api-haus/review-plan
skills/review-plan/SKILL.md
Audit plan file for completeness before exiting plan mode — context is wiped on transition to work
testing
Updated Apr 3, 2026
$ install --global
skillsauthnpx skillsauth add api-haus/my-claude-workflow review-planInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 20, 2026, 3:22 PM1.8s1 file scanned
SKILL.md
- name:
- review-plan
- description:
- Audit plan file for completeness before exiting plan mode — context is wiped on transition to work
Read the plan file. A fresh agent with zero conversation history must be able to execute it.
Verify presence of:
- Context: why, what prompted it
- File paths: every file to touch
- Reuse targets (if applicable): existing functions/patterns to use (file:name)
- Steps: ordered, concrete, no ambiguity
- Done when: acceptance criteria + how to verify (commands, expected outcomes)
Flag gaps to the user. No fluff — only missing substance. Never remove user intent.
Related Skills
api-haus/research
data-ai
VerifiedTrustedCommunity
Extract research content from YouTube presentations, PDFs, or PPTX files into structured markdown. Dispatches each pass to a dedicated sub-agent (research-extractor / research-vision / research-refiner) so per-deck vision passes scale to hundreds of slides without bloating the parent context.
1SKILL.mdUpdated May 22, 2026
api-haus/profile
development
VerifiedTrustedCommunity
Build, run, and analyze Unity profiler data with perf-report-style call-stack attribution
1SKILL.mdUpdated May 22, 2026
api-haus/handoff
documentation
VerifiedTrustedCommunity
Write a handoff prompt for a future session. A handoff is a continuation-link — minimal context plus a kickoff line the user can copy-paste. Never a diagnosis, never an investigation script, never a prescribed deliverable.
1SKILL.mdUpdated May 10, 2026
api-haus/delegate
testing
VerifiedTrustedCommunity
Multi-agent orchestration mode. The orchestrator never reads, edits, runs, or tests directly — it scopes work, runs a re-implementation audit, presents a freeform method brief with grounded recommendations, then dispatches every step to sub-agents through shared context files at `docs/orchestrate/<topic>/`. Use when invoked via /delegate, when the user asks to orchestrate or coordinate multi-agent work, or when the task explicitly calls for delegation.
1SKILL.mdUpdated May 10, 2026