skill-creator
Create new skills, modify and improve existing skills, and measure skill performance.
Skill by ZieMat
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/ziemat-skill-creator
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.
About
Use cases: testing, writing, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions: not checked yet.
What's inside
- Skill name
skill-creator- Description
- Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
- License
- unknown
- Instructions
- 482 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (18)
- LICENSE.txt
- SKILL.md
- analyzer.md · agents/
- comparator.md · agents/
- grader.md · agents/
- eval_review.html · assets/
- generate_review.py · eval-viewer/
- viewer.html · eval-viewer/
- schemas.md · references/
- __init__.py · scripts/
- aggregate_benchmark.py · scripts/
- generate_report.py · scripts/
- improve_description.py · scripts/
- package_skill.py · scripts/
- quick_validate.py · scripts/
- run_eval.py · scripts/
- run_loop.py · scripts/
- utils.py · scripts/
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from ZieMat/my-fancy-crazy-prompts
- 0.469score
python-generate-unit-tests
ZieMat
Creates focused Python unit tests with clear assertions and minimal mocking.
SkillCFreshness: CClaude Code +9 - 0.469score
python-identify-critical-scenarios
ZieMat
Identifies the smallest set of critical behaviors in Python code that must not break.
SkillCFreshness: CClaude Code +9 - 0.469score
python-generate-integration-tests
ZieMat
Creates meaningful Python integration tests for module, service, database, API, filesystem, or queue boundaries.
SkillCFreshness: CClaude Code +9 - 0.469score
python-convert-bug-report-to-test
ZieMat
Turns a bug report into a reproducible failing or regression test in Python.
SkillCFreshness: CClaude Code +9 - 0.469score
python-detect-risk-areas
ZieMat
Identifies Python code most likely to break or cause regressions.
SkillCFreshness: CClaude Code +9 - 0.469score
python-find-edge-cases
ZieMat
Finds boundary conditions, invalid inputs, rare states, and surprising combinations in Python functions, classes, services, or scripts.
SkillCFreshness: CClaude Code +9 - 0.466score
python-dead-code
ZieMat
Run vulture to detect dead code in Python projects, then carefully evaluate each finding before acting.
SkillCFreshness: CClaude Code +9 - 0.466score
python-linter
ZieMat
Run ruff and ty to check Python code quality, then fix the errors they report.
SkillCFreshness: CClaude Code +9 - 0.401score
python-project-setup
ZieMat
Initialize a new Python project with uv, git, env files, README/AGENTS docs, pyproject tooling (ruff, ty, pytest, python-dotenv as dev), agents/skills layout…
SkillDFreshness: DClaude Code +9 - 0.208score
design-regression-tests
ZieMat
No description from the publisher yet.
SkillDFreshness: DClaude Code +9 - 0.208score
find-edge-cases
ZieMat
No description from the publisher yet.
SkillDFreshness: DClaude Code +9 - 0.208score
identify-critical-scenarios
ZieMat
No description from the publisher yet.
SkillDFreshness: DClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Apr 15, 2026 (6 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- Repository
- github.com/ZieMat/my-fancy-crazy-prompts
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from ZieMat
- 0.469score
python-generate-unit-tests
ZieMat
Creates focused Python unit tests with clear assertions and minimal mocking.
SkillCFreshness: CClaude Code +9 - 0.469score
python-identify-critical-scenarios
ZieMat
Identifies the smallest set of critical behaviors in Python code that must not break.
SkillCFreshness: CClaude Code +9 - 0.469score
python-generate-integration-tests
ZieMat
Creates meaningful Python integration tests for module, service, database, API, filesystem, or queue boundaries.
SkillCFreshness: CClaude Code +9 - 0.469score
python-convert-bug-report-to-test
ZieMat
Turns a bug report into a reproducible failing or regression test in Python.
SkillCFreshness: CClaude Code +9 - 0.469score
python-detect-risk-areas
ZieMat
Identifies Python code most likely to break or cause regressions.
SkillCFreshness: CClaude Code +9 - 0.469score
python-find-edge-cases
ZieMat
Finds boundary conditions, invalid inputs, rare states, and surprising combinations in Python functions, classes, services, or scripts.
SkillCFreshness: CClaude Code +9
Cite this page
skill-creator. Agent Mart. https://agentmart.dev/skills/ziemat-skill-creator (last updated 2026-10-24)