tslateman/debrief
skills/debrief/SKILL.md
Review what agents accomplished, surface loose ends across sessions
data-ai
Updated Apr 25, 2026
$ install --global
skillsauthnpx skillsauth add tslateman/duet debriefInstall 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 25, 2026, 6:25 PM15.0s1 file scanned
SKILL.md
- name:
- debrief
- description:
- Review what agents accomplished, surface loose ends across sessions
Agent Debrief
Overview
Consolidate work done by agents or across sessions. Review what landed and what's still open.
1. Recent Commits
Check what actually shipped:
git log --oneline -15 --all --decorate
Note any commits from agents or parallel work streams.
2. Work In Progress
Check for uncommitted changes or stashed work:
git status --short
git stash list
3. Synthesis
Produce a brief debrief:
What Landed
- Summarize completed work (be specific—name files, features, fixes)
Loose Ends
- Uncommitted work that needs attention
- Agent work that wasn't fully integrated
- TODOs or FIXMEs introduced
Connections
- Note any overlap or conflicts between parallel work streams
- Flag if multiple changes touched the same files
Next Actions
- Concrete steps to consolidate or continue the work
Keep it actionable. Skip anything that's already clean and integrated.
Related Skills
tslateman/vibe-check
development
VerifiedTrustedCommunity
Judgment linter for vibe-coded output — reads the energy of the code, not just correctness. Use when the user says "vibe check", "check this vibe code", "does this hold up", "sanity check this AI code", or after a fast generation session before committing.
SKILL.mdUpdated Apr 25, 2026
tslateman/vamp
tools
VerifiedTrustedCommunity
Survey the project and choose what to play next
SKILL.mdUpdated Apr 25, 2026
tslateman/testing
development
VerifiedTrustedCommunity
Design test strategy using Beck's Test Desiderata — which properties matter, which tradeoffs to make. Use when the user asks "how should I test this", "what tests do I need", "review my test strategy", "is this well-tested", or when planning tests for a new feature or refactor.
SKILL.mdUpdated Apr 25, 2026
tslateman/sweep
testing
VerifiedTrustedCommunity
Post-op check for artifacts, damage, and stale references after agent work
SKILL.mdUpdated Apr 25, 2026