mstar-harness

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

• grill-me

  Interview the user relentlessly about a plan or design until shared understanding, resolving each decision branch. Use when a plan or design needs stress-testing, or the user says 'grill me'.

  skills/grill-me/SKILL.md on GitHub (opens in a new tab)

• mstar-artifacts

  Plan artifacts: main plans, durable review summaries, QC/QA bundles, workflow state/config/progress/evidence, issue capture, residual severity. Read when authoring or mapping them.

  skills/mstar-artifacts/SKILL.md on GitHub (opens in a new tab)

• mstar-audit

  Audit or survey a codebase into an evidence-backed, prioritized review report (read-only): bugs, security, perf, test gaps, tech debt, DX, a PR/branch/diff (`pr` variant), test-suite audit.

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

• mstar-branch-worktree

  Branch authorization, control/integration/source checkout isolation, L1/L2 writable-task isolation, QC/QA checkout alignment, guarded worktree/branch cleanup after merge.

  skills/mstar-branch-worktree/SKILL.md on GitHub (opens in a new tab)

• mstar-coding-behavior

  Use for non-trivial implementation, debugging, refactoring or code review in any project: requirement drift, speculative complexity, agent-facing interfaces. Not workflow or role selection.

  skills/mstar-coding-behavior/SKILL.md on GitHub (opens in a new tab)

• mstar-compound-refresh

  Knowledge maintenance 与项目知识 bootstrap：审查/更新/合并/清理 `{KNOWLEDGE_DIR}` 文档，或从代码库提炼 CONCEPTS.md 与基线 knowledge。触发：可合并文档、定期维护、stale scaffolding、显式 bootstrap/refresh。

  skills/mstar-compound-refresh/SKILL.md on GitHub (opens in a new tab)

• mstar-compound

  知识结晶 (compound)：把已解决的问题沉淀为 `{KNOWLEDGE_DIR}` 下的结构化知识文档，迭代收口时提升 specs/guides；双轨 Bug/Knowledge，含重叠与可发现性检查。无结晶时以 reasoned `skipped` 结束。

  skills/mstar-compound/SKILL.md on GitHub (opens in a new tab)

• mstar-conventions

  harness 路径约定：`{HARNESS_DIR}`/`{PLAN_DIR}`/`{SDD_DIR}`/`{ITERATION_DIR}`/`{KNOWLEDGE_DIR}`/`{SPECS_DIR}`/`{REVIEW_DIR}` 等符号的发现与初始化、docs 与 harness 子树边界、Spec 分支模型。读写 `.mstar/` 或开 plan 前必读。

  skills/mstar-conventions/SKILL.md on GitHub (opens in a new tab)

• mstar-design-md

  DESIGN.md 设计系统规范：创建/审计/维护 design tokens、三级完整性清单、light/dark 双主题（DESIGN.dark.md）。用户提到 DESIGN.md / design tokens / design system，或实现、审查 UI 时读取。

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

• mstar-design-system

  Use when an implementation must be walked into alignment with an existing baseline — a prototype, a design export, an existing product's markup, or a written design contract — and each difference has to be judged as defect, decision, or phantom. Not for designing from nothing, and not for authoring or auditing `DESIGN.md` itself (that is `mstar-design-md`).

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

• mstar-dispatch-gates

  Dispatch gates: PM-only leaf dispatch, executor/delegation identity, anti-recursion, parallel readiness, SDD QC tri-review, inline single-seat exceptions. Read before dispatch or leaf execution.

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

• mstar-e2e

  Separately requested E2E / real-browser / device / installed-deployment verification. Load only for an explicit request or `amazing-e2e-check`; never from routine QA or missing screenshots.

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

• mstar-engine-legacy

  Engine-absent safety and historical-field archive: field history, checkout/atomic safety, dispatch/QC invariants. Use only when the host has no CLI/engine (execution state = conversation tracking).

  skills/mstar-engine-legacy/SKILL.md on GitHub (opens in a new tab)

• mstar-harness-core

  Lifecycle and authorization authority: delivery loop, state machine, Done ownership, task-category routing, topic index. Use for lifecycle, authorization, Done, routing, or CLI/plugin version drift.

  skills/mstar-harness-core/SKILL.md on GitHub (opens in a new tab)

• mstar-host

  Host adapter for OpenCode, Cursor, Codex, Kimi, ZCode, omp, dsh: entry, dispatch, plan mode, parallel dispatch, skill/command loading. Detect from session tools, then read `references/<host>.md`.

  skills/mstar-host/SKILL.md on GitHub (opens in a new tab)

• mstar-iteration

  Start, drive, resume or close an iteration (also without a slash command): Phase 1 direction lock, autonomous execute, iteration-close, PR delivery, merge-ready loop, post-merge close.

  skills/mstar-iteration/SKILL.md on GitHub (opens in a new tab)

• mstar-phase-gates

  Spec-Driven 双阶段门禁：Prepare（specify→clarify→plan）、Execute（plan(locked)→tasks→implement，多 task 默认 SDD）；意图门禁、clarify 纪律、hotfix 压缩路径、可验证编辑、Phase Gate 证据。

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

• mstar-pr-loop

  Opt-in skill loaded when the user explicitly asks for a review → fix loop on an existing ready PR, or when iteration Phase 1 selects it as that iteration's `pr_merge_policy: reviewed-auto` review path. It never activates for routine review requests or on its own initiative.

