Repository
hylarucoder/hai-stack agent skills
- skills
- 18
- GitHub stars
- 380
GitHub description: “daily use skills”
- Stars
- 380 (18 forks)
- Licence
- Unknown
- Last push
- Oct 2026
- Created
- Mar 2026
Install all skills
npx skills add hylarucoder/hai-stackAdd --skill <name> for a single skill and -a <agent> to choose the agent (see the agent guides).
Skills in hylarucoder/hai-stack, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Verify a defined software change against requirements and produce a proportional, evidence-backed acceptance report with specification precedence, scope boundaries, requirement-to-evidence… | hylarucoder/ | 380 | — | ~2.1k | Automated safety check: Pass | Unknown | 2 days ago |
| 2 | Produces a ready-to-run ast-grep command or reusable YAML lint/codemod rule, validated against positive and negative fixtures. | hylarucoder/ | 380 | — | ~1.5k | Automated safety check: Pass | Unknown | 2 days ago |
| 3 | Reformats and restructures a README or similar Markdown project document without changing its factual content, voice, or scope, then summarizes formatting-only edits. | hylarucoder/ | 380 | — | ~1.8k | Automated safety check: Pass | Unknown | 2 days ago |
| 4 | Turns supplied content into self-contained HTML and PNG in two modes: card for one shareable frame（知识卡、信息卡、金句卡、封面、把要点做成一张图）, report for multi-section documents（可视化报告、HTML 汇报页、PRD/计划/评审做成网页）. | hylarucoder/ | 380 | — | ~2k | Automated safety check: Pass | Unknown | 2 days ago |
| 5 | Reviews a code change for correctness, security, maintainability, architecture, performance, and verification gaps, or performs a local code-smell review. | hylarucoder/ | 380 | — | ~934 | Automated safety check: Pass | MIT | 2 days ago |
| 6 | Audits an entity model field by field: what should exist, what exists now, where each value belongs (column, config, computed runtime value, or removal), and what must migrate. | hylarucoder/ | 380 | — | ~1.5k | Automated safety check: Pass | Unknown | 2 days ago |
| 7 | 7.Geju Challenges an overly conservative, incremental, or compatibility-led proposal with a bold target model, a concrete kill/merge/split list, materially different options, and a falsifiable first proof… | hylarucoder/ | 380 | — | ~1.8k | Automated safety check: Pass | Unknown | 2 days ago |
| 8 | 8.Goudi Pressure-tests an ambitious proposal and returns a landing judgment, one minimum viable proof, explicit cuts, success/failure signals, and a stop rule. | hylarucoder/ | 380 | — | ~1.3k | Automated safety check: Pass | Unknown | 2 days ago |
| 9 | Investigates architecture and change complexity from repository runtime paths to bounded modules, React components, and shared contracts. | hylarucoder/ | 380 | — | ~2.1k | Automated safety check: Pass | Unknown | 2 days ago |
| 10 | Audits documentation for internal contradictions and/or mismatches with code, config, schemas, and approved contracts. | hylarucoder/ | 380 | — | ~1.1k | Automated safety check: Pass | Unknown | 2 days ago |
| 11 | 11.Hai Debug Diagnoses an unexplained software failure through reproduction, competing hypotheses, discriminating checks, and a causal explanation. | hylarucoder/ | 380 | — | ~1k | Automated safety check: Pass | Unknown | 2 days ago |
| 12 | 12.Hai Goal Creates or rewrites a goal document for ambiguous, multi-phase, high-risk, or explicitly planned execution: verifiable outcome, boundary, current state, phases, proof-bearing todos, dry-run, and… | hylarucoder/ | 380 | — | ~2k | Automated safety check: Pass | Unknown | 2 days ago |
| 13 | 13.Hai Idea Evaluates whether an idea, feature, product, or project deserves attention and returns one verdict—Do, Validate first, Reframe, Defer, or Kill—plus the strongest objection and cheapest… | hylarucoder/ | 380 | — | ~1.3k | Automated safety check: Pass | Unknown | 2 days ago |
| 14 | 14.Hai Naming Recommends names for concepts, identifiers, modules, files, entities, events, or product terms, or audits an existing naming set for misleading vocabulary and viewpoint drift. | hylarucoder/ | 380 | — | ~1.1k | Automated safety check: Pass | Unknown | 2 days ago |
| 15 | 15.Hai Prd Decides whether a PRD is needed, drafts one from a product problem, repairs an existing PRD, or judges its split/merge boundary. | hylarucoder/ | 380 | — | ~2.1k | Automated safety check: Pass | Unknown | 2 days ago |
| 16 | 16.Hai Razor Tests whether each requirement, step, role, field, state, module, layer, abstraction, or rule deserves independent existence, then classifies it as Keep, Merge, Defer, Delete, Replace, or Prove first. | hylarucoder/ | 380 | — | ~1.9k | Automated safety check: Pass | Unknown | 2 days ago |
| 17 | Rebuilds a drifted, repeatedly patched document from verified current conclusions. | hylarucoder/ | 380 | — | ~2k | Automated safety check: Pass | Unknown | 2 days ago |
| 18 | 18.Hai TDD Drives a real behavior change through red-green-refactor and records the failing RED evidence, minimal GREEN implementation, refactor decision, and verification commands. | hylarucoder/ | 380 | — | ~1.8k | Automated safety check: Pass | Unknown | 2 days ago |
Questions, answered from the data.
What is the best skill in hylarucoder/hai-stack?
Write Technical Acceptance Report from hylarucoder/hai-stack ranks first of the 18 skills in hylarucoder/hai-stack listed here, with the highest score: its repository has 380 GitHub stars, its SKILL.md loads about 2.1k tokens and it passes the automated safety check with no findings. Next come Hai Ast Grep and Readme Beautifier.
Are the skills in hylarucoder/hai-stack official?
None yet. All 18 skills in hylarucoder/hai-stack 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 hylarucoder/hai-stack?
Run npx skills add hylarucoder/hai-stack 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.