菜单
This skill should be used when the user asks to "sync features", "check for new Claude features", "update craft for latest Claude", "what's new in Claude Code", or wants to ensure craft is up-to-date with Claude Code/Desktop capabilities. Chains command-audit and unified release-watch into a prioritized action plan.
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。
This skill should be used when the user asks to "pre-flight check", "validate before commit", "validate before PR", "validate before deploy", "is this ready to ship", "check readiness", "run pre-flight", "validate project state", or wants context-aware validation across commit/PR/release/deploy boundaries. Orchestrates universal validators (lint, tests, types, version sync, stale refs, docs, hook conflicts) and supports generating new custom validators.
This skill should be used when a command's --refine flag is set, or the user asks to "refine my prompt", "optimize this prompt", "make this request sharper" — rewrites a vague natural-language request into a specific, well-structured prompt using project context, shows before/after, and confirms before the caller proceeds. Replaces the deprecated /craft:refine command.
This skill should be used when the user asks to "release", "create a release", "ship it", "publish a new version", "bump version and release", "cut a release", or mentions releasing to GitHub/npm/PyPI. Orchestrates the full release pipeline from pre-flight checks through GitHub release creation.
ADHD-friendly session and task workflow for craft users — captures context at session end, restores it at session start, picks the next task, breaks through blockers, holds focus on one task, reviews a craft spec, or refines a vague craft prompt. Use when wrapping up or resuming a coding session, when deciding what to work on next (also "what's next", "pick a task for me", "give me something to do"), when stuck or in decision paralysis, when focusing on a single craft task, or when reviewing/refining a craft spec or prompt. The full intent-to-operation map is in the "When to Use" table below.
This skill should be used when the user asks to "init a repo", "set up git", "manage branches", "switch branch", "create a worktree", "list worktrees", "clean merged branches", "sync with remote", "git activity", "git recap", "protect main", "apply branch protection", "bypass protection", "undo a commit", "fix a git mistake", or mentions git lifecycle, worktrees, branch protection, GitHub-side baseline protection, safety rails, or learning git workflows. Covers craft's full git lifecycle — repo init, branch and worktree management, remote sync, status/recap, local and GitHub-side branch protection, and the learning/safety reference docs.
This skill should be used when the user asks "what's my friction", "session insights", "friction report", "what patterns am I hitting", "analyze my sessions", "generate insights report", "aggregate facets", or "show CLAUDE.md suggestions". Aggregates session facet history into a friction/goals report. Formerly bundled with the brainstorm skill (ideation); split out because the two operations share no input or output. Directory name kept as brainstorm-insights for path stability — tests and references/insights.md reference it.
| name | sync-features |
| description | This skill should be used when the user asks to "sync features", "check for new Claude features", "update craft for latest Claude", "what's new in Claude Code", or wants to ensure craft is up-to-date with Claude Code/Desktop capabilities. Chains command-audit and unified release-watch into a prioritized action plan. |
Interactive wizard that audits craft's current state, checks for upstream Claude changes, and presents a prioritized list of actions to keep the plugin current.
gh CLI installed and authenticated (for release-watch)Execute these steps in order. Show progress between steps.
Run the command audit to assess current craft health:
bash scripts/command-audit.sh --format json
Parse the JSON output and extract:
health_score — overall healtherrors — list of frontmatter errorswarnings — list of warnings (deprecated patterns, hardcoded models, orphaned scripts)Display summary:
┌───────────────────────────────────────────────────────────────┐
│ STEP 1/3: COMMAND AUDIT │
├───────────────────────────────────────────────────────────────┤
│ Health Score: 85/100 │
│ Errors: 3 | Warnings: 5 | Files: 106 │
│ │
│ Top issues: │
│ - 3 files with invalid frontmatter fields │
│ - 2 files with hardcoded model names │
│ - 3 orphaned scripts │
└───────────────────────────────────────────────────────────────┘
Fetch Code + Desktop releases using the unified release-watch tool:
python3 scripts/release-watch.py --format json --count 3
This single command now covers both Code and Desktop. Parse the JSON v2 output:
findings — Code findings categorized as NEW / DEPRECATED / BREAKING / FIXEDdesktop.findings — Desktop findings (same categories)craft_state — hardcoded models, agent features, hook eventsaction_items — items needing attentionDisplay summary:
┌───────────────────────────────────────────────────────────────┐
│ STEP 2/2: UNIFIED RELEASE WATCH │
├───────────────────────────────────────────────────────────────┤
│ Code: 3 releases (latest: v2.1.59) │
│ Desktop: 20 entries (latest: February 25, 2026) │
│ │
│ Code: NEW 4 | BREAKING 0 | DEPRECATED 0 | FIXED 2 │
│ Desktop: NEW 12 | BREAKING 1 | DEPRECATED 0 | FIXED 1 │
│ │
│ Highlights: │
│ - Cowork plugins and admin controls │
│ - 11 hardcoded model references in craft │
└───────────────────────────────────────────────────────────────┘
Combine all findings into a single prioritized action list. Assign priorities:
| Priority | Criteria |
|---|---|
| P0 (Critical) | BREAKING changes, errors in audit |
| P1 (High) | NEW features craft should adopt, deprecated patterns to remove |
| P2 (Medium) | Warnings from audit, FIXED items to verify |
| P3 (Low) | Desktop integration opportunities, suggestions |
Use AskUserQuestion with multiSelect to let the user choose which items to act on:
{
"questions": [{
"question": "Select items to act on now (you can select multiple):",
"header": "Actions",
"multiSelect": true,
"options": [
{"label": "[P0] Fix breaking change", "description": "v2.1.50 removed X — craft still uses it in Y"},
{"label": "[P1] Adopt new hook events", "description": "WorktreeCreate/WorktreeRemove now available"},
{"label": "[P1] Clean hardcoded models", "description": "9 references to specific model names"},
{"label": "[P2] Fix invalid frontmatter", "description": "3 files with non-schema fields"}
]
}]
}
Note: AskUserQuestion supports maximum 4 options. If there are more items, group by priority and present the top 4 most impactful. Mention remaining items in the description of the last option or in a follow-up message.
For each selected item, take appropriate action:
bash scripts/command-audit.sh --fixAfter each action, report what was done and verify the fix.
Display final summary:
╔═════════════════════════════════════════════════════════════╗
║ SYNC FEATURES — COMPLETE ║
╠═════════════════════════════════════════════════════════════╣
║ ║
║ Actions taken: 3 of 5 selected ║
║ Health score: 85 -> 92 (+7) ║
║ ║
║ Completed: ║
║ - Fixed 3 invalid frontmatter fields ║
║ - Removed 2 hardcoded model references ║
║ - Updated hook event registration ║
║ ║
║ Deferred: ║
║ - Desktop integration (needs separate feature branch) ║
║ - Breaking change migration (needs testing) ║
║ ║
╚═════════════════════════════════════════════════════════════╝
gh is not available: Skip release-watch, note in output, continue with audit only/craft:code:command-audit — Frontmatter validation (Step 1)/craft:code:release-watch — Unified Code + Desktop tracking (Step 2)/craft:check — General pre-flight checks