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

• mstar-project-governance

  项目治理：roadmap 内容在 `{HARNESS_DIR}/store.db` 的权威读写（import/export、revision-guarded replace）、milestone 结构化目标与 issue 关联、issue capture、`_default` 归属。

  skills/mstar-project-governance/SKILL.md on GitHub (opens in a new tab)

• mstar-review-qc

  QC orchestration: SDD mandatory plan QC tri-review (`qc1`…`qc3` + consolidated), inline/hotfix single seat, tri identity gate, residual registration. Read before dispatching or consolidating QC.

  skills/mstar-review-qc/SKILL.md on GitHub (opens in a new tab)

• mstar-roles

  Role prompt hub and single load-selection authority: identity-first `references/<role>.md`, PM-activated skill presets, the none/named-preset/resume decision. Always load for any Morning Star role.

  skills/mstar-roles/SKILL.md on GitHub (opens in a new tab)

• mstar-sdd

  Subagent-driven development (SDD): file handoff, per-task implementer + reviewer (L2), progress ledger, review package for plan QC tri (L3), fresh or sticky session. Read under Execution mode: sdd.

  skills/mstar-sdd/SKILL.md on GitHub (opens in a new tab)

• mstar-skill-authoring

  Agent skill 撰写 / 重写 / 优化规范（SkillsBench 实验门控）。在新建任意 skill、大改 SKILL.md、改写 description 触发契约、压缩过长 body、评审 skill 结构、或判断某段行为塑形文案是否值得保留时读取。适用于任何领域的 skill，不限于本仓库专题；不用于普通应用实现。

  skills/mstar-skill-authoring/SKILL.md on GitHub (opens in a new tab)

• mstar-strategy

  Morning Star 全局战略方向 —— 创建并维护 `STRATEGY.md`（项目级战略文档），作为 brainstorm/plan 的上游锚点。定义产品愿景、技术方向、不做事项、决策原则。触发：项目初始化、方向性决策变更、或 PM 要求战略对齐时。

  skills/mstar-strategy/SKILL.md on GitHub (opens in a new tab)

• mstar-use-cli

  Use when choosing, running or interpreting `mstar`/`mstar-harness` CLI commands: family selection, semantic preconditions (control root, cwd, identity, revision/token), exit codes and refusal codes.

  skills/mstar-use-cli/SKILL.md on GitHub (opens in a new tab)

• pm

  PM entry shim: force `project-manager` orchestration when the user invokes `/pm` or this skill. Boot, routing and dispatch SSOT live in `mstar-roles/references/project-manager.md`.

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

• mstar-routing-eval

  [Cursor maint] Morning Star 路由与 prompt 迭代评估 —— 维护/回归专用（非日常 PM 编排 runtime）。路径：本仓库 `.cursor/skills/mstar-routing-eval/`。(1) PM 路由回归：`assets/routing-evals.json`；(2) Prompt/规则迭代评估；(3) Routing Eval Report 模板。变更 PM 路由或 harness 门禁、`@prompt-engineer` 改 agents/skills、或显式跑场景集时 Read。

  .cursor/skills/mstar-routing-eval/SKILL.md on GitHub (opens in a new tab)

• broken-skill

  No description in the SKILL.md.

  packages/dsh/tests/fixtures/skills/broken-skill/SKILL.md on GitHub (opens in a new tab)

• good-skill

  Use when the gated-session e2e proves relative bundledSkillDir resolution against the launch cwd.

  packages/dsh/tests/fixtures/skills/good-skill/SKILL.md on GitHub (opens in a new tab)

No skill matches that filter.

Similar skills

• reactive-resumeby reactive-resume A one-of-a-kind resume builder that keeps your privacy in mind. Completely secure, customizable, portable, open-source and free forever. Tr… 45.3k stars · 9 skills
• OpenVikingby volcengine Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills. 41.5k stars · 22 skills
• harnessby revfactory A meta-skill that designs domain-specific agent teams, defines specialized agents, and generates the skills they use. 9.3k stars · 2 skills
• reaby morluto Reverse engineer anything with agents, from app behavior down to native binaries. 431k stars · 5 skills
• skillsby mattpocock Skills for Real Engineers. Straight from my .agents directory. 313k stars · 30 skills
• superpowersby obra An agentic skills framework & software development methodology that works. 312k stars · 15 skills