From quiver
Audits review reports for noise, false positives, overkill suggestions, and findings that exist to appear thorough. Invoked via /report-check <path>.
How this skill is triggered — by the user, by Claude, or both
Slash command
/quiver:report-checkWhen to use
user wants to audit a review report for noise or false positives -- '/report-check', 'check this report', 'is this review good', 'verify the review findings'
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
```
!`git rev-parse --is-inside-work-tree 2>/dev/null || echo "NO_GIT"`
!`git branch --show-current 2>/dev/null || echo "NO_GIT"`
Analyze a review report for quality issues -- noise, false positives, overkill suggestions, and findings that exist to appear thorough rather than to help the developer.
Announce: "Using the report-check skill to audit report quality."
If $ARGUMENTS is empty, print:
Usage:
/report-check <path-to-review-report.md>Analyzes a review report for quality issues -- noise, false positives, overkill suggestions.
Stop here.
If $ARGUMENTS contains a file path:
Report file not found:
{path}Stop here.
## Review Context section if present (look for a Branch: line).If git is available AND a branch name was extracted from the report:
Determine the base branch:
!`git rev-parse --verify main 2>/dev/null || echo "NO_MAIN"`
Use main if it exists, otherwise master.
Get the diff:
!`git diff {base}...{branch} 2>/dev/null || echo "NO_DIFF"`
If the diff is non-empty, it will be passed to the agent for cross-referencing.
Print status:
Analyzing report with diff cross-reference...Analyzing report (no diff available for cross-reference)...If git is unavailable or no branch info exists, proceed without diff. The agent works report-only -- Phase 2 accuracy checks will be limited.
Spawn the quiver:report-checker agent with a self-contained prompt containing:
The full report content, clearly delimited:
<report>
{full report markdown}
</report>
The diff (if available), clearly delimited:
<diff>
{full diff output}
</diff>
If no diff is available, include:
<diff>
No diff available for cross-referencing.
</diff>
Instruction: "Audit this review report for quality. Apply all three phases (substance verification, accuracy check, proportionality audit). Return structured findings using your output format."
If agent returns zero issues:
Report passed quality audit -- no issues found.
If agent returns issues, display the structured findings to the user.
Use AskUserQuestion:
Quality audit found {N} issues in the report. What would you like to do?
Buttons:
Apply fixes to the reportShow details onlySkip -- keep as-isHandle each option:
Apply fixes:
## Review ContextShow details:
AskUserQuestion:
Apply the suggested fixes? Buttons:
Apply fixes/Skip -- keep as-is
Skip: Stop. Report unchanged.
{placeholder} text remains in the report.Report updated: {N} findings removed, {M} downgraded, {K} rewritten.
Trigger: /report-check <path> (and /quiver:report-check should also work)
Setup:
.claude/reports/review-*.md).Expected behavior:
Verification checklist:
/report-check.{placeholder} text remains after applying fixes.Known gotchas:
skills/review/SKILL.md Step 3. If the report format changes, update the parsing in Step 4.npx claudepluginhub yagizdo/quiver --plugin quiverProvides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.