Skill Claude CodeCodex
Write standalone single-file Python scripts with PEP 723 inline metadata run by uv. Use for a quick CLI script that needs dependencies without a full project.
not rated 4 yesterday A 34 tokens
original MIT
4Stars on the repository
109Mods indexed here, across every type
yesterdayLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown
python-stack
74Skill Claude CodeCodex
Build typed Python projects with uv, Ruff, ty, pytest, Litestar, and Typer. Use for packages, CLIs, web apps, agents, tests, or typing.
not rated 4
changed today A 40 tokens
original MIT
Skill Claude CodeCodex
Design and execute risk-based test campaigns and exercise risky feature journeys; identify what remains unproved across unit, integration, E2E, browser, accessibility, performance, resilience, and manual tests, not a diff review.
not rated 4 yesterday A 48 tokens
original MIT
Skill Claude CodeCodex
Sync AGENTS.md (for agents) and README.md (for humans) with the codebase's current tools, layout, and usage. Use when either drifts from the project's state.
not rated 4 yesterday A 43 tokens
original MIT
reclaim-disk
77Skill Claude CodeCodex
Reclaim disk space safely with dot prune and per-tool cache cleanup without disturbing running agents or uncommitted work. Use when the disk is full or low.
not rated 4
changed today A 37 tokens
original MIT
Skill Claude CodeCodex
Remove technical debt and accidental complexity: dead code, duplicated logic, over-abstraction, stale config, oversized files, tests kept green. Use to simplify a project.
not rated 4 yesterday A 38 tokens
original MIT
release
79Skill Claude CodeCodex
Cut or verify a versioned release: bump semver, generate the changelog with git-cliff, tag, and publish on GitHub. Use when releasing or reconciling a published tag.
not rated 4 yesterday A 42 tokens
original MIT
Skill Claude CodeCodex
Reconstruct why tracked code exists from read-only Git history. Use to trace files, symbols, or lines to introducing commits or pull requests, rationale, reverts, renames, authorship, co-change, and issues.
not rated 4 yesterday A 48 tokens
original MIT
Skill Claude CodeCodex
Audit a whole repository across architecture, source, tests, tooling, security, CI/CD, docs, and releases with ranked findings. Use for cross-cutting audits, not one diff.
not rated 4 yesterday A 40 tokens
original MIT
Skill Claude CodeCodex
Resolve git merge or rebase conflicts by reading both sides, keeping the intent of each change, then continuing and re-running the gate. Use when a merge or rebase conflicts.
not rated 4 yesterday A 40 tokens
original MIT
secure
83Skill Claude CodeCodex
Run the repository security pass: secret leaks, dependency and IaC scans, workflow audit, image signing, encrypted secrets, threat model. Use for a security review or checklist.
not rated 4 yesterday A 37 tokens
original MIT
Skill Claude CodeCodex
Audit a third-party Agent Skill or extension for supply-chain risk without running it: scripts, hooks, MCP, hidden instructions, symlinks, credential and network flows, provenance. Use before installing or trusting a skill.
not rated 4 yesterday A 48 tokens
original MIT
skillify
85Skill Claude CodeCodex
Turn this conversation, a repeated workflow, or an oversized AGENTS.md section into a global or local SKILL.md. Use when asked to skillify or capture a workflow.
not rated 4 yesterday A 38 tokens
original MIT
sops-secrets
86Skill Claude CodeCodex
Manage secrets with sops and age: commit encrypted files, decrypt only in memory, and wire Flux or OpenTofu runtimes. Use for any secret stored in git.
not rated 4 yesterday A 40 tokens
original MIT
Skill Claude CodeCodex
Diagnose unknown-cause bugs, test/build or auth failures, flakes, and runtime performance regressions. Investigate, reduce, localize, falsify hypotheses, and explain root cause before implementation.
not rated 4 yesterday A 45 tokens
original MIT
Skill Claude CodeCodex
Publish technical articles through package review, canonical web export, and channel copy. Use when drafting, checking, verifying, or publishing an article.
not rated 4 yesterday A 32 tokens
original MIT
Skill Claude CodeCodex
Verify unfamiliar APIs and architectures from installed dependency source and current primary docs, then recommend one option with proof boundaries. Use when a choice depends on unverified facts.
not rated 4 yesterday A 36 tokens
original MIT
Skill Claude CodeCodex
Canonical infrastructure-as-code stack: OpenTofu-first with tflint, trivy config scans, terraform-docs, native tests, GCS state. Use for any Terraform or OpenTofu work.
not rated 4 yesterday A 44 tokens
original MIT
Skill Claude CodeCodex
Implement an isolated bug fix or behavior change with an honest red-green-refactor cycle. Use when a regression test should fail before the fix, or when refactors or seams must prove correctness.
not rated 4 yesterday A 42 tokens
original MIT
threat-model
92Skill Claude CodeCodex
Model attack paths beyond scanners: assets, actors, trust boundaries, data flows, abuse cases, controls, residual risk. Use for auth, sensitive data, AI agents, integrations, APIs, or public exposure.
not rated 4 yesterday A 46 tokens
original MIT
trivy
93Skill Claude CodeCodex
Run Trivy scans for dependency vulnerabilities, IaC misconfigurations, secrets, licenses, SBOMs, and container images with the shared trivy.yaml. Use for any trivy command.
not rated 4 yesterday A 42 tokens
original MIT
Skill Claude CodeCodex
Build TypeScript packages and Node services with pnpm, Biome, tsc, Vitest, and Knip, and route website work to Angular. Use for any TypeScript or Node project.
not rated 4
changed today C 43 tokens
original MIT
typst
95Skill Claude CodeCodex
Create standalone reports, papers, letters, or CVs with Typst, typstyle, mise tasks, and live PDF preview. Use for any document that would otherwise be LaTeX or Word.
not rated 4 yesterday A 43 tokens
original MIT
Skill Claude CodeCodex
Upgrade pinned tools and dependencies to latest stable one ecosystem at a time, validating mise, language, action, and formatter changes between bumps. Use when bumping versions.
not rated 4 yesterday A 36 tokens
original 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: