Repository
leo-kuang-ai/spec-first agent skills
- skills
- 35
- GitHub stars
- 107
GitHub description: “仓库原生 AI Coding Harness —— 把一次性 AI 对话变成可治理、可验证、可沉淀的工程闭环 · spec-first.cn”
- Stars
- 107 (13 forks)
- Licence
- MIT
- Last push
- Oct 2026
- Created
- Mar 2026
- Homepage
- spec-first.cn
- agent
- ai-coding
- claude
- codex
- sdd
- spec
- tdd
- claude-code
- cursor
- kiro
- qoder
- opencode
- zcode
- llm
- ai-agent
- ai-programming
Install all skills
npx skills add leo-kuang-ai/spec-firstAdd --skill <name> for a single skill and -a <agent> to choose the agent (see the agent guides).
Skills in leo-kuang-ai/spec-first, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Audit mobile App PRD/Figma/local-source consistency across page routes, KMP/Clean Architecture, components, analytics, i18n, engineering quality, and industry lenses before runtime validation; use… | leo-kuang-ai/ | 107 | — | ~4.6k | Automated safety check: Pass | MIT | 2 days ago |
| 2 | Create a durable cross-session handoff or resume from a user-selected continuity source. | leo-kuang-ai/ | 107 | — | ~1.8k | Automated safety check: Pass | MIT | 2 days ago |
| 3 | 3.Spec Pov Give a decisive, project-grounded verdict on an external input — judged against the current project, not in the abstract. | leo-kuang-ai/ | 107 | — | ~4.5k | Automated safety check: Pass | MIT | 2 days ago |
| 4 | Resolve PR review feedback by evaluating validity and fixing issues with conflict-aware resolver dispatch. | leo-kuang-ai/ | 107 | — | ~1.8k | Automated safety check: Notes | MIT | 2 days ago |
| 5 | Analyze explicit Riffrec product-feedback captures, including riffrec-.zip, the Riffrec session.json + events.json + recording.webm + voice.webm bundle, or media/notes the user identifies as a… | leo-kuang-ai/ | 107 | — | ~1.4k | Automated safety check: Pass | MIT | 2 days ago |
| 6 | Document a recently solved problem or durable project vocabulary in docs/solutions/ or CONCEPTS.md. | leo-kuang-ai/ | 107 | — | ~18k | Automated safety check: Pass | MIT | 2 days ago |
| 7 | 7.Spec Prd Public workflow entrypoint (spec-prd): create, write, refine, or validate planning-readiness of brownfield PRD-grade requirements for existing systems before implementation planning. | leo-kuang-ai/ | 107 | — | ~16k | Automated safety check: Pass | MIT | 2 days ago |
| 8 | Run metric-driven iterative optimization loops. An agent skill from leo-kuang-ai/spec-first. | leo-kuang-ai/ | 107 | — | ~13k | Automated safety check: Pass | MIT | 2 days ago |
| 9 | Refresh docs/solutions learnings against the current codebase. | leo-kuang-ai/ | 107 | — | ~15k | Automated safety check: Warn | MIT | 2 days ago |
| 10 | 10.Autoresearch Autonomous goal-directed iteration loop: modify, verify, keep/discard against a metric or a checkable success predicate, with bounded cycles, plateau/ceiling backstops, safety-screened commands, and… | leo-kuang-ai/ | 107 | — | ~2.2k | Automated safety check: Pass | MIT | 2 days ago |
| 11 | 11.Spec Explain Create a durable, visual teaching artifact for a concept, diff, idea, or recent-work window, with an optional check-in that makes it stick. | leo-kuang-ai/ | 107 | — | ~3.3k | Automated safety check: Pass | MIT | 2 days ago |
| 12 | 12.Spec Polish Start the dev server, inspect the feature in browser, and iterate on polish. | leo-kuang-ai/ | 107 | — | ~2.5k | Automated safety check: Pass | MIT | 2 days ago |
| 13 | Use this standalone skill to build or update a project architecture knowledge base (docs/architecture.md) for multi-end monorepos or any repo with a shared layer, from code evidence, or to check… | leo-kuang-ai/ | 107 | — | ~1.4k | Automated safety check: Pass | MIT | 2 days ago |
| 14 | 14.Spec Promote Draft launch or promotion copy for a shipped feature. An agent skill from leo-kuang-ai/spec-first. | leo-kuang-ai/ | 107 | — | ~2.8k | Automated safety check: Pass | MIT | 2 days ago |
| 15 | Build a throwaway prototype to answer an unresolved product behavior or visual question before implementation. | leo-kuang-ai/ | 107 | — | ~1k | Automated safety check: Pass | MIT | 2 days ago |
| 16 | Simplify recently changed code for clarity, reuse, quality, and efficiency while preserving behavior. | leo-kuang-ai/ | 107 | — | ~2.4k | Automated safety check: Pass | MIT | 2 days ago |
| 17 | 17.Spec Sweep Sweep configured feedback sources (Slack, GitHub Issues; email experimental) for new items: acknowledge at source, analyze recordings, verify fixes merged to main, and emit a spec-lfg-ready plan. | leo-kuang-ai/ | 107 | — | ~4.8k | Automated safety check: Notes | MIT | 2 days ago |
| 18 | Run browser tests on pages affected by current PR or branch. | leo-kuang-ai/ | 107 | — | ~1.7k | Automated safety check: Pass | MIT | 2 days ago |
| 19 | Standalone entry governor for spec-first. An agent skill from leo-kuang-ai/spec-first. | leo-kuang-ai/ | 107 | — | ~1k | Automated safety check: Pass | MIT | 2 days ago |
| 20 | Explore vague or ambitious ideas into a right-sized requirements-only unified plan. | leo-kuang-ai/ | 107 | — | ~11k | Automated safety check: Pass | MIT | 2 days ago |
| 21 | 21.Spec Debug Diagnosis loop for bugs and failing behavior. An agent skill from leo-kuang-ai/spec-first. | leo-kuang-ai/ | 107 | — | ~9.8k | Automated safety check: Pass | MIT | 2 days ago |
| 22 | 使用角色化 lens 审查 requirements、plans、task packs 或 specs。适用于改进既有规划与执行文档；默认 standard roster（≤3 reviewers），完整条件 roster 使用 roster:full。 | leo-kuang-ai/ | 107 | — | ~6.6k | Automated safety check: Pass | MIT | 2 days ago |
| 23 | 23.Spec Dogfood Hands-off, diff-scoped browser QA of the active branch or PR. | leo-kuang-ai/ | 107 | — | ~6.1k | Automated safety check: Notes | MIT | 2 days ago |
| 24 | 24.Spec Ideate Generate and evaluate grounded ideas. An agent skill from leo-kuang-ai/spec-first. | leo-kuang-ai/ | 107 | — | ~14k | Automated safety check: Pass | MIT | 2 days ago |
| 25 | Install, configure, verify, and refresh required harness runtime readiness facts for spec-first workflows on Claude Code, Codex, Cursor, Kiro, Qoder, or OpenCode. | leo-kuang-ai/ | 107 | — | ~11k | Automated safety check: Pass | MIT | 2 days ago |
| 26 | Internal helper for caller-owned git worktree isolation. An agent skill from leo-kuang-ai/spec-first. | leo-kuang-ai/ | 107 | — | ~3.2k | Automated safety check: Notes | MIT | 2 days ago |
| 27 | Use this standalone skill when the user asks to mine a repo's existing coding conventions for future AI coding, generate or refresh project rules with AGENTS.md/CLAUDE.md pointers, create Cursor or… | leo-kuang-ai/ | 107 | — | ~1.2k | Automated safety check: Pass | MIT | 2 days ago |
| 28 | Create or update STRATEGY.md. An agent skill from leo-kuang-ai/spec-first. | leo-kuang-ai/ | 107 | — | ~1.6k | Automated safety check: Pass | MIT | 2 days ago |
| 29 | 公开 workflow：创建、修改或迁移项目拥有的 Agent Skill package，或对现有/外部 package 做用户明确要求、零执行的只读验证与 readiness 报告时使用；也用于按已接受的 audit finding 修复 source skill。不要用于一次性回答、解释/总结/翻译、普通代码 review、第三方 Skill 纯安装或导入、跨仓批量修改，或直接修补… | leo-kuang-ai/ | 107 | — | ~1.6k | Automated safety check: Pass | MIT | 2 days ago |
| 30 | Public workflow entrypoint (spec-write-tasks): compile a settled local spec-plan into an optional derived task pack for spec-work, or validate an existing local task pack before execution. | leo-kuang-ai/ | 107 | — | ~2.6k | Automated safety check: Pass | MIT | 2 days ago |
| 31 | 31.Spec Lfg Run the full hands-off engineering pipeline from planning through a green PR. | leo-kuang-ai/ | 107 | — | ~6.1k | Automated safety check: Pass | MIT | 2 days ago |
| 32 | 32.Spec Commit Internal commit helper for public workflows that already hold explicit commit authorization; creates scoped, value-communicating commits without owning push or PR landing. | leo-kuang-ai/ | 107 | — | ~2.1k | Automated safety check: Notes | MIT | 2 days ago |
| 33 | Internal landing helper for public workflows that already hold explicit commit and landing authorization; commits scoped changes, pushes, and creates or updates a PR with a value-first description. | leo-kuang-ai/ | 107 | — | ~5.6k | Automated safety check: Pass | MIT | 2 days ago |
| 34 | Build and test iOS apps on simulator using XcodeBuildMCP. An agent skill from leo-kuang-ai/spec-first. | leo-kuang-ai/ | 107 | — | ~2.3k | Automated safety check: Pass | MIT | 2 days ago |
| 35 | 35.Spec Work Execute a settled plan, validated task pack, spec path, or concrete implementation request end-to-end. | leo-kuang-ai/ | 107 | — | ~9.4k | Automated safety check: Pass | MIT | 2 days ago |
Questions, answered from the data.
What is the best skill in leo-kuang-ai/spec-first?
Spec App Consistency Audit from leo-kuang-ai/spec-first ranks first of the 35 skills in leo-kuang-ai/spec-first listed here, with the highest score: its repository has 107 GitHub stars, its SKILL.md loads about 4.6k tokens and it passes the automated safety check with no findings. Next come Spec Handoff and Spec Pov.
Are the skills in leo-kuang-ai/spec-first official?
None yet. All 35 skills in leo-kuang-ai/spec-first 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 leo-kuang-ai/spec-first?
Run npx skills add leo-kuang-ai/spec-first 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.