Skip to content
Agentmart
Submit a tool

writing-skills

Use when creating, editing, or verifying reusable agent skills and process documentation before distribution.

Skill by eyildirim82

IndexedMIT
Write a review

Chalk Labs

Need help deploying writing-skills?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/eyildirim82-writing-skills

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Use when creating, editing, or verifying reusable agent skills and process documentation before distribution.

Use cases: writing, agent-building

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found
Runs as
Node.js package

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/writing-skills

What's inside

Skill name
writing-skills
Description
Use when creating, editing, or verifying reusable agent skills and process documentation before distribution.
License
MIT
Instructions
26 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts

Files (7)

  • SKILL.md
  • anthropic-best-practices.md
  • CLAUDE_MD_TESTING.md · examples/
  • graphviz-conventions.dot
  • persuasion-principles.md
  • render-graphs.js
  • testing-skills-with-subagents.md

SKILL.md (first lines)

# Writing Skills

Skills are production behavior. Author them with behavioral evidence, concise discovery metadata, and pressure scenarios that test the behavior they are meant to teach.

## Preferred skill-TDD loop
For discipline/process skills, baseline the undesired behavior first when practical, then make the smallest guidance change that closes the observed failure, rerun the scenario, and add adjacent regressions. This meta-skill keeps behavior testing as a required authoring discipline for distributed process changes; it does not impose obsolete universal application-code TDD above the active execution profile.

## Skill shape
- `SKILL.md` frontmatter: `name` and a third-person `description` beginning with "Use when..." that states triggering conditions, not the workflow summary.
- Keep frequently loaded bootstrap skills extremely concise; move heavy references/tools to supporting files.
- Use concrete trigger keywords so agents can discover the right skill.
- Prefer positive output contracts/recipes for shape problems; use strong prohibitions/red flags only for demonstrated discipline failures.
- Avoid redundant cross-skill process text. Named sub-skills are capabilities governed by the active Adaptive profile.

## Testing by skill type
- Discipline skill: pressure/rationalization scenarios.
- Technique skill: application + edge cases.
- Pattern skill: recognition + counterexamples.
- Reference skill: retrieval + application.

Success means the agent behaves correctly under representative pressure, not merely that the prose sounds clear.

## Self-review
Check frontmatter, discovery wording, token efficiency, duplicated guidance, placeholders, unresolved exceptions, and whether tests actually exercise the behavior changed. Keep mechanical constraints in scripts/tests when they can be enforced mechanically.

From eyildirim82/adaptive-superpowers, MIT.

More from eyildirim82/adaptive-superpowers

Signals

Stars
0
Forks
0
Open issues
21
Last commit (this folder)
Sep 12, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from eyildirim82

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get writing-skills running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying writing-skills?

CallGet help
Cite this page

writing-skills. Agent Mart. https://agentmart.dev/skills/eyildirim82-writing-skills (last updated 2026-10-24)