Summary
of the process. disable-model-invocation: true only for skills that must never fire on their own; the description then reads as a human-facing one-liner. Keep
pwguler/skills
write-skill
Create or edit a document an agent reads and prove it changes behavior. Use when writing or editing a skill, AGENTS.md, CLAUDE.md, a system prompt, or other agent-facing prose, or verifying one before it ships.
Installation
$
npx skills add pwguler/skills --skill write-skill
Similar popular skills
Related neighbors and high-traction skills in the same topics — useful to compare before installing.
gws-docs-write
Similar name
googleworkspace/cli
Google Docs: Append text to a document.
44.6K installs
documentation-writer
Similar name
github/awesome-copilot
Diátaxis Documentation Expert. An expert technical writer specializing in creating high-quality…
26.2K installs
svelte-code-writer
Similar name
sveltejs/ai-tools
CLI tools for Svelte 5 documentation lookup and code analysis. MUST be used whenever creating, …
9.7K installs
write-coding-standards-from-file
Similar name
github/awesome-copilot
Write a coding standards document for a project using the coding styles from the file(s) and/or…
9.6K installs
pr-writer
Similar name
getsentry/skills
Create or refresh reviewer-facing PR titles and descriptions. Use when opening a PR, updating i…
3.9K installs
write-spec
Similar name
anthropics/knowledge-work-plugins
Write a feature spec or PRD from a problem statement or feature idea. Use when turning a vague …
3.1K installsAlso in this package
Other skills from pwguler/skills · top by installs.
npx skills add pwguler/skills
More details
Agent compatibility
Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.
Claude Code
Declared
Cursor
Not declared
Codex
Not declared
GitHub Copilot
Not declared
Windsurf
Not declared
Gemini CLI
Not declared
Cline
Not declared
OpenCode
Not declared
Repository health
Stars
8
License
LICENSE
Default branch
main
Open issues
0
Status
Active
Skill metadata
Parsed from SKILL.md frontmatter.
Declared agents
claude-code
Package contents
Files included with this skill beyond the listing page.
-
skill md
SKILL.md1,994 B -
docs
SUMMARY.md229 B
History
- First seen on skills.sh
- First recorded snapshot · 74 installs
SKILL.md
Writing for agents is test-first development applied to prose. The same loop ships every document an agent reads: skills, AGENTS.md, CLAUDE.md, system prompts.
- Baseline first: run the scenario the document targets on an agent WITHOUT it, and record exactly how it fails or rationalizes. No observed failure means the document has nothing to teach.
- Write the minimum prose that fixes those specific failures. Not a manual: the shortest process that changes the behavior.
- Re-run the scenario with the document loaded. It passes or the document is wrong.
- Close loopholes: new rationalizations found on re-runs get plugged, then verified again.
A test harness changes mechanics, not the loop: when one exists, automate the baseline re-run.
Conventions for skills in this repo:
- Frontmatter carries
name(letters, digits, hyphens) anddescription. The description states when to fire, with trigger phrasing ("Use when..."), not a summary of the process. disable-model-invocation: trueonly for skills that must never fire on their own; the description then reads as a human-facing one-liner.- Keep SKILL.md lean. Separate files only for heavy reference or reusable assets; link them relatively.
- Name the capability, not the tool. A harness binding (a subagent, the question tool,
/design,run) is written as a preference, with what to do when it is absent. Degrade the mechanism, never the guarantee: where no substitute exists, the skill stops and says so rather than proceeding without it. - No em dashes. Decisive present tense. Zero upstream or status mentions.
Skip it when the work is a one-off, when standard practice is already well documented, or when a linter or hook could enforce the rule mechanically.