[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7DTSAGGWNBNXJFEPMXWGC19":3,"skill-same:01M7DTSAGGWNBNXJFEPMXWGC19":47},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":29,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M7DTSAGGWNBNXJFEPMXWGC19","mk-help",null,"Workflow navigator: scans project state (plans, reviews, tests, git) and recommends the next pipeline step. Use for 'what next?' or 'where am I?'. NOT for complexity routing (mk:scale-routing).","ngocsangyem\u002FMeowKit","ngocsangyem","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F33769536?v=4","01M6J3FSMJAG9PVQEGRT7AQ9J2","Sang Nguyen","01M6J3FSRTJG0MNP6NV71639RM",16,"MIT","https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Fkit\u002Fbundles\u002Fcodex\u002Froot\u002F.agents\u002Fskills\u002Fmk-help\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: \"mk-help\"\ndescription: \"Workflow navigator: scans project state (plans, reviews, tests, git) and recommends the next pipeline step. Use for 'what next?' or 'where am I?'. NOT for complexity routing (mk:scale-routing).\"\n---\n\n# Navigation Help\n\nAnswers \"What should I do next?\" by scanning project state and mapping to the 7-phase pipeline.\n\n## How It Works\n\n`mk:help` is the FORWARD-looking navigator (what to do next). Backward-looking delivery\nanalysis stays with `the status skill` (project-manager) — this skill never reproduces it.\n\nCollect candidates from ALL scan sources below, then RANK them and emit the top 3 — do\nNOT stop at the first hit. The rank-1 candidate equals what the old \"stop at first\nactionable hit\" behavior would have returned (back-compat); ranks 2–3 are alternates with\none-line rationale. This skill is read-only: it reads state, never writes it.\n\n### 1. Paused Step-File Workflows\nCheck `.meowkit\u002Fstate\u002F*-progress.json` for any in-progress step-file workflow.\n- Found → \"Resume [skill] at step [N]. Run `\u002Fmk:[skill]` to continue.\"\n\n### 2. In-Progress Plans\nCheck `tasks\u002Fplans\u002F` for plan files without matching review verdicts.\n- Plan exists, no tests → \"Plan approved. Next: run tester agent (Phase 2 — RED)\"\n- Plan exists, tests failing → \"Tests failing. Next: run developer agent (Phase 3 — GREEN)\"\n- Plan exists, tests passing, no review → \"Tests green. Next: run reviewer agent (Phase 4 — Review)\"\n\n### 3. Pending Reviews\nCheck `tasks\u002Freviews\u002F` for verdict files with WARN or action items.\n- WARN verdict → \"Review has warnings. Acknowledge and approve for Gate 2, or fix findings.\"\n- FAIL verdict → \"Review failed. Fix required changes, then re-run reviewer.\"\n\n### 4. Uncommitted Changes\nCheck `git status` for staged\u002Funstaged changes.\n- Changes exist + review approved → \"Ready to ship. Run `the ship skill` (Phase 5)\"\n- Changes exist, no review → \"Changes detected but no review. Run reviewer first.\"\n\n### 5. Clean State\nNo plans, no reviews, no changes.\n- \"Everything clean. Options: start a new task with planner, run `the retro skill`, or ask me anything.\"\n\n## Additional Scan Sources (read after sources 1–5)\n\nALL four may be absent at rest (e.g. `.meowkit\u002Fstate\u002Fcheckpoints\u002F` does not exist until\nruntime). Absent file → skip silently; note the skip only under `--verbose`. Never error\non a missing source.\n\n| # | Source | Fields to read | Absent-case |\n|---|--------|----------------|-------------|\n| 6 | `.meowkit\u002Fstate\u002Fcheckpoints\u002Fcheckpoint-latest.json` | `state.model_tier`, `progress.plan_path`, `environment.{git_branch,working_dir_clean,uncommitted_changes}`, `budget.