Self Reviewer
Shen-Hua self-review workflow before finishing a task. Use before final responses, commits, PRs, handoffs, or readiness claims to inspect requirements coverage, diffs, risks, tests, missed edge cases, destructive changes, and unresolved work.
Install
$ agentstack add skill-fengsihao23-eng-shen-hua-self-reviewer ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-fengsihao23-eng-shen-hua-self-reviewer) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Self Reviewer
Self Reviewer is the final quality gate before saying the task is done.
Trigger Conditions
Use this skill when:
- A work round is ending.
- The agent is about to claim completion or readiness.
- Code/config/docs changed.
- A verification loop passed, failed, or was skipped.
Do Not Trigger
Do not use this skill for:
- Pure Q&A with no project impact.
- Early planning before implementation begins, unless the user asks for plan review.
Review Workflow
- Re-read the user's latest request and project rules.
- Read
.agent/PLAN.md,.agent/TASKS.md,.agent/LOG.md, and.agent/HANDOFF.md. - Inspect the current diff or changed-file list when version control is available.
- Check:
- requirement coverage
- accidental unrelated changes
- edge cases and error handling
- public API or contract changes
- security/privacy concerns
- missing tests or weak verification
- documentation or handoff gaps
- If a serious issue is found and is in scope, fix it and rerun
$verification-loop. - If not fixing, record the risk clearly.
Required .agent/ Updates
Always update:
.agent/REVIEW_CHECKLIST.md: checklist result and findings..agent/LOG.md: self-review summary..agent/TASKS.md: any reopened or completed items..agent/HANDOFF.md: residual risks and next action.
Update when relevant:
.agent/DECISIONS.md: accepted risk or deliberate non-fix.
Other Skills
- Use
$verification-loopif no current verification exists after changes, or if the review leads to fixes. - Use
$handoff-writerafter self-review.
Subagents
A reviewer subagent may be useful for large diffs when permitted, but the main agent remains responsible for final judgment.
Verification Commands
Self-review itself is mostly inspection. Run commands only when review reveals missing or stale verification.
Output Format
SELF REVIEW
Requirements covered:
Changed files reviewed:
Verification freshness:
Findings:
Residual risks:
Ready status:Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: fengsihao23-eng
- Source: fengsihao23-eng/shen-hua
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.