Skill Creator
This is meta-tooling for building AI agent skills with token efficiency as the first principle. It enforces a three-level loading system where you front-load critical info, defer details to references folders, and design for context windows between 4k and 32k tokens. The approach is opinionated: imperative compression, progressive disclosure, lazy references. If you're writing skills that agents keep running out of context on, or you're annoyed at verbose prompt engineering practices, this gives you a strict framework. It's marked P0 critical, which feels a bit self-important for what's essentially a set of authoring guidelines, but the token economy angle is legitimately useful if you're shipping skills at scale.
- GitHub stars
- 538
- last updated
- Aug 21, 2026
Install
$ npx -y skills add hoangnguyen0403/agent-skills-standard --skill 'Skill Creator' --agent claude-codeInstalls into .claude/skills of the current project.
Files
Repository Skill Maintenance Standard
Priority: P1 (HIGH)
Project-local maintenance procedures for contributing to agent-skills-standard.
Generic Skill Authoring: Follow the canonical
common-skill-creatorstandard; this local skill covers repository maintenance only.
Repository Contribution Workflow
Sponsors
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 languageDetails
- Repository
- github.com/hoangnguyen0403/agent-skills-standard
- Category
- AI & Agent Building
- License
- Apache-2.0
- First seen
- Jun 3, 2026
More from hoangnguyen0403/agent-skills-standard
All 28- Traceability Audit
- Update Docs
- Verify Bug
- Verify Work
- Zephyr Coverage Analysis
- Battle Test
- Brainstorm Feature
- Caveman
- Caveman Commit
- Caveman Compress
- Caveman Review
- Code Review
- Codebase Review
- Deploy Release
- Design Solution
- Dev Fix
- Implement Feature
- Implementation Readiness
- Pentest
- Plan Feature
- Publish Notes
- Retro Learn
- Review Ticket
- Sdlc
Recommended
More AI & Agent Building
release-guardhoangsonww/claude-code-agent-monitorRun release-readiness checks for this repository. Use when validating docs, scripts, verification coverage, and operational safety before merge or release.0skills.sh installsrepo-onboardinghoangsonww/claude-code-agent-monitorUnderstand this repository quickly before making changes. Use for architecture discovery, ownership mapping, command selection, and initial implementation plann0skills.sh installs