{estimated_spent_usd,turn_count}`, `created_at` | skip; no checkpoint context |\n| 7 | `.meowkit\u002Fstate\u002Fbudget-state.json` | `estimated_cost_usd`, `turn_count`, `warnings_emitted` (advisory only) | skip; no budget caution |\n| 8 | `.meowkit\u002Fstate\u002Fdetected-model.json` | `tier` (authoritative current-session tier) | skip; tier unknown |\n| 9 | `tasks\u002Freviews\u002F\u003Cslug>-verdict.json` | `decision`, `dimensions[].verdict`, `created_at`; `.md` is prose fallback | use git\u002Fplan scan only |\n| 10 | `docs\u002Fdevelopment-roadmap.md` (when present; Type-1 allowlisted) | current phase \u002F milestone progress | skip; tag `(CF-C5)` if relied on |\n\n**Model tier:** source the current tier from `.meowkit\u002Fstate\u002Fdetected-model.json` (written\nfresh at SessionStart). Do NOT source `model_tier` from `budget-state.json` — it has no\n`created_at`\u002Fsession marker and may carry a prior session's tier. Treat budget figures as\nadvisory unless a current-session signal corroborates them.\n\n**Staleness:** if `checkpoint-latest.json` `created_at` is older than 24h, demote its\nevidence and note the staleness in the rationale.\n\n## Ranking Heuristic (deterministic, evidence-cited — no vibes ranking)\n\nCollect candidates from all sources, then rank:\n\n1. **Blocked phase or BLOCKED verdict** → rank-1 unblock\u002Ffix action. A review verdict is\n   blocked when `decision === \"BLOCKED\"` — the verdict enum is `PASS | PASS_WITH_RISK |\n   BLOCKED`; there is NO top-level `\"FAIL\"` value. `FAIL` exists only per-dimension in\n   `dimensions[].verdict`. Cite the failing dimension(s) in the rationale.\n2. **In-progress phase** (plan phase `status: in-progress`, or GFM `- [ ]` checkboxes\n   remaining) → continue action, rationale cites checkbox % (count `- [x]` vs `- [ ]`).\n3. **Approved plan, nothing built** → cook action.\n4. **Budget caution:** if `warnings_emitted > 0` OR spent ≥ $30, fold a budget caution into\n   the rank-1 rationale (does not by itself create a rank).\n5. **Clean state** → the existing fallback table (start a task \u002F retro \u002F ask).\n\nEach candidate's rationale MUST cite the source file(s) it came from.\n\nFor skill suggestions based on task type, see `mk:agent-detector` (its `..\u002Fagent-detector\u002Freferences\u002Flifecycle-routing.md` maps task patterns to skills).\n\n## State-to-Recommendation Map\n\n> `mk:plan-creator` is the planning entrypoint, and its `red-team`, `validate` and `archive` subcommands are handled by that same skill — there is no separate dispatcher to route through.\n\n| State | Pipeline Phase | Recommendation |\n|-------|---------------|----------------|\n| No plan | Phase 0 → 1 | \"Start with `the plan skill` or describe your task\" |\n| Existing plan — stress-test | Standalone subcommand | \"`the plan skill red-team {path}` — adversarial review of existing plan\" |\n| Existing plan — interview | Standalone subcommand | \"`the plan skill validate {path}` — critical question interview on existing plan\" |\n| Completed\u002Fcancelled plans | Housekeeping | \"`the plan skill archive` — archive completed or cancelled plans\" |\n| Plan approved, no tests | Phase 2 (TDD mode only) | \"In TDD mode (`--tdd` \u002F `MEOWKIT_TDD=1`): run tester agent — write failing tests (RED phase). In default mode: skip Phase 2; run developer directly\" |\n| Tests written, failing | Phase 3 | \"Run developer agent — implement to pass tests (GREEN)\" |\n| Tests passing, no review | Phase 4 | \"Run `the review skill` — adversarial code review\" |\n| Review PASS\u002FWARN | Phase 5 | \"Run `the ship skill` — commit, PR, deploy\" |\n| Shipped | Phase 6 | \"Run documenter — update docs, then `the retro skill`\" |\n| Paused workflow | Resume | \"Resume [skill] at step [N]\" |\n| Mixed state | Clarify | \"Multiple items in progress. Which to focus on?