Skill Claude CodeCodex ✓ vendor
Determines which LLM model to use for each agent spawn.
not rated 5.4k
+32 today A SkillSpector: pass 15 tokens
original MIT
i18n-lookup
02Skill Claude Code needs its repo
Look up Zeabur platform UI term translations from the dashboard i18n files. Use when writing or reviewing docs that reference UI elements (button labels, tab names, menu items) to ensure docs match the actual platform translations.
not rated 686
+1
changed 4d ago A SkillSpector: pass 52 tokens
original MPL-2.0
Skill Claude CodeCodex
Cut a new release of the habit-hooks packages. Use when asked to release, publish, or bump the version. Reviews what lands, enforces the in-sync versioning rule, validates the changelog, and drives the tag-triggered PyPI publish.
not rated 228
+7
changed 1mo ago A SkillSpector: warn 56 tokens
original MIT
Skill Claude CodeCodex
Code review with LSP-powered code intelligence. Uses MCP tools (diagnostics, hover, references, definition, symbols) for semantic code understanding, not just text grep.
not rated 204 17d ago A SkillSpector: pass 40 tokens
original MIT
loops
05Skill Claude CodeCodex
A collection of AI-assisted automation loops for software development, data science, content creation, product operations, and learning management.
not rated 124 3mo ago B 53 tokens
brainblast
06Skill Codex
Research external APIs and SDKs before coding. Identifies every external component in a requirements file, browses official sources, and produces a structured handoff report with facts, risks, and answered questions.
not rated 93 3mo ago A SkillSpector: warn 43 tokens
original MIT
loops
07Skill Claude CodeCodex
A collection of AI-driven automation loops covering software development, data science, content creation, product operations, learning management, and more. Use when users need to automate workflows, fix issues, generate content, analyze data, or run quality checks.
not rated 59
+1 3mo ago A 50 tokens
Skill Claude CodeCodex
Inspect accessible names, roles, and tree structure to drive or audit browser UI behavior.
not rated 29
+96 20d ago A SkillSpector: warn 21 tokens
original MIT
Skill Claude Code
Generate or update the architecture documentation in docs/content/architecture/. Use on "update architecture docs", "generate architecture documentation", "regenerate architecture docs", or after any structural change to the codebase.
not rated 11 2d ago A 46 tokens
GPL-3.0
Skill Claude CodeCodex
Review and merge GitLab merge requests via the gitlab-api MCP server — by default the MRs assigned to you or where you are a reviewer, optionally scoped to a project, group, or the whole instance. Read an MR, gate it on a green pipeline (pipeline → jobs → job log), then approve, accept/merge, or set…
not rated 10 5d ago A SkillSpector: warn 158 tokens
original MIT
Skill Claude CodeCodex
Core conventions and patterns used in the Squad codebase.
not rated 4 3d ago A 15 tokens
copy · 91% MIT
inkcheck
12Skill Claude CodeCodex
CI for ink interactive-fiction stories. Use it whenever a .ink file changes hands or changes state: "does my story compile?", "can any path crash it?", "are all my endings reachable?", "is there content nobody can ever see?", pre-commit checks, reviewing a story PR, or validating a generated/edited ink file before…
not rated 3 1mo ago A 104 tokens
original MIT
agentlint
13Skill Claude CodeCodex
Audit a repository's AI-agent readiness with the agentlint CLI and fix the findings. Use when the user asks to score, audit, or improve how well a repo works with AI coding agents (AGENTS.md, build/test docs, conventions, guardrails), or mentions agentlint.
not rated 3 4d ago A 60 tokens
original MIT
docverity
14Skill Claude CodeCodex
Check whether a project's documentation still matches its code, and report stale or wrong claims with suggested fixes. Use this after editing, renaming, moving, or deleting source files, CLI flags, environment variables, or functions, to catch docs you may have just made inaccurate; when the user asks whether the…
not rated 2 3mo ago A 84 tokens
original MIT
migmcc/agent-skill-quality-gate
Skill Claude CodeCodex
Use when a release is being prepared and a human-readable changelog must be generated from merged pull requests.
not rated 2 3mo ago A 26 tokens
original MIT
tripwire
16Skill Claude CodeCodex
Use when authoring, editing, or reviewing a SKILL.md file — lints it against the Agent Skills best-practice rules and checks whether the description would actually activate the skill on the prompts it claims to cover, before the skill ships.
not rated 2 1mo ago A 52 tokens
original MIT
Skill Claude CodeCodex needs its repo
Validate AGENTS.md and related agent instruction files with the published agents-doctor CLI. Use when the user asks to check, lint, verify, explain, audit, fix, release-check, or compare AGENTS.md, CLAUDE.md, GEMINI.md, agent instruction inheritance, tool profiles, context fidelity, instruction graphs, GitHub…
not rated 2
changed 21d ago A 93 tokens
original MIT
CodeSigils/python-project-workflow-skill
Skill Claude CodeCodex
Set up, inspect, preserve, and verify Python project workflows, including greenfield scaffolding, packaging, dependency and tool configuration, CI, compatibility contracts, mature automation repositories, and project-native validation. Use when the task affects repository-wide Python structure or workflow. Do not use…
not rated 1
changed yesterday A 90 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: