andreaswasita/copilot-agents-dojo/writing-skills
Claude Code and agent skill by andreaswasita/copilot-agents-dojo
- community
Checking that the SKILL.md file is still in the repository.
Authors new SKILL.md files that conform to the dojo spec.
Install
npx vskill@latest install andreaswasita/copilot-agents-dojo/writing-skillsSKILL.md
Writing Skills (meta) Skill
Walks the agent through producing a new SKILL.md that conforms to spec/copilot-skills-spec.md and passes scripts/verify.sh spec. Covers intent capture, folder layout, frontmatter, canonical body sections, and the test loop. Does NOT auto-register the new skill in skills.md — that is the regen script's job.
When to Use
- The user explicitly asks to create or amend a skill.
- A
tasks/lessons.mdpattern has ≥3 occurrences and should graduate to a skill. - The dojo curator (see
self-improvement) flags a candidate skill to formalize. - Team adapts the dojo for a new domain.
- NOT for one-off rules — those live in
tasks/lessons.mduntil they recur.
Prerequisites
spec/copilot-skills-spec.mdandtemplate/SKILL.mdexist (this skill is parasitic on them).- The
view,edit, andpowershellCopilot tools. scripts/verify.shavailable on the path (or git bash on Windows).- Decision recorded for which tier the new skill belongs in.
How to Run
Quick Reference
| Tier | Folder | Loaded when | |
|---|---|---|---|
| core | skills/ | Always | |
| practical | skills/ | On trigger | |
| optional | optional-skills/ | Installed explicitly |
| Frontmatter key | Rule | |||
|---|---|---|---|---|
name | Lowercase, hyphens, matches folder | |||
description | ≤60 chars, ends with period, no marketing words | |||
tier | core \ | practical \ | optional | |
category | See spec §1.2 valid set | |||
created_by | human or agent | |||
platforms | Subset of [windows, macos, linux] | |||
author | Name (@handle), human first |
| Body section (in order) | Purpose | |
|---|---|---|
| When to Use | Triggers and contexts | |
| Prerequisites | What must be true before running | |
| How to Run | One-screen happy path | |
| Quick Reference | Tables the agent can act from | |
| Procedure | Deep step-by-step | |
| Pitfalls | DO NOT imperative register | |
| Verification | Checkboxes that prove the skill ran |
Procedure
Step 1: Capture Intent
Answer four questions before touching files:
- What behavior does this skill teach?
- When should it trigger? (keywords, contexts)
- What does good output look like?
- What mistakes does it prevent?
If lesson-driven, open tasks/lessons.md and read every entry with the same error_type to extract the pattern.
Step 2: Pick Tier and Folder
| Signal | Tier | |
|---|---|---|
| Always-on discipline applied to every session | core | |
| Triggered by a task family (review, debug, plan) | practical | |
| Heavy, niche, or requires external installation | optional |
Create the folder:
Step 3: Copy the Template
Use edit to read template/SKILL.md and edit to write <folder>/<name>/SKILL.md. Replace every placeholder. Do NOT introduce sections outside the canonical seven.
Step 4: Frontmatter
Forbidden description words (marketing — flagged by verify.sh):
Step 5: Body — Canonical Sections
Write each section in order. The Verification section MUST be a checklist whose items are testable — not aspirations.
In prose, reference Copilot tools by name in backticks (view, edit, grep, glob, powershell, web_fetch, task). Do NOT instruct the agent to call bare shell utilities — verify.sh warns on these:
Step 6: Run the Spec Gate
Iterate until the new skill produces no errors and no warnings.
Step 7: Smoke Test
Open a fresh session. Use a trigger phrase the skill claims to handle. Observe whether it activates and whether the output reflects the procedure. Iterate description and triggers as needed.
Pitfalls
- DO NOT invent new body sections. Seven canonical, in fixed order.
- DO NOT write a description over 60 chars or without a period — the gate will reject it.
- DO NOT use marketing adjectives in the description.
- DO NOT instruct the agent to call bare shell utilities. Use Copilot tool names.
- DO NOT register the skill manually in
skills.md— let the regen script do it. - DO NOT ship a skill without verifying it actually triggers on its claimed contexts.
Verification
- [ ]
bash scripts/verify.sh specproduces no errors for the new skill. - [ ] No warnings on the new skill (banned shell utilities, etc.).
- [ ] Frontmatter complete with all required keys.
- [ ] Body sections present in canonical order.
- [ ] Smoke test in a fresh session confirms the skill activates as claimed.
- [ ] If created from a lesson, the originating
tasks/lessons.mdentry references the new skill.
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingoptional-skills/writing-skills/SKILL.md
Popularity
- Repository stars
- 48
- Repository forks
- 15
- 7-day trend score
- 19
Stars and forks are for the whole GitHub repository, not this skill alone. Refreshed 29 Apr 2026, 6 months ago.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/andreaswasita/copilot-agents-dojo/writing-skills)