xiaohongshu
xiaohongshu
deps-health-inline
Inline orchestration workflow for dependency audit and updates. Provides step-by-step phases for dependency-auditor detection, priority-based updates with dependency-updater, and verification cycles.
Full skill instructions
You ARE the orchestrator. Execute this workflow directly without spawning a separate orchestrator agent.
Audit → Validate → Update by Priority → Verify → Repeat if needed
Max iterations: 3 Priorities: critical → high → medium → low
Setup directories:
mkdir -p .tmp/current/{plans,changes,backups}
Validate environment:
package.json existstype-check and build scripts existInitialize TodoWrite:
[
{
"content": "Dependency audit",
"status": "in_progress",
"activeForm": "Auditing dependencies"
},
{
"content": "Fix critical dependency issues",
"status": "pending",
"activeForm": "Fixing critical deps"
},
{
"content": "Fix high priority dependency issues",
"status": "pending",
"activeForm": "Fixing high deps"
},
{
"content": "Fix medium priority dependency issues",
"status": "pending",
"activeForm": "Fixing medium deps"
},
{
"content": "Fix low priority dependency issues",
"status": "pending",
"activeForm": "Fixing low deps"
},
{ "content": "Verification audit", "status": "pending", "activeForm": "Verifying updates" }
]
Invoke dependency-auditor via Task tool:
subagent_type: "dependency-auditor"
description: "Audit all dependencies"
prompt: |
Audit the entire codebase for dependency issues:
- Security vulnerabilities (npm audit / pnpm audit)
- Outdated packages (major/minor/patch)
- Unused dependencies (via Knip)
- Deprecated packages
- License compliance issues
- Categorize by priority (critical/high/medium/low)
Generate: dependency-scan-report.md
Return summary with issue counts per priority.
After dependency-auditor returns:
dependency-scan-report.mdRun inline validation:
pnpm type-check
pnpm build
For each priority (critical → high → medium → low):
Check if issues exist for this priority
Update TodoWrite: mark current priority in_progress
Invoke dependency-updater via Task tool:
subagent_type: "dependency-updater"
description: "Update {priority} dependencies"
prompt: |
Read dependency-scan-report.md and fix all {priority} priority issues.
For each issue:
1. Backup package.json and lockfile
2. Update ONE dependency at a time
3. Run type-check and build after each update
4. If fails, rollback and skip
5. Log change to .tmp/current/changes/deps-changes.json
Generate/update: dependency-updates-implemented.md
Return: count of updated deps, count of failed updates.
Quality Gate (inline):
pnpm type-check
pnpm build
Update TodoWrite: mark priority complete
Repeat for next priority
After all priorities updated:
Update TodoWrite: mark verification in_progress
Invoke dependency-auditor (verification mode):
subagent_type: "dependency-auditor"
description: "Verification audit"
prompt: |
Re-audit dependencies after updates.
Compare with previous dependency-scan-report.md.
Report:
- Issues fixed (count)
- Issues remaining (count)
- New issues introduced (count)
Decision:
Generate summary for user:
## Dependency Health Check Complete
**Iterations**: {count}/3
**Status**: {SUCCESS/PARTIAL}
### Results
- Found: {total} dependency issues
- Fixed: {fixed} ({percentage}%)
- Remaining: {remaining}
### By Priority
- Critical: {fixed}/{total}
- High: {fixed}/{total}
- Medium: {fixed}/{total}
- Low: {fixed}/{total}
### Validation
- Type Check: {status}
- Build: {status}
### Artifacts
- Audit: `dependency-scan-report.md`
- Updates: `dependency-updates-implemented.md`
If quality gate fails:
Rollback available: .tmp/current/changes/deps-changes.json
To rollback:
1. Read changes log
2. Restore package.json and lockfile from .tmp/current/backups/
3. Run pnpm install
4. Re-run workflow
If worker fails:
| Old (Orchestrator Agent) | New (Inline Skill) |
|---|---|
| 9+ orchestrator calls | 0 orchestrator calls |
| ~1400 lines (cmd + agent) | ~150 lines |
| Context reload each call | Single session context |
| Plan files for each phase | Direct execution |
| ~10,000+ tokens overhead | ~500 tokens |
See references/worker-prompts.md for detailed prompts.
xiaohongshu
technical spec
product ux expert
database patterns
Conduct multi-agent task orchestration and workflow coordination.
Initialize project with Conductor artifacts (product definition,
Expert in web animations, transitions, and motion design using Framer Motion and CSS
Creates Mermaid and ASCII diagrams for flowcharts, architecture, ERDs, state machines, mindmaps, and more. Use when user mentions diagram, flowchart, mermaid, ASCII diagram, text diagram, terminal diagram, visualize, C4, mindmap, architecture diagram, sequence diagram, ERD, or needs visual docume...
PostgreSQL bindings for H3 hexagonal grid system. Use when working with H3 cells in Postgres, including spatial indexing, geometry/geography integration, and raster analysis.
Context-Driven Development skill for projects using Conductor. Use this skill when you detect a `conductor/` directory in the project, when working on tasks defined in a `plan.md` file, or when the user asks about tracks, specs, or plans. Automatically applies TDD workflow, tracks task completion...
Display project status, active tracks, and next actions
Official Stakpak application containerization standard operating procedure, a step-by-step guidline to properly dockerize applications. This is a rule book curated by the Stakpak Team.
Generate, edit, and beat-sync AI video with leading models in one workspace.
The world's fastest calendar for remote work
Transform Your Design with AI Designer by ImgCreator.ai
Revolutionizing Video Production with AI-Powered Creativity
Extend an image past the frame and let AI fill the new aspect ratio.
Discover your celebrity doppelgänger with StarByFace!
ChainClarity explains 700+ crypto whitepapers in plain English, with layered summaries, comparisons, research tools, alerts, and a $4.99 Pro plan.
Opus.ai: Revolutionize Your Web Experience