gh-review-pr
25Skill Claude Code
Review a GitHub PR focusing on correctness, tests, and risk.
not rated 2 today A 17 tokens
2Stars on the repository
92Mods indexed here, across every type
todayLast push, which is what freshness is scored on
noneNo LICENSE: all rights reserved, so bodies are not copied
gh-ship
26Skill Claude Code
Commit, push, and file a concise pull request in one step, or file one for a branch already committed. Use when the user asks to ship or open a PR.
not rated 2
changed today A 39 tokens
grill-me
27Skill Claude CodeCodex
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
not rated 2 today A 49 tokens
grilling
28Skill Claude CodeCodex
Interview the user relentlessly about a plan or design. Use when the user wants to stress-test a plan before building, or uses any 'grill' trigger phrases.
not rated 2 today A 36 tokens
Skill Claude CodeCodex
Design, ground, and harden eval suites for LLM/agent systems. Use when the user wants to add evals or regression datasets, fix flaky or vacuous evals, pin agent behavior like tool routing or authorization, add answer-quality guards or deny lists, ground eval expectations in fixtures, set up LLM-as-judge scoring, score…
not rated 2 today A 95 tokens
handoff
30Skill Claude Code
Generate a continuation prompt so the next session can pick up where this one left off.
not rated 2 today A 19 tokens
Skill Claude CodeCodex
Present finished work as a standalone document to read — a writeup, plan, findings, comparison, or a set of UI mocks to pick from. Use when the user asks for something to review, not when they ask to edit HTML, copy, or components inside a project.
not rated 2 today A 60 tokens
Skill Claude Code
Humanize AI-shaped writing. Use for "make this less AI/ChatGPT", AI writing or slop audits, citation/source checks in AI-drafted text, detector concerns, leaked citation tokens, placeholders, broken markup, or wrong target-format cleanup.
not rated 2 today B 56 tokens
Skill Claude CodeCodex
Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.
not rated 2 today A 68 tokens
improve
34Skill Claude CodeCodex
Survey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on source code — never implements, fixes, or refactors anything itself. Use when asked to audit a codebase, find improvement opportunities (bugs, security…
not rated 2 today A 102 tokens
Skill Claude CodeCodex
Bring crafted micro-interactions, thoughtful details, and polish to interfaces. Use when building UI, reviewing UI for detail/polish opportunities, making an interface "feel better," or adding tasteful delight and micro-interactions.
not rated 2 today A 47 tokens
Skill Codex
Visual-reference-to-app implementation loop for building or restyling a web app screen to match a provided reference image. Use when Codex is asked to take a screenshot/reference/mockup/image and build an app or route that looks like it, especially when the task requires hosting the app, capturing Playwright…
not rated 2 today A 81 tokens
loop-me
37Skill Claude Code
Grill me about specs for the workflows I want to build, within this workspace.
not rated 2 today A 20 tokens
make-tests
38Skill Claude Code
Add tests for the change you're working on.
not rated 2 today A 11 tokens
Skill Claude Code
Rebase current branch onto main/master, resolve merge conflicts, and force-push.
not rated 2 today A 20 tokens
Skill Claude CodeCodex
Use this skill when a React component's props have been widened for stories, mocks, tests, or demos and now express states the live application does not enter.
not rated 2 today A 18 tokens
Skill Claude CodeCodex
NestJS best practices and architecture patterns for production applications. Use when writing, reviewing, or refactoring NestJS code covering modules, dependency injection, security, and performance.
not rated 2 today A 40 tokens
no-comments
42Skill Claude Code
Aggressively remove comments, docstrings, suppressions, and explanatory clutter that code can express better. Preserve only proven external constraints, required public documentation, and rationale that cannot be encoded.
not rated 2 today A 41 tokens
no-ui-flash
43Skill Claude CodeCodex
Use when an SPA or SSR page flashes the wrong UI before client-side state resolves, such as auth skeletons for signed-out visitors, empty-state mismatches, theme flashes, or skeletons for routes that redirect or 404.
not rated 2 today A 51 tokens
pre-pr
44Skill Claude Code
Run project-appropriate validation before opening a PR, then draft the PR summary.
not rated 2 today A 19 tokens
Skill Claude Code
Use when a bug, error, crash, stack trace, regression, or "X doesn't work / broke" report needs fixing. Reproduces the bug with a failing test before any fix is written, then confirms the test passes after. Triggers on bug reports, error messages, and "prove the fix works" requests.
not rated 2 today A 73 tokens
qa
46Skill Claude Code
Verify completed work in the browser using QA notes from a plan file.
not rated 2 today A 15 tokens
Skill Claude CodeCodex
Use when writing, reviewing, or refactoring Python code that needs cleaner structure, precise types, better error handling, safer IO, smaller functions, clearer domain models, Ruff/uv tooling, async correctness, realistic tests, or removal of junior Python smells like broad exceptions, mutable defaults, dict blobs…
not rated 2 today A 76 tokens
Skill Claude CodeCodex
Use when writing, reviewing, or refactoring React code that needs smaller components, clearer state ownership, fewer unnecessary effects, typed props, semantic HTML, accessible form controls, explicit loading/error/empty states, safer async effects, Next.js server/client boundaries, cleaner hooks, better tests, or…
not rated 2 today A 117 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: