One search for your own team's files and the public ecosystem. See how real projects write their agent instructions, and bring the good ideas home.
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
timmo001Skilltimmo001/context/.agents/skills/context-cli/SKILL.md
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.
timmo001Skilltimmo001/context/.agents/skills/context-mcp/SKILL.md
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.
timmo001Skilltimmo001/skills/agentic-workflows/SKILL.md
Design, create, update, debug, audit, or upgrade GitHub Agentic Workflows with the `gh aw` extension. Use when work involves workflow Markdown, compiled `.lock.yml` files, agent engines, MCP tools, safe outputs, work queues, or `gh aw` commands.
Often used withagentic-workflow-designer
timmo001AGENTS.mdtimmo001/skills/AGENTS.md
No summary in the file. Open it to read it.
timmo001Skilltimmo001/skills/asking-questions/SKILL.md
Decide when to ask the user a question and how to present it. Use before any clarifying question, choice, or confirmation, whether through the Plannotator Inbox, a structured question tool or in chat, and to decide whether to hold questions until findings are presented or divert to grilling; do not use to run light or full grilling rounds.
timmo001Skilltimmo001/skills/bro/SKILL.md
Re-pitch the immediately preceding response with enough context to follow, using plain, concise, unambiguous language. Use ONLY when the user explicitly invokes /bro or says the previous response did not land.
Often used within-your-own-wordspoteto-helpmake-bot-ui
timmo001Skilltimmo001/skills/browser-access/SKILL.md
Decide whether browser access is needed and keep authorised checks narrow. Use for frontend or UI diagnosis, before proposing or using Chrome DevTools or other browser automation, and when the user explicitly requests browser interaction.
timmo001Skilltimmo001/skills/change-review-handoff/SKILL.md
Hand a finished code change to the user for review in Plannotator, with a standing next-steps question they answer when they have no notes. Use when an implementation, fix, refactor, or cleanup is complete and verified, before reporting it done; picks a diff review or a guided review plus diff review by size, and offers commit, push, pull request, or publish steps that fit the context.
timmo001Skilltimmo001/skills/check-skill-updates/SKILL.md
Check imported skills for upstream changes and review safe updates. Use when an import's origin in skills.yml may have changed, when a tool a skill depends on has a new release, or when refreshing installed skills from their source repositories.
timmo001Skilltimmo001/skills/chill/SKILL.md
Stop overengineering and reinventing the wheel. Use when the user says a change has become overly complicated, out of scope, or is rebuilding something an existing tool or library already does.
timmo001Skilltimmo001/skills/cleanup-unnecessary-variables/SKILL.md
Safe removal of unnecessary variables during code review and refactoring. Use when simplifying code, inlining temporary or single-use variables, or removing redundant aliases, while preserving runtime behaviour, evaluation order, and variables kept for readability or debugging.
timmo001Pipes a download into a shellSkilltimmo001/skills/decision-models/SKILL.md
Make typed, calibrated decisions about text, JSON or images with decision models, locally through Ollaya or Ollama or hosted as Cloudflare Clef on Workers AI: classify (choice), rate (score) or check a yes/no statement (noul), with probabilities you can threshold. Use it to triage tickets and emails, route requests, moderate posts, screen prompts for jailbreaks or injections, or any step where the agent needs a quick judgement it can act on, instead of reasoning it out in text. Also use it whenever the user names a decision model such as laya, winnow, tev1, nimble, clef or clef-flash, which are models, not commands. Works through the Ollaya MCP server (the `decide` tool), the `ollaya` CLI or local HTTP API, Ollama's local HTTP API, or the Cloudflare API MCP server.
timmo001Skilltimmo001/skills/diagnose/SKILL.md
Investigate bugs using source, observed failures, and proportionate verification. Use for regressions, intermittent failures, incorrect behaviour, or performance problems whose cause needs investigation.
Often used withzoom-outto-issueswrite-a-skill
timmo001Skilltimmo001/skills/effect-principles/SKILL.md
Apply the Effect way of reasoning in codebases that do not use Effect, in any programming language. Use when editing or reviewing non-Effect code so dependencies, failures, state, boundaries, resources, time, and workflows stay explicit without adding Effect-shaped architecture or broader scope.
timmo001Skilltimmo001/skills/evidence-first/SKILL.md
Check uncertain claims against the source that owns them before answering, while following clear user choices and limits. Use when the user's statement is tentative or possibly wrong (I think, I remember, I don't think, is this correct), when giving advice or a recommendation, or when the user sets a firm preference such as I don't want this, reduce the scope, or this is going too far. Load once per conversation; it stays in effect.
timmo001Skilltimmo001/skills/gh-stack/SKILL.md
Manage stacked branches and pull requests with GitHub's `gh stack` extension. Use when work involves stacked PRs, dependent branches, stack creation, navigation, submission, synchronisation, rebasing, restructuring, linking, or merging.
timmo001Skilltimmo001/skills/git-context/SKILL.md
Patterns for working with git branches, remotes, diffs against the default branch, and rebases. Use when resolving rebase conflicts, continuing interactive rebases, amending commits, or any git operation that would open an interactive editor.
timmo001Skilltimmo001/skills/github-development-rulesets/SKILL.md
Create GitHub Development rulesets from the bundled JSON baseline, compare and migrate existing rulesets, or update required CI checks. Use when setting up a Development ruleset, choosing among existing rulesets, or reconciling their policy and emitted check names.
timmo001Skilltimmo001/skills/github-repository-setup/SKILL.md
Create GitHub repositories with the preferred settings, ask about licensing using GitHub templates, enable watching during creation or induction, offer CI and automerge workflows, and finish first-push setup with a Development ruleset. Use when creating or inducting a GitHub repository, using gh repo create or dot repo induct, applying repository defaults, or completing initial GitHub setup.
timmo001Skilltimmo001/skills/grilling/SKILL.md
Grill the user about a plan, decision, or idea in dependency-ready rounds. Use when the user wants to stress-test their thinking or uses a grill trigger phrase.
Often used withdecision-mappingloop-mesetup-ts-deep-modules
Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.
CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.
A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.
