avifenesh/self-review
skills/self-review/SKILL.md
Use when agent should review its own output before responding, or when asked to double-check work. Keywords: self-review, double-check, verify, validate, review output
$ install --global
skillsauthnpx skillsauth add avifenesh/cairn self-reviewInstall 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 12, 2026, 3:10 AM13.1s1 file scanned
SKILL.md
- name:
- self-review
- description:
- Use when agent should review its own output before responding, or when asked to double-check work. Keywords: self-review, double-check, verify, validate, review output
- inclusion:
- always
- allowed-tools:
- cairn.journalSearch,cairn.searchMemory
Self-Review
Review your own output before presenting it to the user:
- Check facts — Search memories with
cairn.searchMemoryto verify claims against stored knowledge. - Check history — Search journal with
cairn.journalSearchfor similar past tasks and their outcomes. - Validate — Verify:
- Are claims accurate based on available evidence?
- Is the response complete and addresses the user's question?
- Are there any contradictions with known facts or past decisions?
- Correct — Fix any issues found before responding.
When to Self-Review
- Before presenting important decisions or recommendations
- When synthesizing information from multiple sources
- When the response involves technical details that could be wrong
- After completing multi-step tasks
Related Skills
avifenesh/pr-stall-detector
data-ai
VerifiedTrustedCommunity
Detect agent-cairn PRs that have stalled (no activity >=90 min) and classify the failure mode to route to appropriate recovery agent.
4SKILL.mdUpdated Apr 12, 2026
avifenesh/installer
tools
VerifiedTrustedCommunity
Post-install skill adaptation: read a newly installed SKILL.md, fix environment-specific references (paths, accounts, tool names), assign the skill to relevant agent types, and propose an AGENTS.md update. Triggered automatically after cairn.installSkill completes.
4SKILL.mdUpdated Apr 12, 2026
avifenesh/growth-brief
data-ai
VerifiedTrustedCommunity
Monthly self-improvement brief for Cairn. Queries error_patterns, action_exemplars, experiment_windows, and session_journal to synthesize what Cairn learned, where it failed, and 3 concrete proposals for Avi to approve. Run on the 1st of each month. Keywords: growth brief, monthly review, self-improvement, what did cairn learn, how is cairn doing, monthly report
4SKILL.mdUpdated Apr 12, 2026
avifenesh/decision-support
testing
VerifiedTrustedCommunity
Decision support with memory-backed context. Retrieves past decisions, journal history, and relevant facts before answering questions that involve a choice or tradeoff. Keywords: should I, which is better, tradeoff, compare, decide, choose, option, alternative, pros and cons, recommend
4SKILL.mdUpdated Apr 12, 2026