epic-harness

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

• _critic

  HarnessX Critic (Tier 2.1) — adversarial review of evolved-skill proposals against trace evidence. Detects reward hacking and manifest/evidence contradictions. Out-of-band LLM counterpart to the in-loop deterministic critic in src/evolve/critic.rs.

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

• _dispatch

  Core router. Always active. Auto-invokes matching skill before every response. Runs confusion protocol on high-risk ambiguity.

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

• agent-introspection

  Loop-breaking self-diagnosis. Use when 3+ consecutive failures occur, circular retries persist, or context overwhelms the session.

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

• audit

  Audit phase. Parallel review: code quality + security + tests. Semantic dedup of cross-mode findings. Outputs PASS/WARN/FAIL per dimension. Validates spec coverage.

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

• commit

  Conventional Commits 1.0 generator. Stages relevant files, infers type(scope): description, never uses --no-verify.

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

• context

  Working-state snapshot guidance. Restates task/files/decisions in one block so state survives context compaction. Compaction timing is the host's job.

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

• council

  4-voice parallel deliberation (Architect · Skeptic · Pragmatist · Critic) for architecture, tech selection, or design decisions with no clear answer. Anti-anchoring: each voice gets independent context. Records decision in harness-mem.

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

• debug

  Systematic root-cause isolation for test failures, runtime errors, or unexpected behavior. Narrow hypothesis → verify → fix.

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

• discover

  Trigger: vague/unfocused request or solution-without-problem. Also invoked via /discover command. Reframes goal before acting.

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

• document

  Documentation generator for public APIs, functions, and modules. Use when exports, signatures, or new modules are added or changed.

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

• eval

  Quality and performance evaluation with baseline comparison. Sub-modes: correctness, performance, quality, regression. Outputs PASS/WARN/FAIL per dimension. Use for pre-ship evaluation or regression checks.

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

• evolve

  Ring 3 evolution engine. Analyzes session observations, generates and improves evolved skills, shows metrics dashboard. Subcommands: status, history, rollback, reset. Use for post-session review and skill improvement.

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

• go

  Go phase. Reads the approved SPEC file, maps Requirements to tasks (plan), executes via TDD (build), and integrates results verifying all Acceptance Criteria.

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

• orbit

  State-persisted autonomous pipeline: spec → go → audit → eval → ship → evolve in one command. Auto-detects direct/council/interactive mode. Crash-recoverable via PIPELINE-*.json. Hands-off until PR.

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

• orchestrate

  Trigger: active multi-agent run. Handles inbox reading, dep resolution, message formatting, handoffs. Also provides status dashboard and intervention control via internal modes.

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

• perf

  Performance optimizer for loops, DB queries, rendering, and batch operations. Catches N+1 queries, missing indexes, and unnecessary re-renders.

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

• reflect

  On-demand human self-assessment of AI usage quality. Scores 5 dimensions from session data. Not agent performance review.

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

• secure

  Security review checklist with optional engagement scoping. Use when auth, DB, API, infra, or secrets code is touched.

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

• ship

  Ship phase. Runs isolated integration test in a fresh worktree, creates a PR with full spec + audit report in the body, watches CI, and auto-fixes failures.

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

• simplify

  Code simplification for high-complexity files. Targets deep nesting, copy-paste patterns, and god functions.

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

• spec

  Spec phase. Converts user requirements into a numbered Requirements + Acceptance Criteria document saved as SPEC-{timestamp}.md. Prompts /team suggestion when 3+ requirements are detected.

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

• tdd

  Test-Driven Development enforcer. Red→Green→Refactor cycle with no production code without a failing test first. Use for new features and bug fixes.

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

• team

  Org-level agent team designer via `epic team` CLI (cross-project, append-merge). Subcommands: list, show, sync, link, unlink, history. Use when setting up agents, designing teams, or /spec yields 3+ requirements.

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

• threat-model

  Threat modeling and attack surface analysis. Use when assessing security boundaries, modeling threat actors, or generating threat scenarios.

  skills/threat-model/SKILL.md on GitHub (opens in a new tab)

• triage

  Adversarial validation of vulnerability findings. Use when triaging security findings, validating vulnerabilities, or prioritizing remediation.

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

• verify

  Pre-merge verification gate. Build, test, and lint must all pass before marking done or shipping.

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

• vuln-scan

  Systematic vulnerability scan across injection, auth, data exposure, and dependencies — traced by reading code, not grepping for keywords. Use when scanning for vulnerabilities, reviewing security, or validating threat models.

  skills/vuln-scan/SKILL.md on GitHub (opens in a new tab)

• benchmark

  Executes Bare-vs-Epic A/B benchmarking, Ring 0 Guard 50 challenge, and full golden set evaluation for epic-harness. Orchestrates worker sessions, enforces strict workspace isolation, and synthesizes multi-dimensional comparison reports in TUI. Triggers: /benchmark, 'benchmark', 'a/b test', 'eval harness', 'smoke test', 'full eval'.

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

No skill matches that filter.

Similar skills

• ECCby affaan-m The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Cod… 288k stars · 30 skills
• cavemanby JuliusBrussee 🪨 why use many token when few token do trick. Viral skill + proxy for coding agents that cuts 65% of tokens by talking like a caveman. 115k stars · 20 skills
• CowAgentby zhayujie Open-source personal AI assistant & Agent Harness. Plans tasks, runs tools and skills, self-evolves with memory and knowledge. Multi-agent,… 47.6k stars · 3 skills
• khazix-skillsby KKKKhazix 数字生命卡兹克开源的 AI Skills 合集 | Agent Skills: leader（帮你定义目标）, neat-freak 洁癖, hv-analysis, khazix-writer & more — Claude Code, Codex & 40+ agents 21.6k stars · 6 skills
• ai-guideby liyupi 程序员鱼皮的 AI 资源大全 + Vibe Coding 零基础教程，分享 OpenClaw 保姆级教程、大模型玩法（DeepSeek / GPT / Gemini / Claude / GLM）、最新 AI 资讯、Prompt 提示词大全、AI 知识百科（Agent Skil… 21.6k stars
• cc-hahaby NanmiCoder 本地优先的跨平台 Claude Code / AI Agent 桌面工作台：多 Agent 协作、Git Worktree、代码 Diff、技能市场、多模型、Computer Use、桌面宠物；支持微信、飞书、钉钉及 H5 等远程访问。 | Local-first Claude… 15.2k stars · 4 skills