Help the user understand the current topic visually with concise diagrams, code-shape sketches, and focused HTML artifacts. Use ONLY when the user explicitly asks to see, visualise, diagram, sketch, or be shown the preceding explanation.
Execute broad changes one coherent, independently verifiable stage at a time. Use when work spans multiple independently reviewable changes, or when contracts, producer-consumer migrations, generated artefacts, or release packaging create an ordered multi-stage rollout; skip small single-purpose changes.
Keep the original task on track when the user raises a side thought, side question, tentative branch idea, or explicit change of task. Use before diverting work, switching branches, or choosing between a BTW session, a fresh session, and the current conversation, especially with a large context window.
Turn a decision the user cannot answer alone into a channel-aware questionnaire draft for one other person. Use when missing knowledge belongs to a colleague, maintainer, or domain expert and the user needs questions for GitHub, Slack, Discord, or a document.
Use the project's Wrangler CLI for Cloudflare development, configuration, and deployment in projects with a wrangler.jsonc, wrangler.json, or wrangler.toml file. Load before running Wrangler or changing its configuration; retrieve exact flags and binding shapes from current docs and installed schemas. For new projects and projects without a Wrangler configuration file, use the cf CLI instead.
Craft for authoring Agent Skills that select reliably and stay lean. Use when creating or revising a skill's description, workflow, references, scripts, or structure.
Review a pull request, branch, work-in-progress changes, or diff for concrete defects, unmet requirements, and repository convention violations. Keep findings scoped, evidenced, and proportionate.
Use the context CLI to inspect repository branches, working-tree changes, recent commits, pull requests, and tech stacks. Use for context git, context stack, and shell-based repository snapshots. For Context MCP tool calls, use context-mcp instead.
Use Context MCP tools for repository branches, working-tree changes, recent commits, pull requests, and tech stacks. Use for git_context, stack_context, command_help, and context resources, including client-prefixed names. For shell-based Context commands, use context-cli instead.
Use @timmo001/effect-gh for GitHub CLI integration in Effect TypeScript code. Apply when adding or changing gh-backed API requests, repository, issue, pull request or workflow operations, streaming output, or migrating hand-written gh subprocess wrappers to Effect.
Name skills with an owner prefix so they do not collide with shared, imported or other repositories' skills. Use when creating, renaming, importing or reviewing a skill name, especially for repository-local or tool-owned skills.
Run and write project tasks so checks, builds, tests and dev servers finish fast - run only what a change needs, in parallel, skipping work that is already up to date. Use when running linters, type checks, test suites or builds; when writing or reviewing task runner config (mise.toml, package.json scripts, justfile, deno.json, Makefile, pitchfork.toml) or CI steps; or when a check, build or task run is slow.
Choose tests for their concrete regression value, avoid low-value coverage, and verify changes by exercising the real built behaviour. Use during implementation, fixes, planning, diagnosis, and code review when choosing verification, adding or changing tests, considering a missing-test finding, or when the user asks to test, check, or verify a change.
Write commit messages, PR and issue text and comments, docs (README), code comments, and user-facing strings (notifications, UI labels, toasts, error messages) in the project owner's voice: concise, human, UK English, no em-dashes, no robotic or marketing tone. Use when writing, editing, or reviewing these, including requests to make writing sound natural or remove jargon. Keep the meaning and follow the repo's established writing style.
A folder with a SKILL.md file: a name, a description of when to use it, and instructions. Claude loads a skill only when the task matches its description.
How do I use one I find here?
Copy the folder into your project's .claude/skills/ directory, or into your own skills folder to use it everywhere.
What do the warnings mean?
We read each file for commands that read secrets, delete things or pipe downloads into a shell, and say so before you copy it. No warning is not a promise that a file is safe.
Which skills worked for people?
Open a skill to see its discussion. Reports from people and their agents are coming.