\" |\n\n## Specialist Skills (surface when domain matches)\n\n| Situation | Skill | When to suggest |\n|-----------|-------|----------------|\n| Operations, triage, case management, escalation protocols, billing workflows | `the decision-framework skill` | User asks \"how should we handle X cases\" or is designing any case-routing system |\n| \"Is everything green?\", pre-review check, post-implementation validation | `the verify skill` | After implementation completes, before review, or when user wants a quick health check |\n| API contract design or review — interface shape, error semantics, compatibility, pagination | `the api-design-principles skill` | User is authoring or reviewing what an API promises, not how it runs |\n| Backend change end to end — handler, service, integration, webhook, job | `the backend-development skill` | User is changing backend behavior and needs contract, data, and auth owners coordinated |\n| Schema, migration, query, index, or ORM data-access boundary | `the database skill` | User is modelling, evolving, or querying data |\n| Infrastructure, containers, CI\u002FCD, deployment safety, rollback | `the devops skill` | User is changing how the system is built, configured, or delivered |\n\n## Fast Paths (surface these prominently)\n\nNot every task needs the full 7-phase pipeline. Mention these when relevant:\n\n| Situation | Fast Path | What it bypasses |\n|-----------|-----------|-----------------|\n| Simple bug fix, typo, rename, config tweak | `the fix skill` | Gate 1 (plan approval) — scope is the plan |\n| Task flagged as `one-shot` by scale-routing | Auto Gate 1 bypass | Gate 1 — zero blast radius confirmed |\n| Rapid iteration \u002F spike work | `MEOWKIT_HOOK_PROFILE=fast` | post-write scan, pre-ship, pre-task-check, TDD check |\n\n**Quick fix?** Use `the fix skill` — bypasses Gate 1 for simple changes.\n\n**Small config change?** Scale-routing may auto-bypass Gate 1 when blast radius is zero.\n\n**Hook profiles:** Set `MEOWKIT_HOOK_PROFILE=fast` for rapid iteration (skips non-critical hooks).\nSet `MEOWKIT_HOOK_PROFILE=strict` to enable ALL hooks including post-session capture.\n\n## Gotchas\n\n- Multiple in-progress plans create ambiguity — ask user which to focus on, don't guess\n- `.meowkit\u002Fstate\u002F` files from previous sessions may be stale — check timestamps, warn if >24h old\n- Git status can be noisy (untracked IDE files) — focus on files in `src\u002F`, `lib\u002F`, `app\u002F`, `tests\u002F`\n- Don't recommend skipping phases — even if the user seems impatient, show the full path\n- Fast paths are not loopholes — Gate 2 (review) is NEVER bypassed; security hooks are NEVER skipped\n- `.meowkit\u002Fstate\u002Fcheckpoints\u002F` does not exist until runtime — its absence is normal, not an error; skip silently\n- `budget-state.json` is missing at session start — treat budget figures as advisory; never source model tier from it (use `detected-model.json`)\n- Prefer the machine-readable `*-verdict.json` over the `.md` prose verdict; a verdict is blocked when `decision === \"BLOCKED\"` (never a top-level `\"FAIL\"`)\n- This is the forward-looking navigator — backward-looking delivery status stays with `the status skill`; do not duplicate it here\n\n## Output Format\n\nThe ranked next-steps are a JSON-compatible shape (documented here for downstream tooling),\nrendered as a concise human summary. This skill does NOT emit machine JSON itself — there is\nno scanner script; the shape documents what the ranking reasons about.