Skill Creator
Creates new Claude skills from scratch, optimizes existing ones, and runs evals to measure performance. The workflow is iterative: draft the skill, write test prompts, run benchmarks, evaluate results both qualitatively and quantitatively, then refine based on feedback. It includes a separate script for optimizing skill descriptions to improve triggering accuracy, which matters because Claude tends to undertrigger skills. The tool adjusts its communication style based on user technical literacy, from plumbers opening terminals for the first time to experienced developers. Useful when you need to capture a workflow you've been doing manually, or when a skill isn't firing when it should.
- skills.sh installs
- 484
- GitHub stars
- 33.2K
- last updated
- Aug 21, 2026
Install
$ npx -y skills add davila7/claude-code-templates --skill skill-creator --agent claude-codeInstalls into .claude/skills of the current project.
Files
Skill Creator
A skill for creating new skills and iteratively improving them.
At a high level, the process of creating a skill goes like this:
- Decide what you want the skill to do and roughly how it should do it
- Write a draft of the skill
- Create a few test prompts and run claude-with-access-to-the-skill on them
- Help the user evaluate the results both qualitatively and quantitatively
- While the runs happen in the background, draft some quantitative evals if there aren't any (if there are some, you can either use as is or modify if you feel something needs to change about them). Then explain them to the user (or if they already existed, explain the ones that already exist)
- Use the
eval-viewer/generate_review.pyscript to show the user the results for them to look at, and also let them look at the quantitative metrics
- Rewrite the skill based on feedback from the user's evaluation of the results (and also if there are any glaring flaws that become apparent from the quantitative benchmarks)
- Repeat until you're satisfied
- Expand the test set and try again at larger scale
Sponsors
Promote your product hereReach 125k+ visitors monthlyPromote your product hereReach 125k+ visitors monthly
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any language
Agent CaffeineSponsoredClose your lid, come back to finished workSnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthlyWaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthlyknobsSponsoredSee your site on any phone, any day, in any languageDetails
- Repository
- github.com/davila7/claude-code-templates
- Categories
- Testing & QA, Skill Development, Debugging
- First seen
- Jun 3, 2026
More from davila7/claude-code-templates
All 618- Supabase Postgres Best Practices481
- File Organizer480
- Research Engineer478
- Llama Cpp475
- App Builder474
- Security Review471
- Api Security Best Practices466
- Senior Secops466
- Long Context465
- Autogpt Agents464
- Parallel Agents463
- Serving Llms Vllm461
- Llamaindex460
- Code Review457
- Computer Use Agents455
- Powershell Windows454
- React Useeffect454
- Backend Patterns452
- Find Bugs447
- Langgraph447
- Agent Md Refactor446
- Autonomous Agent Patterns446
- D3 Viz445
- Manim444
Recommended
More Testing & QA1
bash-masterjosiahsiegel/claude-plugin-marketplaceExpert bash/shell scripting across environments where Bash is available (Linux, macOS, Git Bash on Windows, WSL, containers). This is a Bash-focused skill - it 462skills.sh installs
bash-masterjosiahsiegel/claude-plugin-marketplaceExpert bash/shell scripting across environments where Bash is available (Linux, macOS, Git Bash on Windows, WSL, containers). This is a Bash-focused skill - it 462skills.sh installs2
nestjs-best-practicesejirocodes/agent-skillsNestJS 11+ best practices for enterprise Node.js applications with TypeScript. Use when writing, reviewing, or refactoring NestJS controllers, services, modules460skills.sh installs
nestjs-best-practicesejirocodes/agent-skillsNestJS 11+ best practices for enterprise Node.js applications with TypeScript. Use when writing, reviewing, or refactoring NestJS controllers, services, modules460skills.sh installs3
email-subject-linesopenclaudia/openclaudia-skillsGenerate, evaluate, and A/B test email subject lines for maximum open rates. Includes formulas for curiosity, urgency, personalization, and more. Trigger phrase458skills.sh installs
email-subject-linesopenclaudia/openclaudia-skillsGenerate, evaluate, and A/B test email subject lines for maximum open rates. Includes formulas for curiosity, urgency, personalization, and more. Trigger phrase458skills.sh installs4
postmanpostman-devrel/agent-skillsFull API lifecycle management through Postman. Sync OpenAPI specs to collections, generate typed client code, run API tests, create mock servers, publish docume458skills.sh installs
postmanpostman-devrel/agent-skillsFull API lifecycle management through Postman. Sync OpenAPI specs to collections, generate typed client code, run API tests, create mock servers, publish docume458skills.sh installs5
code-reviewdavila7/claude-code-templatesPerform code reviews following Sentry engineering practices. Use when reviewing pull requests, examining code changes, or providing feedback on code quality. Co457skills.sh installs
code-reviewdavila7/claude-code-templatesPerform code reviews following Sentry engineering practices. Use when reviewing pull requests, examining code changes, or providing feedback on code quality. Co457skills.sh installs6
systematic-debuggingsecondsky/claude-skillsFour-phase debugging framework that ensures root cause investigation before attempting fixes. Never jump to solutions. Use when encountering any bug, test failu457skills.sh installs
systematic-debuggingsecondsky/claude-skillsFour-phase debugging framework that ensures root cause investigation before attempting fixes. Never jump to solutions. Use when encountering any bug, test failu457skills.sh installs