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.
PdbjorkAGENTS.mdPdbjork/hermosskills-site/AGENTS.md
This repo uses Guardian Compound Engineering. Plan → Work → Simplify → Review → Compound → Repeat A meaningful change is not done until it leaves behind reusable learning, validation,…
PdbjorkSkillPdbjork/hermosskills-site/skills/agents-sdk/SKILL.md
Build AI agents on Cloudflare Workers using the Agents SDK. Load when creating stateful agents, durable workflows, real-time WebSocket apps, scheduled tasks, MCP servers, chat applications, voice agents, or browser automation. Covers Agent class, state management, callable RPC, Workflows, durable execution, queues, retries, observability, and React hooks. Biases towards retrieval from Cloudflare docs over pre-trained knowledge.
Often used withnextjs-on-cloudflaresandbox-sdkbasin
PdbjorkSkillPdbjork/hermosskills-site/skills/ai-visibility-for-small-sites/SKILL.md
Make a small business website (solo founder, local service, niche SaaS, personal brand) discoverable and citable by AI search — ChatGPT, Perplexity, Claude, Gemini, Google AI Overviews. Covers the schema.org JSON-LD scaffolding (Organization, LocalBusiness, Service, Offer, FAQPage), the "answer-ready content for buyer prompts" plan, the citation/reputation gap closer, and the validate-before-ship discipline (always re-parse every JSON-LD block you write). Load when the user asks about AI visibility, GEO (generative engine optimization), being cited by ChatGPT, schema.org / structured data, FAQ rich snippets, or wants to close the "AI says nothing about my business" gap. Skip for large enterprise SEO (technical sitemaps, hreflang, log-file analysis) — this is the small-team, no-Specialist playbook.
PdbjorkSkillPdbjork/hermosskills-site/skills/ce-brainstorm/SKILL.md
Explore vague or ambitious ideas into a right-sized requirements-only unified plan. Use when the user wants to brainstorm, think through scope, decide what to build, or needs collaborative product framing before planning.
PdbjorkSkillPdbjork/hermosskills-site/skills/ce-code-review/SKILL.md
Structured code review for bugs, regressions, tests, and standards. Use before PRs or when asked for review; interactive mode can fix locally, while mode:agent reports only for pipeline callers.
PdbjorkReads credentialsSkillPdbjork/hermosskills-site/skills/ce-commit-push-pr/SKILL.md
Commit, push, and open a PR. Use when asked to ship/open a PR, or for PR-description-only flows like writing, rewriting, or describing a PR body.
Often used withce-explaince-handoffce-prototype
PdbjorkReads credentialsSkillPdbjork/hermosskills-site/skills/ce-commit/SKILL.md
Create a git commit with a clear, value-communication message. Use when the user asks to commit/save staged or unstaged changes with a repo-appropriate, value-communicating message.
Often used withce-skill-workce-explaince-handoff
PdbjorkSkillPdbjork/hermosskills-site/skills/ce-compound-refresh/SKILL.md
Refresh docs/solutions learnings against the current codebase. Use when auditing stale, overlapping, superseded, or drifted learnings; avoid general refactor, debugging, or code review unless docs/solutions is explicit.
Often used withce-explaince-handoffce-prototype
PdbjorkSkillPdbjork/hermosskills-site/skills/ce-compound/SKILL.md
Document a recently solved problem or durable project vocabulary in docs/solutions/ or CONCEPTS.md. Use when capturing a learning after work.
Often used withce-explaince-handoffce-prototype
PdbjorkSkillPdbjork/hermosskills-site/skills/ce-debug/SKILL.md
Diagnosis loop for bugs and failing behavior. Use for errors, stack traces, regressions, failed tests, issue-tracker bugs, stuck investigations after failed fixes, or asks to debug/fix a bug.
PdbjorkSkillPdbjork/hermosskills-site/skills/ce-doc-review/SKILL.md
Review requirements, plans, or specs with role-specific lenses. Use when the user wants to improve an existing planning document.
Often used withce-explaince-handoffce-prototype
PdbjorkReads credentialsSkillPdbjork/hermosskills-site/skills/ce-dogfood-beta/SKILL.md
[BETA] Hands-off end-to-end branch dogfood pass with browser testing, auto-fixes, regression tests, and fix commits.
PdbjorkSkillPdbjork/hermosskills-site/skills/ce-ideate/SKILL.md
Generate and evaluate grounded ideas. Use when the user asks for ideas, improvements, surprising options, or AI-generated directions before choosing one to develop; use ce-brainstorm to refine the user's own idea.
PdbjorkSkillPdbjork/hermosskills-site/skills/ce-optimize/SKILL.md
Run metric-driven optimization loops. Use when improving measurable outcomes such as search relevance, clustering quality, build performance, prompt quality, or scored behavior through experiments.
Often used withce-explaince-handoffce-prototype
PdbjorkSkillPdbjork/hermosskills-site/skills/ce-plan/SKILL.md
Create structured plans for multi-step work, including software and non-software tasks. Use when asked to plan, break down implementation, plan from requirements, or deepen an existing plan; prefer ce-brainstorm for exploratory framing.
PdbjorkSkillPdbjork/hermosskills-site/skills/ce-polish/SKILL.md
Start the dev server, inspect the feature in browser, and iterate on polish.
Often used withce-explaince-handoffce-prototype
PdbjorkSkillPdbjork/hermosskills-site/skills/ce-product-pulse/SKILL.md
Generate time-windowed product pulse reports from configured signals.
PdbjorkSkillPdbjork/hermosskills-site/skills/ce-promote/SKILL.md
Draft launch or promotion copy for a shipped feature.
PdbjorkSkillPdbjork/hermosskills-site/skills/ce-proof/SKILL.md
Publish, read, comment on, or edit markdown in Proof. Use for Proof links, sharing specs/plans/drafts, or publish handoffs from planning workflows; avoid proofread, math, evidence, or proof-of-concept meanings.
PdbjorkSkillPdbjork/hermosskills-site/skills/ce-resolve-pr-feedback/SKILL.md
Resolve PR review feedback. Use when addressing review comments, resolving review threads, or fixing code-review feedback.
Often used withce-explaince-handoffce-prototype
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.
