hikarilan-skills

In the author's own words, from each skill's SKILL.md.

• afk

  Autonomous work while the user is away, for any agent. Use when the user types /afk [duration or instructions], says they are going offline or leaving for N hours and you should decide for yourself (我要离线, 你自行决断), or says they are back (我回来了) during an afk. It defaults to 8 hours, decides on its own, parks what it is unsure of or does it reversibly and lets the user rule later, and schedules a che…

  skills/afk/SKILL.md on GitHub (opens in a new tab)

• capability-pruning

  Prune a codebase by capability — inventory every capability, give each an evidence card, and let the owner decide removals item by item. Use when simplifying or slimming a project, hunting for unused features or dead mechanisms, or before claiming that something is unused, never used, or safe to delete.

  skills/capability-pruning/SKILL.md on GitHub (opens in a new tab)

• concurrent-worktrees

  Run several lines of work in parallel using git worktrees — when a tree is worth creating, how to split roles between an orchestrator and its agents, and how to merge back without losing anyone's changes. Use when work will run alongside other sessions or agents, when spawning agents into worktrees, or when merging a worktree branch back to the trunk.

  skills/concurrent-worktrees/SKILL.md on GitHub (opens in a new tab)

• e2e-first-testing

  Test strategy for a repository — which tests to write, keep, or delete. Use when adding tests for a change or a bug fix, designing fakes, mocks or test doubles, reviewing a diff that adds or edits tests, deciding whether a regression test is warranted, or pruning a slow or brittle test suite.

  skills/e2e-first-testing/SKILL.md on GitHub (opens in a new tab)

• llm-agent-surface

  Design rules for what an LLM sees inside an agent framework — tool schemas, rejection messages, prompts — and for where the framework stops and the model decides. Use when building or changing an LLM agent, adding a tool or a schema field, writing a rejection or validation message, fixing a wrong model decision, or adding validation, retries or guards around model output.

  skills/llm-agent-surface/SKILL.md on GitHub (opens in a new tab)

• matt-skills-on-openspec

  Wire Matt Pocock's engineering skills onto a repo whose work items are OpenSpec changes — which skill maps to which change artifact or /opsx command, and which need no wiring at all. Use when installing or running to-spec, to-tickets, triage, wayfinder, implement, research, domain-modeling, or code-review in an OpenSpec repo.

  skills/matt-skills-on-openspec/SKILL.md on GitHub (opens in a new tab)

• minimal-design-gate

  A gate against over-design, applied before and after a change. Use when proposing a design or a fix, writing a brief for another agent, reviewing a diff or an agent's delivery, or when a change adds fields, options, abstractions, fallbacks, compatibility paths or dependencies.

  skills/minimal-design-gate/SKILL.md on GitHub (opens in a new tab)

• progress

  Report where the work stands, as tables in one fixed shape - what you are doing now, what comes next, what is not done, what is done, how long is left, and how far along it is. Use when the user types /progress, or asks where you are, what the status is, how far along you are, what is left, or how long this will take. Any arguments are extra questions to answer after the standard report.

  skills/progress/SKILL.md on GitHub (opens in a new tab)

• repo-audit-loop

  Audit a whole repository, or a batch of finished work, until a round finds nothing — coverage ledger over every tracked file, orthogonal lenses, spec–code sync, every public entry actually run, and a defect ledger cleared as you go. Use when asked to audit, review or health-check a project, when closing out a batch of changes, before a release or handover, or when checking that specs and code sti…

  skills/repo-audit-loop/SKILL.md on GitHub (opens in a new tab)

• site-annotated-gates

  Enforce architectural and code-shape rules with static gates whose exceptions are annotated at the code site. Use when adding a lint or CI check for an architectural constraint, when a test is about to lock code structure, when an allowlist or exemption list keeps growing, or when a rule needs justified exceptions.

  skills/site-annotated-gates/SKILL.md on GitHub (opens in a new tab)

• structural-fix

  How to fix a defect so its whole class disappears, not just the reported instance. Use when fixing a bug, writing a fix brief for another agent, reviewing someone's fix, or when a fix is tempting to write as a guard, special case, retry cap or fallback.

  skills/structural-fix/SKILL.md on GitHub (opens in a new tab)

No skill matches that filter.

Similar skills

• reaby morluto Reverse engineer anything with agents, from app behavior down to native binaries. 431k stars · 5 skills
• ECCby affaan-m The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Cod… 297k stars · 30 skills
• andrej-karpathy-skillsby multica-ai A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls. 230k stars · 1 skill
• ponytailby DietrichGebert Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote. 185k stars · 6 skills
• difyby langgenius Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-h… 160k stars
• ui-ux-pro-max-skillby nextlevelbuilder An AI skill that provides design intelligence for building professional UI/UX across multiple platforms. 145k stars · 7 skills