broken-skill
25Skill Claude CodeCodex
This skill is missing the required description frontmatter field — the skill-lint gate flags writes into it.
Skill Claude CodeCodex
This skill is missing the required description frontmatter field — the skill-lint gate flags writes into it.
Skill Claude CodeCodex
Use when the gated-session e2e proves relative bundledSkillDir resolution against the launch cwd.
Cursor rule
When using Cursor Plan mode with Morning Star, dual-write CreatePlan to .mstar/ harness artifacts and require per-task commits.
Cursor rule
Ensure Morning Star core skill is loaded first in Cursor plugin usage.
Skill Claude CodeCodex
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
Skill Claude CodeCodex
Morning Star plan harness artifacts — {PLANDIR} main plans and durable review summaries, {SDDDIR}/review/ ephemeral QC/QA bundles, {KNOWLEDGEDIR} / {ITERATIONDIR} indexes, plus {HARNESSDIR}/status.json (v2 root register) / {WORKFLOWDIR}/ /snapshot.json (plan rows + leases) and {PROJECTDIR}/ /residuals.json (residual…
Skill Claude CodeCodex
Morning Star codebase audit — survey any repository and produce prioritized, self-contained improvement plans for the normal Prepare → Execute flow. Strictly read-only on source code. Use when asked to audit or survey a codebase, find improvement opportunities (bugs, security, performance, test gaps, tech debt…
Skill Claude CodeCodex
Morning Star 业务仓 Git 功能分支、worktree 隔离(L1 跨 plan:control worktree + 每 plan feature worktree + executionlease,默认 gitignore 下经 control 绝对路径读写进程产物;L2 同 plan:references/parallel-writable-pre-dispatch.md,N 次 invoke ≠ 隔离)、Spec 集成分支、QC/QA 检出对齐(Review cwd / Working branch / planid / Review range / Diff basis 三审 + QA 逐字相同)。Read…
Skill Claude CodeCodex
A set of coding guidelines for implementation, debugging, refactoring, and code review. It emphasizes understanding the code first, making small focused changes, reproducing bugs before fixing them, and checking feedback with evidence.
Skill Claude CodeCodex
A knowledge-maintenance workflow for reviewing project knowledge documents, removing outdated material, merging overlaps, or creating a starter knowledge set from a codebase.
Skill Claude CodeCodex
A process for saving useful lessons from completed development work as organized project documents. The documents are stored where future planning and debugging can find them.
Skill Claude CodeCodex
Morning Star (启明星) harness 计划目录约定 —— {HARNESSDIR} / {PLANDIR} / {SDDDIR} / {ITERATIONDIR} / {KNOWLEDGEDIR} / {SPECSDIR} / {WORKFLOWDIR} / {PROJECTDIR} 发现与初始化(默认 .mstar/,兼容 .agents/)、docs 与 harness 子树边界、review bundle、未启用 plan 时的工作方式、Spec 集成分支与多 Plan 实现分支(显式 base / merge 靶 / PR target)、Morning Star plan-writing path…
Skill Claude CodeCodex
DESIGN.md design system specification for Morning Star projects. Create, audit, and maintain project-level design tokens (Colors, Typography, Spacing, Elevation, Motion, Shapes, Components, Voice & Content) using Vercel Geist as reference template. Three-level completeness checklist (MVP/Standard/Production) with…
Skill Claude CodeCodex
A set of rules for assigning work to subagents in the Morning Star workflow. It defines who may delegate, how assignments identify roles, and which safety limits apply to workers.
Skill Claude CodeCodex
A conditional archive of Morning Star workflow rules for hosts that do not have the engine tool or engine library. It stores the longer contract text that runtime skills otherwise reference.
Skill Claude CodeCodex
A central rulebook for the Morning Star coding workflow. It defines which instructions to read first, how work moves through stages, and when a task may be marked done.
Skill Claude CodeCodex
Morning Star host adapter (OpenCode, Cursor, Codex, Kimi, ZCode, omp, dsh). Use after mstar-harness-core whenever host entry, clarify, dispatch, or plan UX differs by platform - OpenCode question/task-tool subagent invoke, Cursor /pm and CreatePlan/SwitchMode dual-write and Task parallel QC, Codex plugin skills plus…
Skill Claude CodeCodex
Use when starting, driving, resuming, or closing a Morning Star iteration, or running an autonomous Phase 1–5 loop — including without a slash command (e.g. 'start an iteration', 'drive the iteration', 'run an autonomous loop'). Manages Phase 1 (default interactive direction lock; opt-in autonomous), Autonomous…
Skill Claude CodeCodex
Morning Star Spec-Driven 双阶段门禁:Prepare(specify → clarify → plan)、Execute(plan(locked) → tasks → implement;多 task 默认 Execution mode: sdd)。覆盖意图门禁、长期目标优先、分批 roadmap 强制落盘、clarify 纪律、hotfix 压缩路径、可验证编辑、Phase Gate 最小证据。Read when judging Prepare/Execute gates, before first implement dispatch, when product/architect enter…
Skill Claude CodeCodex
A project-management rulebook for writing project roadmaps and tracking unresolved issues. A roadmap describes project direction, while a residual register records open problems until they are verified as closed.
Skill Claude CodeCodex
Morning Star QC orchestration — SDD mandatory plan QC tri-review ({SDDDIR}/review/qc1.md…qc3.md + consolidated); inline/hotfix single-seat (qc.md in review bundle); PM dispatch timing, tri identity gate, residual registration contract, layer boundaries, durable plan summary. Leaf QC execution →…
Skill Claude CodeCodex
Morning Star role prompt hub — agents/.md shells plus full behavior in references/.md. Role files are identity-first (mission / responsibilities / NEVER rules); topic mstar- skills appear only as PM-activated skill presets (Assignment Skill presets: field), not default dependencies. Always load for any Morning Star…
Skill Claude CodeCodex
Morning Star subagent-driven development (SDD) — file handoff, per-task implementer + task reviewer (L2), progress ledger, branch review-package for plan QC tri (L3). Implementer session fresh (default) or sticky (same dev subagent across tasks — references/sticky-implementer-session.md). Must Read when…
Skill Claude CodeCodex
A writing guide for creating, rewriting, reviewing, and optimizing agent skills. It covers when a skill should activate, how much instruction it should contain, and how to verify that changes improve agent behavior.