Corewise.Academy
ryanportfolio/Corewise.Academy/AGENTS.md
This is the Codex boundary for repositories using the AI Operating System starter. Claude Code keeps using CLAUDE.md and .claude/ unchanged.
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.
ryanportfolio/Corewise.Academy/AGENTS.md
This is the Codex boundary for repositories using the AI Operating System starter. Claude Code keeps using CLAUDE.md and .claude/ unchanged.
ryanportfolio/Corewise.Academy/.agents/skills/addskill/SKILL.md
Create, import, update, or install repository or personal skills; includes runtime ownership, resources, and discovery validation.
ryanportfolio/Corewise.Academy/.agents/skills/adopt-repo/SKILL.md
Mirror an existing external repo privately under the user's account and overlay the firmware: clone upstream, strip template-only files, privacy-sweep, run init-project. Use on $adopt-repo <url> or 'pull this repo into our firmware'.
Often used withaddskilldareastra-review
ryanportfolio/Corewise.Academy/.agents/skills/advocate/SKILL.md
Use only when the user explicitly invokes $advocate to challenge a change just made before it lands. Do not trigger from natural-language requests.
Often used withaddskilldareastra-review
ryanportfolio/Corewise.Academy/.agents/skills/arena/SKILL.md
Builds parallel attempts at one task, judges them blind, and grafts the best ideas onto the strongest. Use for $arena, \"try a few approaches\", \"build me options\", bakeoffs, competing versions, or a stalled long-horizon or wow-loop step.
Often used withpoteto-helpprinciple-explain-the-numbermake-bot-ui
ryanportfolio/Corewise.Academy/.agents/skills/astra-review/SKILL.md
Codex CLI review configured for gpt-6-astra at medium reasoning. Same verified CLI lifecycle as codex-review. Use for $astra-review or 'have Astra review this'.
ryanportfolio/Corewise.Academy/.agents/skills/babysit-ci/SKILL.md
Watches a PR's checks and fixes failures. Use for $babysit-ci, \"watch CI\", \"fix CI\", \"get checks green\", or a PR with failing or pending checks; not a bare merge request.
Often used withaddskilldareastra-review
ryanportfolio/Corewise.Academy/.agents/skills/brainstorming/SKILL.md
Use when product, interface, workflow, or architecture goals have unresolved material tradeoffs. Skip routine work and implementation of an approved design.
Often used withchinese-code-reviewaddskillchinese-commit-conventions
ryanportfolio/Corewise.Academy/.agents/skills/bro/SKILL.md
Plain-language restatement. Use on $bro anywhere in a message, \"plain english\", \"plain language\", \"dumb it down\", \"I don't understand\", or \"what does that mean\".
Often used within-your-own-wordspoteto-helpmake-bot-ui
ryanportfolio/Corewise.Academy/.agents/skills/caveman/SKILL.md
Use for every session reply to the user: concise Caveman prose with built-in Unslop. User-facing deliverables use Writing instead.
Often used withcaveman-exploreaddskillastra-fullreview
ryanportfolio/Corewise.Academy/.agents/skills/clarity-pass/SKILL.md
Use when a guide draft needs editorial review after writing, including required review in $ingest and $create-guide, or when prose sounds unnatural, unclear, or obtuse.
ryanportfolio/Corewise.Academy/.agents/skills/claude-review/SKILL.md
Use when the user says $claude-review, asks Claude or Fable to review code written in Codex, or requests a cross-vendor review through Claude CLI.
Often used withaddskilldareastra-review
ryanportfolio/Corewise.Academy/.agents/skills/codex-review/SKILL.md
Second-opinion review. Drives OpenAI Codex CLI (codex exec review, gpt-6.1-sol, high reasoning) over a PR, branch, commit, or uncommitted diff, then verifies each finding. Trigger: $codex-review, \"have Codex/Sol review this\".
Often used withaddskilldareastra-review
ryanportfolio/Corewise.Academy/.agents/skills/create-guide/SKILL.md
Use for $create-guide or a CoreWise Academy guide from current official AI docs without a video source.
ryanportfolio/Corewise.Academy/.agents/skills/crosslink/SKILL.md
Sweep CoreWise Academy guides and add inline links where topics overlap. Use when the user says $crosslink, asks to cross-link guides or add internal links between articles, or after new guides land.
ryanportfolio/Corewise.Academy/.agents/skills/dare/SKILL.md
Use for $dare, first principles, or questioning the problem: four fresh stages decompose, audit, recombine and test, preserving immutable goals and constraints.
Often used withaddskillastra-reviewadvocate
ryanportfolio/Corewise.Academy/.agents/skills/design-study/SKILL.md
Study admired reference websites into a persistent design-learnings file future design work must consult. Use when the user says $design-study, sends links to study for design inspiration, or asks what prior site studies found.
ryanportfolio/Corewise.Academy/.agents/skills/enhance-prompt/SKILL.md
Use when the user asks for a rewritten, copy-ready prompt for another agent or session. Produce the prompt without executing its task.
Often used withaddskilldareastra-review
ryanportfolio/Corewise.Academy/.agents/skills/fable-mode/SKILL.md
Use for difficult multi-step work, uncertain diagnoses, repeated failures, 'did it work/is it fixed/prove it' questions, or tasks where verification and handoff need particular care. Skip routine changes.
Often used withaddskilldareastra-review
ryanportfolio/Corewise.Academy/.agents/skills/forge-repo-ui-skill/SKILL.md
Use when the user wants a repository-specific UI or design skill synthesized from current agent skills; not for ordinary UI implementation or backend-only work.
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.