A code writing assistant that actually verifies its work before calling it done. It reads files before editing them, makes targeted changes to existing code, and runs tests to prove everything works. No placeholders, no TODO comments, just production-ready implementations. The background task execution via sessions_spawn is smart for larger refactors where you don't want to wait around. It's opinionated about its workflow (read first, edit surgically, test always) which means less back and forth fixing half-baked changes. If you're tired of AI code tools that generate broken boilerplate and leave you to debug, this takes a more rigorous approach.
- skills.sh installs
- 4.1K
- GitHub stars
- 32
- last updated
- Aug 21, 2026
Install
$ npx -y skills add starchild-ai-agent/official-skills --skill coder --agent claude-codeInstalls into .claude/skills of the current project.
Files
A code writing assistant that actually verifies its work before calling it done. It reads files before editing them, makes targeted changes to existing code, and runs tests to prove everything works. No placeholders, no TODO comments, just production-ready implementations. The background task execution via sessions_spawn is smart for larger refactors where you don't want to wait around. It's opinionated about its workflow (read first, edit surgically, test always) which means less back and forth fixing half-baked changes. If you're tired of AI code tools that generate broken boilerplate and leave you to debug, this takes a more rigorous approach.
Browse the repository on GitHubSponsors
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/starchild-ai-agent/official-skills
- Categories
- Documentation, AI & Agent Building, Debugging
More from starchild-ai-agent/official-skills
All 43- Slide Creator4.1K
- Wallet Policy4.1K
- Community Publish4K
- Preview Dev4K
- Web Crawler3.9K
- Chart3.9K
- User Onboarding3K
- Agentx2.8K
- Video2.7K
- Byok Custom Model2.7K
- Chatgpt Codex Onboarding2.5K
- Xai Grok Onboarding2.3K
- Image Edit2.3K
- Image Portrait2.2K
- Agent Hooks2.2K
- Wechat Binding2.2K
- Tg Bot Binding2.2K
- Image Create2.1K
- Image Ecommerce2K
- Image 3d2K
- Image Bg Remove1.8K
- Cli Bridge1.8K
- Video Analysis1.8K
- Ui Design1.8K
Recommended
More Documentation
test-smell-detectiondotnet/skillsDeep-dive audit using the full testsmells.org 19-smell academic catalog for tests in any language. Every finding maps to a named, citable smell from the researc4.1Kskills.sh installs
prometheus-cardinality-troubleshootergrafana/skillsDiagnostic guide for active Prometheus cardinality problems — slow queries, OOMing Prometheus, high Grafana Cloud Active Series or DPM bills, "too many samples"4.1Kskills.sh installsmtp-hot-reloaddotnet/skillsSuggests using Microsoft Testing Platform (MTP) hot reload to iterate fixes on failing tests without rebuilding. Use when user says "hot reload tests", "iterate4.1Kskills.sh installs
literature-reviewlingzhi227/agent-research-skillsConduct comprehensive literature reviews using multi-perspective dialogue simulation. Generate diverse expert personas, conduct grounded Q&A conversations, and 4.1Kskills.sh installs
spark-engineerjeffallan/claude-skillsUse when writing Spark jobs, debugging performance issues, or configuring cluster settings for Apache Spark applications, distributed data processing pipelines,4.1Kskills.sh installsresolve-project-referencesdotnet/skillsGuide for interpreting ResolveProjectReferences time in MSBuild performance summaries. Activate when ResolveProjectReferences appears as the most expensive targ4.1Kskills.sh installs