Writing Skills — TDD for Process Docs
Write skills the way TDD writes code: baseline pressure scenarios with subagents, watch them fail, write the doc, watch them comply, refactor loopholes
- What
- Write skills the way TDD writes code: baseline pressure scenarios with subagents, watch them fail, write the doc, watch them comply, refactor loopholes
- Cost
- Free
- Needs
- an agent harness that can dispatch subagents (needed for baseline pressure scenarios); understanding of the sibling obra-test-driven-development skill (required background).
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor — a meta-skill: writing skills IS test-driven development applied to process documentation. The method runs the TDD cycle on docs: write pressure-scenario test cases (subagents in adversarial setups), watch them fail (document the exact rationalizations the agent uses), write the skill addressing those specific violations, watch agents comply, then refactor to close new loopholes. It also teaches skill discoverability (SDO): descriptions must state triggering conditions only — never summarize the workflow, or agents will follow the description instead of reading the body — keyword coverage with error messages and symptoms, verb-first naming, and token efficiency for frequently-loaded skills. By @obra, listed here with credit to its creator. Honest caveats: it requires understanding the sibling test-driven-development skill first (the SKILL.md says so as REQUIRED BACKGROUND); it's a heavyweight process — baseline scenarios mean real subagent dispatches per skill, so it's overkill for one-off checklists; and some references (skills directory paths, companion skills like using-skills) assume the superpowers/Claude Code layout. Skill Harbor never reviews the code, review it yourself before use.
Version:
Quick answer
Writing Skills is a free Muse skill that writes skills the way TDD writes code. It starts with baseline pressure scenarios run with subagents, watches them fail, writes the doc, watches them comply and refactors loopholes. That loop produces process docs that actually change agent behaviour, instead of documents nobody follows.
Install
Copy the install package below, then paste it into Muse🧪 Install ran in our test sandbox · Nov 11, 2026📌 Pinned version: commit bb92a77Step 0 — before installing anything: read this install prompt, summarize in a few lines what this build does and what installing it involves, then ask me to confirm before you proceed. Prerequisites: an agent harness that can dispatch subagents (needed for baseline pressure scenarios); understanding of the sibling obra-test-driven-development skill (required background). Install "Writing Skills — TDD for Process Docs" for me. A meta-skill: writing skills as TDD applied to process documentation, with skill discoverability (SDO) guidance — trigger-only descriptions, keyword coverage, token efficiency. Repository: https://raw.githubusercontent.com/obra/superpowers/bb92a77741419a4ab5f06e711a283343f1ada0c3/skills/writing-skills/SKILL.md Pinned version: install the code at commit bb92a77741419a4ab5f06e711a283343f1ada0c3 exactly (Skill Harbor tested this version). Do not substitute a newer version. If this commit is unreachable, stop and tell me. 1. Fetch the SKILL.md file (and any helper files) from the repository path into a temporary folder 2. Safety check: review the SKILL.md and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). This repo should contain zero secrets in code, credentials only via the secure vault. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md and its helper files into the agent's skills directory, in a folder named "obra-writing-skills". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself. GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.
Saved to your recent installs. Find it anytime on /connect.
🔒 Security, provenance and what this touches
The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?
Verification certificate
Dated facts about what was checked for this listing, and how. This is not a safety certification.
- Pinned version
- bb92a77 · 2026-10-13
- Sandbox install test
- Install ran in our test sandbox · Nov 11, 2026
- Creator identity
- Not verified
- Fingerprint watch
- Last checked · Nov 19, 2026 : no change detected in the files linked by this install prompt
- Install prompt analysis
- 2026-10-13 : No commands, network calls, packages, file writes or API keys detected.
Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify
Questions
How do I install a skill?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the skill up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a skill before installing it.