Reusable skills for your AI agents
365Skill is our public lab for agent skills: a standard SKILL.md format, a deny-by-default publish policy and an evals harness. Open source, installable, forkable — the exact setup we run our own agents on.
What are Agent Skills?
An agent skill is a job description for an AI agent: a directory with a SKILL.md that says when to engage, which steps to follow and which resources to load.
A standard SKILL.md format
A Markdown file with frontmatter: name and description drive triggering, the body spells out steps, constraints and output format. Executable by agents, readable by humans.
Loaded on demand
The agent sees only skill names and descriptions until a task matches — then it reads the full file. Skills can bundle instructions, deterministic scripts and references that load only when needed.
Portable across clients
An open directory format supported by mainstream coding agents — Claude Code, Codex, Cursor and others. Write once, version in git, share anywhere.
11 original skills
All 365-original skills currently public: graded, evals-tested, and published under a deny-by-default policy.
365-five-step-dev-codex
A five-step dev workflow (Codex edition): Research → Plan → Implement → Review → Verify. Risk-graded, plan-first, evidence-based verification — top-tier models reserved for high-stakes decisions.
365-chatgpt-pro-delivery
Coordinate one bounded collaboration between Codex and an explicitly requested ChatGPT Pro workspace: Pro research/creative work combined with Codex verification, deliverable divided between the two.
365-session-rotation-maintainer
Rotate, replace, or hand off a long-running Codex task to one successor while preserving durable work state, Git ownership, acknowledgement, and verified closeout.
parallel-sessions-protocol
Coordinate parallel dev sessions on one repo: draft-PR board registration, resource claiming, ledger writes only at merge time, merge discipline, three-checkpoint refresh.
discover-project-skills
Inventories a project's existing skills, discovers reusable practices and — with your approval — extracts them into portable skill packages. Ships with a Python structural scanner; discovery and audit are read-only.
shopify-theme-delivery
Draft-first Shopify theme delivery: layered architecture, content preservation, remote readback, browser acceptance and dynamic DOM stability checks — never publishes without approval.
gws-workspace
Operate Gmail, Calendar, Drive, Sheets, Docs and more through the gws CLI: read-by-default safety gates, helper-command cheat sheet, and a from-zero OAuth setup guide.
gws-weekly-digest
A weekly mail+calendar briefing workflow: last week's mail stats, day-grouped upcoming events, markdown digest plus chat summary — strictly read-only.
365-five-step-dev-claude
Graded five-step dev flow (Claude Code edition) for business-minded developers: A/B/C risk grading, Plan approval and Verify evidence as the human control points, plus a model-tier gate for high-stakes work.
365-five-step-retro-claude
The five-step retrospective loop: mine real run logs (logbook) for process issues, then upgrade the flow itself with approval — no rule changes on impressions.
project-health-check
Read-only cross-project health sweep: CI red streaks, stale PRs, unpushed commits and orphan worktrees — one page of judgment, never fixes.
Recommended: community skills
We use these community skills from mattpocock/skills (MIT) ourselves. Maintained upstream — click through to the source to install.
grilling
Stress-test a plan, decision or idea: one question at a time, each with a recommended answer, until the design is sharp enough to ship.
View sourcecode-review
Two-axis code review — Standards vs Spec — in parallel sub-agents, reported side by side.
View sourcetdd
Test-driven development: red-green-refactor and integration tests, tests first.
View sourcewayfinder
Plan huge work as a shared map of decision tickets, resolved one at a time without losing context.
View sourcewait-what
Stop — that last message did not land. Re-pitch it in simpler language and get back on the same channel.
View sourceteach
Teach the user a new skill or concept within the workspace, with learning-record formats.
View sourceEngineering discipline
Deny-by-default publishing
The public repo is a deterministic export of a private source repo: only skill IDs whitelisted in catalog/publication-policy.json ship, and CI rejects unlisted skill directories, evals and references.
Trigger evals
Every skill carries 10 positive and 10 negative cases in English and Chinese — fire when it should, stay quiet when it shouldn't. Structure checks, unit tests and real-repo scans gate every release.
Safety boundaries
The scanner never reads or outputs .env* files, credentials, private keys or secret stores, and skips dependency folders and build artifacts. Discovery and audit are read-only; writes happen only after your explicit approval.
Install in three minutes
Skills are plain directories. No package-manager magic.
Clone the repo
git clone https://github.com/laojin1900/365Skill.gitApache-2.0 — fork it, change it, republish it.
Link into your agent's skills directory
ln -s "$PWD/skills/discover-project-skills" ~/.codex/skills/Codex shown; copying the directory works too. For other clients (Claude Code, Cursor, …), drop the skill into the path their docs specify.
Invoke it
Start a task and say: use $discover-project-skills to scan this repository. See the repo README for client-specific adapters.
Useful? Give it a star
Stars, forks and issues all welcome — or see where 365Skill sits in the product family.