菜单
Capture bugs/enhancements/ideas to request-logs. For quick operations use /mc command instead.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Cross-feature visibility layer for implementation plans, PRDs, and progress files. Use when: checking what's in progress, auditing stale plan statuses, remediating mismatches between frontmatter and task reality, summarizing active work, investigating orphaned/superseded PRDs. Complements artifact-tracking (which handles per-phase task updates). Routes intent to scripts/plan-status-report.py and artifact-tracking scripts.
Create rich, evidence-backed, theme-aware HTML delivery reports. One skill, four routes: `feature` (a completed feature, backward-looking — what did we deliver and how do we know), and `program` / `phase` / `readiness` (work in flight, forward-looking — where are we, what's blocked, and the next concrete action on each open item). Forward-route items each carry domain tags and a copyable agent handoff (command, existence-checked paths, grep-verified requirement IDs, blocking gates, tracker node, and a paste-ready prompt) — including for deferrals and externally blocked work. Use for: feature completion showcase, project/program status, phase or wave recap, go/no-go readiness review, stakeholder-friendly explanation of delivered value or current state. Triggers: "feature report", "completion showcase", "project status", "where are we", "program status", "status report", "phase report", "wave recap", "readiness review", "go/no-go". Do NOT use for: generic markup-to-HTML capsules (use html-capsules), live dashbo
Token-efficient tracking for AI orchestration. CLI-first for status updates (~50 tokens), agent fallback for complex ops (~1KB). Use when: updating task status, querying blockers, creating progress files, validating phases.
Unified execution engine for all development workflows. Progressive disclosure for phase execution, quick features, story completion, and scaffolding. Integrates with artifact-tracking and meatycapture-capture. Use when running /dev:execute-phase, /dev:quick-feature, /dev:implement-story, /dev:complete-user-story, or /dev:create-feature commands.
Generate and optimize PRDs, Implementation Plans, and Progress Tracking documents optimized as AI artifacts for development agents. Use when creating new feature plans, breaking down long planning docs (>800 lines), or setting up progress tracking. Supports: 1) Create PRD from feature request, 2) Create Implementation Plan from PRD with phase breakdown and subagent assignments, 3) Optimize existing plans by breaking into phase-specific files, 4) Create progress tracking with task assignments. Example: "Create a PRD for user authentication feature" or "Break down the sidebar-polish implementation plan into phase files" or "Create progress tracking for data-layer-fixes PRD".
Use this skill when authoring, modifying, or validating SkillMeat Dynamic Workflow scripts (.claude/workflows/*.js). Covers the full governed procedure: loading the master contract and per-workflow spec, choosing patterns from the pattern library, generating scripts against ExecutionGraph/ExecutionReport schemas, validating against the four-constraints checklist (no FS/shell in script, Mode D as boundary, edit-less reviewers, no Date.now/Math.random), syntax-check recipe (async-IIFE wrap for node --check), dry-run guidance, saving to .claude/workflows/, and registering in workflow-registry.md. Use whenever creating a new workflow, extending an existing one, or reviewing a workflow script for compliance.
| name | meatycapture-capture |
| description | Capture bugs/enhancements/ideas to request-logs. For quick operations use /mc command instead. |
Request-log markdown files for development tracking.
| Scenario | Method | Tokens/Effort |
|---|---|---|
| Single capture during development | mc-quick.sh | ~50 tokens |
| AI agent capturing findings | mc-quick.sh | ~50 tokens |
| Batch capture (3+ items) | Direct CLI | ~200+ tokens |
| Complex notes or custom fields | Direct CLI | ~200+ tokens |
| Appending to existing docs | Direct CLI | ~150 tokens |
| Post-commit: update docs + close item | update-bug-docs.py | ~20 tokens |
| Batch file bugs (3+) from JSON/CSV | batch-file-bugs.sh | ~30 tokens |
Scripts spec: .claude/specs/script-usage/bug-automation-scripts.md
| Type | Strategy |
|---|---|
| bug | Daily aggregation - all bugs from same day in one doc titled "Bug Log - YYYY-MM-DD" |
| enhancement/idea/task/question | One doc per topic (title = request title, often 1 item) |
Ultra-simple wrapper - reduces ~20 lines JSON to single command:
mc-quick.sh TYPE DOMAIN SUBDOMAIN "Title" "Problem" "Goal" [notes...]
# Examples:
mc-quick.sh enhancement web deployments "Add remove button" "Button not implemented" "Full removal workflow"
mc-quick.sh bug api validation "Fix timeout" "Sessions expire early" "Extend TTL to 24h"
# With environment variables:
MC_PROJECT=other-project MC_PRIORITY=high mc-quick.sh bug cli commands "Title" "Problem" "Goal"
Environment Variables: MC_PROJECT (default: skillmeat), MC_PRIORITY (default: medium), MC_STATUS (default: triage)
Full documentation: ./usage-specs/mc-quick-script.md
/mc for simple operations)| Command | Example |
|---|---|
| List | meatycapture log list PROJECT --json |
| View | meatycapture log view PATH --json |
| Search | meatycapture log search "query" PROJECT --json |
| Capture | meatycapture log create --json < input.json |
| Note Add | meatycapture log note add DOC ITEM -c "text" |
| Update | meatycapture log item update DOC ITEM --status done |
| Action | When to Load |
|---|---|
| Capture | Batch capture, validation, templates |
| View/Search | Advanced filters, output formats |
| Status Update | Change item status, add notes |
| Projects | Configure projects, defaults |
See ./references/field-options.md for valid values.