ✓ vendor
Guides application developers in designing correct and performant transaction patterns for CockroachDB, covering transaction lifetime, implicit vs explicit transactions, retry handling with exponential backoff, pushing invariants into SQL, selective pessimistic locking, set-based operations, connection pooling…
not rated 2 1mo ago A 102 tokens
copy · 100% Apache-2.0
cookbook-audit
973Najeebullah3124/awesome-claude-universe
Skill Claude Code
Audit an Anthropic Cookbook notebook based on a rubric. Use whenever a notebook review or audit is requested.
not rated 2 1mo ago A 26 tokens
Skill Claude CodeCodex
Cursor rules for building custom frontends with Momen.app as headless BaaS with GraphQL API, actionflows, AI agents, and Stripe integration.
not rated 2 6d ago A 10 tokens
original Apache-2.0
SparkElf/deepseek-harness-plus
Skill Claude CodeCodex
Use before adding, moving, publishing, curating, or default-mounting a DSH capability to decide plugin ownership, npm distribution, repository placement, and profile composition independently.
not rated 2 yesterday A 45 tokens
original MIT
Skill Claude CodeCodex
Create premium, Awwwards-quality website designs as React (.jsx) components that look like they were built by a top-tier agency charging $50k+ per project. Use this skill whenever the user asks for a website, landing page, portfolio, or web component that should look expensive, premium, luxury, editorial, high-end, or…
not rated 2 5d ago A 196 tokens
original MIT
galdr-demo
977Skill Claude CodeCodex
Summarize a git repository's recent changes and write them to a Markdown file. Use it when asked for a «change summary», «quick changelog», «what changed in the repo», or to dump git state to a file. Parameters: the repository and the output path.
not rated 2 5d ago A 61 tokens
original MIT
cartograph
978Skill Claude CodeCodex
Explore a codebase through Cartograph v2's PostgreSQL code graph: intent-aware context, exact/BM25/hybrid search, callers/callees/impact, affected tests, live source, review, freshness, and bounded index administration.
not rated 2
changed 2d ago A 0 tokens
original MIT
muapi-media
979Skill Claude CodeCodex
Create, edit, enhance, and inspect AI images, videos, music, and audio through Muapi when the user asks for generative-media work.
not rated 2
+1 yesterday A 34 tokens
asolfre/plantuml-rendering-skill
Skill Claude CodeCodex
Render PlantUML text and .puml files into image outputs (PNG). Use this skill whenever the user mentions PlantUML, .puml files, UML diagram source text, or asks to render/export/generate a sequence/class/activity/component diagram image. Trigger even when the user does not explicitly say "PlantUML" but provides…
not rated 1
+1 5mo ago A 92 tokens
original MIT
Skill Claude CodeCodex
Provides a structured approach for diagnosing errors (reproduce, observe, hypothesize, test fix, verify).
not rated 1
+1 25d ago A 26 tokens
Skill Claude CodeCodex
Manage what goes into the AI agent context window for maximum quality and minimum waste.
not rated 1
+1 14d ago A 19 tokens
original MIT
static-rust
983Skill Claude CodeCodex
Use for Soma built-in Rust actions, scaffold intent collection, MCP elicitation flows, and CLI/REST action reference.
not rated 1 yesterday A 28 tokens
AGPL-3.0
Skill Codex
Classify a completed public GitHub Actions failure with FlakeVerdict before spending a retry. Use when deciding whether a failed workflow run is a confirmed flake, likely flake, recurring failure signature, new failure, inconclusive failure, or not currently failed by comparing attempts, same-commit outcomes, and…
not rated 1 1mo ago A 74 tokens
original MIT archived
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: