Repository
HsienW/chat-gun agent skills
- skills
- 8
- GitHub stars
- 143
GitHub description: “🤖 A full-stack Agent Chat Runtime for pre-production validation, built with act, TypeScript, and LangGraph JS combining streaming, multimodal, HITL, and tools with durable Task/Step execution, retry budgets, idempotency, compensation, distributed locks, context governance, OpenTelemetry tracing, model fallback, cost tracking, and Opik evaluation.”
- Stars
- 143 (20 forks)
- Licence
- Unknown
- Last push
- Oct 2026
- Created
- Jun 2026
- agent
- chatbot
- langgraph
- multi-agent
- qwen
- mcp
- ai-agent
Install all skills
npx skills add HsienW/chat-gunAdd --skill <name> for a single skill and -a <agent> to choose the agent (see the agent guides).
Skills in HsienW/chat-gun, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Chat Gun 的前端、OpenSpec、Streaming Event、Tool Renderer、型別邊界、多模態流式鏈路與 React/Vite 編程約束。Use when working on frontend code, tool rendering, streaming contracts, multimodal requests/responses, Weather… | HsienW/ | 143 | — | ~467 | Automated safety check: Pass | Unknown | 5 days ago |
| 2 | 2.Node Provides domain-specific best practices for Node.js development with TypeScript, covering type stripping, async patterns, error handling, streams, modules, testing, performance, caching, logging… | HsienW/ | 143 | — | ~1.6k | Automated safety check: Pass | Unknown | 5 days ago |
| 3 | MUST be considered at task start in this repository to detect OpenSpec change lifecycle work and route Claude Code/CCR coordination tasks without loading unnecessary context. | HsienW/ | 143 | — | ~939 | Automated safety check: Pass | Unknown | 5 days ago |
| 4 | MUST be considered at task start in this repository to detect OpenSpec change lifecycle work and route it to token-efficient stage prompts. | HsienW/ | 143 | — | ~907 | Automated safety check: Pass | Unknown | 5 days ago |
| 5 | MUST be considered at task start in this repository to detect OpenSpec change lifecycle work and route Qwen Code review tasks without loading unnecessary context. | HsienW/ | 143 | — | ~923 | Automated safety check: Pass | Unknown | 5 days ago |
| 6 | 對 OpenSpec、Git Diff、frontend、bff、backend、LangGraph、Tool、MCP 與安全邊界進行獨立唯讀審查，輸出 Blocker、Major、Minor 與標準 Verdict。 | HsienW/ | 143 | — | ~775 | Automated safety check: Pass | Unknown | 5 days ago |
| 7 | Apply when creating, modifying, refactoring, debugging, testing, or reviewing TypeScript, LangGraph JS, LangChain, provider adapter, tool, MCP, prompt, state, checkpoint, runtime event, or backend… | HsienW/ | 143 | — | ~2.1k | Automated safety check: Pass | Unknown | 5 days ago |
| 8 | Apply when creating, modifying, refactoring, debugging, testing, or reviewing TypeScript and Node.js code under bff/ in chat-gun. | HsienW/ | 143 | — | ~2.6k | Automated safety check: Pass | Unknown | 5 days ago |
Questions, answered from the data.
What is the best skill in HsienW/chat-gun?
Chat Gun Frontend Contract from HsienW/chat-gun ranks first of the 8 skills in HsienW/chat-gun listed here, with the highest score: its repository has 143 GitHub stars, its SKILL.md loads about 467 tokens and it passes the automated safety check with no findings. Next come Node and Openspec Workflow Router.
Are the skills in HsienW/chat-gun official?
None yet. All 8 skills in HsienW/chat-gun listed here come from community repositories; a skill counts as official when the product's own GitHub organization publishes it.
How do I install all skills from HsienW/chat-gun?
Run npx skills add HsienW/chat-gun in your project: the open-source skills CLI installs the repository's skills into your coding agent's skills folder. To install a single skill, open its page here for the exact command.
How are these skills ranked?
By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.