\n\n```json\n{\n  \"next_steps\": [\n    {\n      \"rank\": 1,\n      \"action\": \"the cook skill tasks\u002Fplans\u002F260610-x\u002Fplan.md\",\n      \"priority\": \"high\",\n      \"rationale\": \"Plan approved (Gate 1), phase-02 in-progress at 3\u002F7 checkboxes; budget $4.20 of $30\",\n      \"source\": [\"tasks\u002Fplans\u002F260610-x\u002Fphase-02-*.md\", \".meowkit\u002Fstate\u002Fbudget-state.json\"]\n    }\n  ],\n  \"progress\": { \"plan\": \"260610-x\", \"phases_done\": 1, \"phases_total\": 6, \"checkbox_pct\": 43 }\n}\n```\n\nHuman rendering (same headings as before — rank-1 is \"Recommended Next Step\"):\n\n```\n## Status\n\n**Current phase:** [Phase N — Name]\n**State:** [brief description]\n\n### Recommended Next Step\n[rank-1 action] — [rationale]\n\n### Other Options\n- [rank-2 action] — [one-line rationale]\n- [rank-3 action] — [one-line rationale]\n```\n\nIf `--verbose` flag: also show full state scan results (plan files, review files, test\nstatus, git status) AND which additional sources (6–10) were present vs skipped.","# Navigation Help\n\nAnswers \"What should I do next?\" by scanning project state and mapping to the 7-phase pipeline.\n\n## How It Works\n\n`mk:help` is the FORWARD-looking navigator (what to do next). Backward-looking delivery\nanalysis stays with `the status skill` (project-manager) — this skill never reproduces it.\n\nCollect candidates from ALL scan sources below, then RANK them and emit the top 3 — do\nNOT stop at the first hit. The rank-1 candidate equals what the old \"stop at first\nactionable hit\" behavior would have returned (back-compat); ranks 2–3 are alternates with\none-line rationale. This skill is read-only: it reads state, never writes it.\n\n### 1. Paused Step-File Workflows\nCheck `.meowkit\u002Fstate\u002F*-progress.json` for any in-progress step-file workflow.\n- Found → \"Resume [skill] at step [N]. Run `\u002Fmk:[skill]` to continue.\"\n\n### 2. In-Progress Plans\nCheck `tasks\u002Fplans\u002F` for plan files without matching review verdicts.\n- Plan exists, no tests → \"Plan approved. Next: run tester agent (Phase 2 — RED)\"\n- Plan exists, tests failing → \"Tests failing. Next: run developer agent (Phase 3 — GREEN)\"\n- Plan exists, tests passing, no review → \"Tests green. Next: run reviewer agent (Phase 4 — Review)\"\n\n### 3. Pending Reviews\nCheck `tasks\u002Freviews\u002F` for verdict files with WARN or action items.\n- WARN verdict → \"Review has warnings. Acknowledge and approve for Gate 2, or fix findings.\"\n- FAIL verdict → \"Review failed. Fix required changes, then re-run reviewer.\"\n\n### 4. Uncommitted Changes\nCheck `git status` for staged\u002Funstaged changes.\n- Changes exist + review approved → \"Ready to ship. Run `the ship skill` (Phase 5)\"\n- Changes exist, no review → \"Changes detected but no review. Run reviewer first.\"\n\n### 5. Clean State\nNo plans, no reviews, no changes.\n- \"Everything clean. Options: start a new task with planner, run `the retro skill`, or ask me anything.\"\n\n## Additional Scan Sources (read after sources 1–5)\n\nALL four may be absent at rest (e.g. `.meowkit\u002Fstate\u002Fcheckpoints\u002F` does not exist until\nruntime). Absent file → skip silently; note the skip only under `--verbose`. Never error\non a missing source.\n\n| # | Source | Fields to read | Absent-case |\n|---|--------|----------------|-------------|\n| 6 | `.meowkit\u002Fstate\u002Fcheckpoints\u002Fcheckpoint-latest.json` | `state.model_tier`, `progress.plan_path`, `environment.{git_branch,working_dir_clean,uncommitted_changes}`, `budget.{estimated_spent_usd,turn_count}`, `created_at` | skip; no checkpoint context |\n| 7 | `.meowkit\u002Fstate\u002Fbudget-state.json` | `estimated_cost_usd`, `turn_count`, `warnings_emitted` (advisory only) | skip; no budget caution |\n| 8 | `.meowkit\u002Fstate\u002Fdetected-model.json` | `tier` (authoritative current-session tier) | skip; tier unknown |\n| 9 | `tasks\u002Freviews\u002F\u003Cslug>-verdict.json` | `decision`, `dimensions[].verdict`, `created_at`; `.md` is prose fallback | use git\u002Fplan scan only |\n| 10 | `docs\u002Fdevelopment-roadmap.md` (when present; Type-1 allowlisted) | current phase \u002F milestone progress | skip; tag `(CF-C5)` if relied on |\n\n**Model tier:** source the current tier from `.meowkit\u002Fstate\u002Fdetected-model.json` (written\nfresh at SessionStart). Do NOT source `model_tier` from `budget-state.json` — it has no\n`created_at`\u002Fsession marker and may carry a prior session's tier. Treat budget figures as\nadvisory unless a current-session signal corroborates them.