Agent Skills — English Productivity Pack

Listed on the M8ven Trust Index:

All 5 skills in this repo are listed on OpenAgentSkill; example: git-commit-message

Also listed on AwesomeSkills.dev, and now live on Skillstore.

Also listed in awesome-hermes-agent-skills (Domain skill packs section), merged 2026-10-14.

All 5 skills are also indexed on SkillsMP; example: git-commit-message

A small collection of agent skills for everyday knowledge-work tasks: proofreading technical docs, writing commit messages, turning meeting notes into minutes, reviewing code, and structuring deep research. Free to use, no sign-up.

中文用户：另有《Agent Skills 中文实战包》v1（5 个 skill 中文版 + 中文安装指南 + 3 个中文实战案例），¥9.90 起一次买断 → 爱发电购买。本仓库英文原版永久免费（MIT）。

Prefer a printable desk reference? The code review and git commit skills are also sold as condensed, print-ready cheat sheets (PDF + PNG, $19 one-time) in a Gumroad bundle. The full skill text in this repo stays free (MIT).

Previews above show the top portion of each sheet; the bundle contains the complete sheets (PDF + PNG).

Read the cheat sheets free as Gists: Code Review Cheat Sheet · Git Commit Cheat Sheet. The Gist text is free; the Gumroad bundle above is the condensed, print-ready version.

Install

All five skills at once, via the skills CLI:

npx skills add alapha888/agent-skills-en

No account required. To install a single skill instead, see Install via SkillMD below; or copy any skills/<name>/SKILL.md into your agent's skills directory manually (see How to use).

Skills

Read the proofreading checklist free as a Gist: Proofreading Checklist for Technical Writing.

See it in action

Raw notes in, structured minutes out — the meeting-notes skill's worked example (full text in skills/meeting-notes/SKILL.md; every skill ships a minimal example like this):

Input: "...James said the login page is too slow, Maria suggested adding a cache layer, everyone agreed it's worth a pilot; draft the proposal by next Wednesday; pricing strategy still open, invite Finance next time..."

Output — Bottom line: Pilot a cache layer to speed up the login page; pricing strategy undecided, pending a session with Finance. Decisions: adopt a cache layer for login-page performance (pilot first, not a full rollout). Action items: Maria — draft the caching proposal, due next Wednesday [date to confirm]; [unassigned] — schedule pricing discussion with Finance [time TBD]. Open questions: pricing strategy — no decision reached; the action-item owner will book a dedicated session with Finance.

Note what the skill refuses to do: it does not invent the calendar date for "next Wednesday" or guess an owner the notes never named — missing details are marked, never fabricated.

How to use

Each skill lives in skills/<name>/SKILL.md. The SKILL.md file starts with a name and a description field — the description is written so agent frameworks can surface the skill when a matching request comes in.

To use a skill, tell your agent what you want to do (for example, "proofread this README" or "turn these notes into minutes"), and point it at the corresponding SKILL.md if it doesn't pick it up automatically. The agent then follows the workflow inside.

Security: nothing to execute

A study of 31,132 published agent skills found 26.1% contained at least one security vulnerability — and skills that bundle executable scripts were 2.12× more likely to be vulnerable than instruction-only ones (coverage).

This pack is instruction-only by design:

• Each skill is a single SKILL.md — plain Markdown, no scripts, no binaries, no dependencies.
• All five skills together are 283 lines. You can read every word before you install.
• No skill touches credentials, the network, or your files on its own; it only tells your agent how to structure a task.

Install via SkillMD

All five skills are listed on SkillMD. Install any of them by name:

npx skillmds@latest add alapha888/git-commit-message
npx skillmds@latest add alapha888/code-review-checklist
npx skillmds@latest add alapha888/meeting-notes
npx skillmds@latest add alapha888/deep-research-framework
npx skillmds@latest add alapha888/tech-writing-proofread

Design principles

• Checklists, not essays. Every skill is a workflow the agent can execute step by step, with a minimal runnable example.
• Proofread, don't rewrite. The proofreading skill flags defects and suggests fixes; it never rewrites your voice away.
• No fabrication. The meeting-notes and research skills refuse to invent names, dates, or sources — missing information is marked, never guessed.
• Actionable over exhaustive. Code review is capped at 10 comments; a review drowning in trivia is worse than a short one that finds the real bug.

License

MIT. Use them, fork them, adapt them — attribution appreciated but not required.

Custom skill development

I take on custom skill / AI workflow commissions: a tailored skill for your team's recurring workflow (from ¥499), or a lightweight automation / landing-page build (from ¥999). Reach me via Afdian DM. After we agree on scope, the 30% deposit goes through this Afdian listing (¥150 / ¥299 tiers).

Agent Skills Pro

Need the advanced workflows? Agent Skills Pro ($39 one-time) adds three paid skills — multi-agent-decompose, codebase-map, and release-notes — for coordinating parallel agents, onboarding onto unfamiliar repos, and cutting readable releases. The free pack above stays free.

Validating next (not yet built)

• MDClip Pro — web page → Markdown converter; planned ¥15/month (not built yet, no payment taken). Waitlist: https://alapha888.github.io/mdclip-waitlist/ — builds only if 30 people sign up by Oct 31, 2026.
• SyncMatrix — multi-account publishing management for matrix/team operators; planned ¥39/month (not built yet, no payment taken). Waitlist: https://alapha888.github.io/syncmatrix-waitlist/ — builds only if 20 people sign up by Oct 31, 2026.