Agent skill · Documentation

skill-creator

Create, improve, evaluate, benchmark skills. Use when authoring a new skill, updating an existing one, running evals, or optimizing a skill's description for triggering. Don't use for invoking skills, writing prose, or scaffolding Python projects.

luongnv89github.com/luongnv89GitHub ↗
claude-codeships scriptsMIT
Install
npx skills add luongnv89/asm --skill skill-creator --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 32
SKILL.md size: 21 KB
Bundled scripts: yes
Version: 1.13.2
Declared author: Luong NGUYEN <luongnv89@gmail.com>
Path: skills/skill-creator/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 782
Language: TypeScript

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# Skill Creator A skill for creating new skills and iteratively improving them. The agent's context budget is the primary constraint, so this SKILL.md links out to focused reference files. The core loop: 1. Decide what the skill should do and how it should do it 2. Write a draft 3. Run test prompts against claude-with-access-to-the-skill 4. Evaluate results with the user (qualitative review via `eval-viewer/generate_review.py`, plus quantitative evals) 5. Revise the skill based on feedback and benchmarks 6. Repeat until satisfied; expand the test set and try again at scale Identify where the user is in this loop and jump in there. New skill from scratch → start at step 1. Existing draft → jump to step 3 or 4. User wants to vibe-iterate without formal evals → support that. After the skill stabilizes, optionally run the description improver to optimize triggering. ## Two entry paths The skill supports two distinct workflows. **Identify which one the user is on before you do anything else** — they don't share a starting step. - **Path A — Create a new skill from scratch.** The user wants to capture a workflow, codify a pattern, or build a new capability. Start at **"Creating a skill"*

What's inside
Steps it walks through
  1. Two entry paths
  2. Step Completion Reports
  3. Communicating with the user
  4. Mandatory Rule for Repo-Mutating Skills
  5. Frontmatter rules (mandatory)
  6. Creating a skill
  7. Capture Intent
  8. Interview and Research
  9. Write the SKILL.md
  10. Skill Writing Guide
  11. Make it predictable (publish-ready by construction)
  12. Adversarial review (mandatory before evals)
  13. Running and evaluating test cases
  14. Improving an existing skill
Ships with 24 files
  • LICENSE.txt
  • agents/analyzer.md
  • agents/comparator.md
  • agents/grader.md
  • assets/eval_review.html
  • docs/README.md
  • eval-viewer/generate_review.py
  • eval-viewer/viewer.html
  • references/description-guide.md
  • references/description-optimization.md
  • references/environment-modes.md
  • references/eval-loop.md
  • references/exemplars.md
  • references/frontmatter-rules.md
  • references/iteration.md
  • references/predictability-rubric.md
  • references/readme-template.md
  • references/schemas.md
  • references/subagent-patterns.md
  • references/validation-prompts.md
  • references/writing-guide.md
  • scripts/__init__.py
  • scripts/aggregate_benchmark.py
  • scripts/generate_report.py
first 24 of 32
Commands it runs
python -m scripts.package_skill <path/to/skill-folder>
More from asm
All skills →
About this skill
What does the skill-creator skill do?

Create, improve, evaluate, benchmark skills. Use when authoring a new skill, updating an existing one, running evals, or optimizing a skill's description for triggering. Don't use for invoking skills, writing prose, or scaffolding Python projects.

How do I install it?

Run `npx skills add luongnv89/asm --skill skill-creator --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From luongnv89/asm, a repository with 782 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going