\n\n**Staleness:** if `checkpoint-latest.json` `created_at` is older than 24h, demote its\nevidence and note the staleness in the rationale.\n\n## Ranking Heuristic (deterministic, evidence-cited — no vibes ranking)\n\nCollect candidates from all sources, then rank:\n\n1. **Blocked phase or BLOCKED verdict** → rank-1 unblock\u002Ffix action. A review verdict is\n   blocked when `decision === \"BLOCKED\"` — the verdict enum is `PASS | PASS_WITH_RISK |\n   BLOCKED`; there is NO top-level `\"FAIL\"` value. `FAIL` exists only per-dimension in\n   `dimensions[].verdict`. Cite the failing dimension(s) in the rationale.\n2. **In-progress phase** (plan phase `status: in-progress`, or GFM `- [ ]` checkboxes\n   remaining) → continue action, rationale cites checkbox % (count `- [x]` vs `- [ ]`).\n3. **Approved plan, nothing built** → cook action.\n4. **Budget caution:** if `warnings_emitted > 0` OR spent ≥ $30, fold a budget caution into\n   the rank-1 rationale (does not by itself create a rank).\n5. **Clean state** → the existing fallback table (start a task \u002F retro \u002F ask).\n\nEach candidate's rationale MUST cite the source file(s) it came from.\n\nFor skill suggestions based on task type, see `mk:agent-detector` (its `..\u002Fagent-detector\u002Freferences\u002Flifecycle-routing.md` maps task patterns to skills).\n\n## State-to-Recommendation Map\n\n> `mk:plan-creator` is the planning entrypoint, and its `red-team`, `validate` and `archive` subcommands are handled by that same skill — there is no separate dispatcher to route through.\n\n| State | Pipeline Phase | Recommendation |\n|-------|---------------|----------------|\n| No plan | Phase 0 → 1 | \"Start with `the plan skill` or describe your task\" |\n| Existing plan — stress-test | Standalone subcommand | \"`the plan skill red-team {path}` — adversarial review of existing plan\" |\n| Existing plan — interview | Standalone subcommand | \"`the plan skill validate {path}` — critical question interview on existing plan\" |\n| Completed\u002Fcancelled plans | Housekeeping | \"`the plan skill archive` — archive completed or cancelled plans\" |\n| Plan approved, no tests | Phase 2 (TDD mode only) | \"In TDD mode (`--tdd` \u002F `MEOWKIT_TDD=1`): run tester agent — write failing tests (RED phase). In default mode: skip Phase 2; run developer directly\" |\n| Tests written, failing | Phase 3 | \"Run developer agent — implement to pass tests (GREEN)\" |\n| Tests passing, no review | Phase 4 | \"Run `the review skill` — adversarial code review\" |\n| Review PASS\u002FWARN | Phase 5 | \"Run `the ship skill` — commit, PR, deploy\" |\n| Shipped | Phase 6 | \"Run documenter — update docs, then `the retro skill`\" |\n| Paused workflow | Resume | \"Resume [skill] at step [N]\" |\n| Mixed state | Clarify | \"Multiple items in progress. Which to focus on?\" |\n\n## Specialist Skills (surface when domain matches)\n\n| Situation | Skill | When to suggest |\n|-----------|-------|----------------|\n| Operations, triage, case management, escalation protocols, billing workflows | `the decision-framework skill` | User asks \"how should we handle X cases\" or is designing any case-routing system |\n| \"Is everything green?\", pre-review check, post-implementation validation | `the verify skill` | After implementation completes, before review, or when user wants a quick health check |\n| API contract design or review — interface shape, error semantics, compatibility, pagination | `the api-design-principles skill` | User is authoring or reviewing what an API promises, not how it runs |\n| Backend change end to end — handler, service, integration, webhook, job | `the backend-development skill` | User is changing backend behavior and needs contract, data, and auth owners coordinated |\n| Schema, migration, query, index, or ORM data-access boundary | `the database skill` | User is modelling, evolving, or querying data |\n| Infrastructure, containers, CI\u002FCD, deployment safety, rollback | `the devops skill` | User is changing how the system is built, configured, or delivered |\n\n## Fast Paths (surface these prominently)\n\nNot every task needs the full 7-phase pipeline. Mention these when relevant:\n\n| Situation | Fast Path | What it bypasses |\n|-----------|-----------|-----------------|\n| Simple bug fix, typo, rename, config tweak | `the fix skill` | Gate 1 (plan approval) — scope is the plan |\n| Task flagged as `one-shot` by scale-routing | Auto Gate 1 bypass | Gate 1 — zero blast radius confirmed |\n| Rapid iteration \u002F spike work | `MEOWKIT_HOOK_PROFILE=fast` | post-write scan, pre-ship, pre-task-check, TDD check |\n\n**Quick fix?** Use `the fix skill` — bypasses Gate 1 for simple changes.\n\n**Small config change?** Scale-routing may auto-bypass Gate 1 when blast radius is zero.\n\n**Hook profiles:** Set `MEOWKIT_HOOK_PROFILE=fast` for rapid iteration (skips non-critical hooks).\nSet `MEOWKIT_HOOK_PROFILE=strict` to enable ALL hooks including post-session capture.\n\n## Gotchas\n\n- Multiple in-progress plans create ambiguity — ask user which to focus on, don't guess\n- `.meowkit\u002Fstate\u002F` files from previous sessions may be stale — check timestamps, warn if >24h old\n- Git status can be noisy (untracked IDE files) — focus on files in `src\u002F`, `lib\u002F`, `app\u002F`, `tests\u002F`\n- Don't recommend skipping phases — even if the user seems impatient, show the full path\n- Fast paths are not loopholes — Gate 2 (review) is NEVER bypassed; security hooks are NEVER skipped\n- `.meowkit\u002Fstate\u002Fcheckpoints\u002F` does not exist until runtime — its absence is normal, not an error; skip silently\n- `budget-state.json` is missing at session start — treat budget figures as advisory; never source model tier from it (use `detected-model.json`)\n- Prefer the machine-readable `*-verdict.json` over the `.md` prose verdict; a verdict is blocked when `decision === \"BLOCKED\"` (never a top-level `\"FAIL\"`)\n- This is the forward-looking navigator — backward-looking delivery status stays with `the status skill`; do not duplicate it here\n\n## Output Format\n\nThe ranked next-steps are a JSON-compatible shape (documented here for downstream tooling),\nrendered as a concise human summary. This skill does NOT emit machine JSON itself — there is\nno scanner script; the shape documents what the ranking reasons about.\n\n```json\n{\n  \"next_steps\": [\n    {\n      \"rank\": 1,\n      \"action\": \"the cook skill tasks\u002Fplans\u002F260610-x\u002Fplan.md\",\n      \"priority\": \"high\",\n      \"rationale\": \"Plan approved (Gate 1), phase-02 in-progress at 3\u002F7 checkboxes; budget $4.20 of $30\",\n      \"source\": [\"tasks\u002Fplans\u002F260610-x\u002Fphase-02-*.md\", \".meowkit\u002Fstate\u002Fbudget-state.json\"]\n    }\n  ],\n  \"progress\": { \"plan\": \"260610-x\", \"phases_done\": 1, \"phases_total\": 6, \"checkbox_pct\": 43 }\n}\n```\n\nHuman rendering (same headings as before — rank-1 is \"Recommended Next Step\"):\n\n```\n## Status\n\n**Current phase:** [Phase N — Name]\n**State:** [brief description]\n\n### Recommended Next Step\n[rank-1 action] — [rationale]\n\n### Other Options\n- [rank-2 action] — [one-line rationale]\n- [rank-3 action] — [one-line rationale]\n```\n\nIf `--verbose` flag: also show full state scan results (plan files, review files, test\nstatus, git status) AND which additional sources (6–10) were present vs skipped.",{"name":5,"description":7},"main","c7ff0a9e672de2c0590b03f6459385c2d7a63c1a","kit\u002Fbundles\u002Fcodex\u002Froot\u002F.agents\u002Fskills\u002Fmk-help",3,"https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit","https:\u002F\u002Fdocs.meowkit.dev\u002F","https:\u002F\u002Fgithub.com\u002Fngocsangyem","Keep moving forward","2026-11-15 03:54:21",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add ngocsangyem\u002FMeowKit --skill mk-help",{"tool":39,"command":40},"bunx","bunx skills add ngocsangyem\u002FMeowKit --skill mk-help",{"tool":42,"command":43},"pnpm","pnpm dlx skills add ngocsangyem\u002FMeowKit --skill mk-help","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Fkit\u002Fbundles\u002Fcodex\u002Froot\u002F.agents\u002Fskills\u002Fmk-help\u002FSKILL.md",true,[],[48,55,62,69,76,83],{"skillNo":49,"name":50,"nameZh":6,"description":51,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":52,"categories":53,"keywords":54,"publishedAt":19},"01M7DVHF481B4J41T4855KGM50","mk-worktree","Manages git worktrees for parallel agent isolation: creates parallel\u002F{name}-{timestamp} branches, merges with conflict detection. NOT for user feature branches (use git worktree directly).","https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Fkit\u002Fbundles\u002Fcursor\u002Froot\u002F.cursor\u002Fskills\u002Fmk-worktree\u002FSKILL.md",[],[],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":19},"01M7DVHAWVKDKPB1EA3F1NC4JC","mk-workflow-orchestrator","Auto-invoked 7-phase workflow for complex-feature intent; fasttrack mode for pre-approved specs. NOT for explicit single tasks (mk:cook), green-field builds (mk:autobuild), or simple fixes (mk:fix).","https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Fkit\u002Fbundles\u002Fcursor\u002Froot\u002F.cursor\u002Fskills\u002Fmk-workflow-orchestrator\u002FSKILL.md",[],[],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":19},"01M7DVH6SYBHWW00TRZXCC56JW","mk-web-to-markdown","Fetch a URL and return clean markdown, for arbitrary external pages (blog, RFC, GitHub issue, vendor doc) not covered by mk:docs-finder. Static-only by default; opt-in JS rendering available.","https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Fkit\u002Fbundles\u002Fcursor\u002Froot\u002F.cursor\u002Fskills\u002Fmk-web-to-markdown\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":19},"01M7DVH3HGW47BX3PEF30JV6EJ","mk-vulnerability-scanner","Vulnerability analysis: OWASP Top 10, current threat landscape, supply chain security, attack surface mapping, risk prioritization. Use for security audits. NOT for STRIDE\u002FCSO infra audits (mk:cso).","https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Fkit\u002Fbundles\u002Fcursor\u002Froot\u002F.cursor\u002Fskills\u002Fmk-vulnerability-scanner\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M7DVGZBKMB9WDFH9MFMA99FV","mk-vue","Vue 3 authoring\u002Freview: components, composables, reactivity, Pinia, Pinia Colada, file routing, forms. Composition API + script setup. Auto-activates on .vue files. Deep review: mk:vue-best-practices.","https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Fkit\u002Fbundles\u002Fcursor\u002Froot\u002F.cursor\u002Fskills\u002Fmk-vue\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M7DVGSE12AA1M7599HB8HRCT","mk-vue-testing-best-practices","Vue 3 testing best-practices review: Vitest + Vue Test Utils for components, composables, Pinia, Router, async\u002FSuspense, forms, a11y, plus Playwright E2E strategy. Advisory only.","https:\u002F\u002Fgithub.com\u002Fngocsangyem\u002FMeowKit\u002Fblob\u002Fmain\u002Fkit\u002Fbundles\u002Fcursor\u002Froot\u002F.cursor\u002Fskills\u002Fmk-vue-testing-best-practices\u002FSKILL.md",[],[]]