本文へ移動
cccskills
無料GitHub で公開

verify-findings

Verify code-review or security-review findings for false positives using deep codebase tracing, framework-aware analysis, and web research. Produces a .verified.md report alongside the original. Use when a review report has been generated and needs independent verification, or when user runs /verify-findings, mentions "verify review", "check false positives", or "validate findings".

インストール方法を見る

含まれるファイル(4)

  • SKILL.md4.9 KB
  • EXAMPLES.md11.5 KB
  • TROUBLESHOOTING.md2.2 KB
  • WORKFLOW.md9.3 KB

SKILL.md(原文)

インストールする前に、エージェントに与えられる指示の中身を確認できます。

Verify Review Findings

Independent false-positive verification. Assume every finding is false until proven by evidence.

Parse Arguments

  • $ARGUMENTS (required): Path to the review report file to verify

If no argument is provided, ask the user for the report path.

Step 1 — Read and Parse Report

  1. Read the report file at the provided path
  2. Detect review type from the header:
    • "Pragmatic Code Review Report" → code review
    • "Security Review Report" → security review
  3. Extract each finding into a structured list:
    • Triage level (Blocker, Improvement, Question)
    • File path and line number
    • Description and confidence/severity scores
    • For security: CWE, category, exploit scenario
  4. Skip Praise and Nit findings — only verify Blocker, Improvement, and Question

Step 2 — Verify Each Finding

For each extracted finding, perform independent verification. See WORKFLOW.md for detailed procedures.

Code Review Findings

  1. Read the flagged code at the specified line with ~50 lines of surrounding context
  2. Grep the codebase for the same pattern to check if it's an established convention
  3. Verify the cited principle — does SOLID/DRY/KISS/YAGNI actually apply here?
  4. Check framework handling — does the framework or library address this concern automatically?
  5. Assess concrete impact — is the problem demonstrable or theoretical?

Security Review Findings

  1. Read the flagged code and trace data flow from source to sink
  2. Grep for sanitizers/validators in the code path between source and sink
  3. Detect framework protections — React auto-escaping, Spring Security, Django ORM parameterization, etc.
  4. WebSearch the CWE/CVE for known false positive patterns and framework-specific mitigations
  5. Verify exploit feasibility — is the exploit scenario actually possible in this application context?
  6. Check code context — is this test-only code, behind authentication, or behind a feature flag?

Step 3 — Render Verdict

For each finding, assign one of:

VerdictCriteriaAction
CONFIRMEDEvidence supports the findingKeep in report, add verification note
DISMISSEDFinding is a false positiveMove to Dismissed section with explanation
DOWNGRADEDValid but lower severity/confidenceAdjust scores, add explanation

Decision rules: See WORKFLOW.md for the complete verdict decision matrix.

Default to CONFIRMED if uncertain after thorough investigation (conservative approach).

Step 4 — Generate Verified Report

  1. Create the verified report at: {original-path-without-extension}.verified.md
    • Example: reviews/code/2026-03-01_14-30-00_code-review.md → reviews/code/2026-03-01_14-30-00_code-review.verified.md
  2. Preserve original structure — keep the same header, PR assessment, and format
  3. Add verification header:
**Verified by**: Claude Code (false-positive-verifier)
**Verification Date**: {ISO 8601 date}

## Verification Summary
| Metric | Count |
|--------|-------|
| **Findings Reviewed** | {N} |
| **Confirmed** | {N} |
| **Downgraded** | {N} |
| **Dismissed** | {N} |
| **Signal Ratio** | {confirmed / total reviewed}% |
  1. Annotate confirmed findings with verification notes:
> **Verification**: CONFIRMED — {evidence summary}
  1. Append Dismissed Findings section:
## Dismissed Findings

### Dismissed 1: `{file}:{line}` — {Original description}
- **Original Triage**: {Blocker/Improvement/Question}
- **Original Confidence**: {score}
- **Reason**: {Why this is a false positive}
- **Evidence**: {What was checked — grep results, framework docs, web research}
  1. Update Verdict with revised counts and recommendation

See WORKFLOW.md for the complete report template. See EXAMPLES.md for sample verified reports.

Output Instructions

  1. Save the verified report alongside the original
  2. Display the full verified report to the user
  3. Confirm: "Verified report saved to: {path}"

Resources

  • WORKFLOW.md — Detailed verification procedures, verdict decision matrix, web research protocol, report template
  • EXAMPLES.md — Sample verified reports for code and security reviews
  • TROUBLESHOOTING.md — Common issues with input parsing, verification quality, and output

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

同じリポジトリのスキル

概要と使いどころ

adr

無料

Create, review, and manage Architecture Decision Records (ADRs) with auto-numbering, template detection, quality review, and index maintenance. Use when user mentions "ADR", "architecture decision", "document this decision", "create ADR", "review ADR", editing ADR files (docs/adr/, doc/adr/, .adr/), or discussing architectural choices and tradeoffs.

日本語の概要は準備中です。原文の説明を表示しています。

joaquimscosta/arkhe-claude-plugins212026年8月14日 更新

architect

無料

Analyze system architecture, module structure, API contracts, data models, and code patterns. Use when designing systems, reviewing module boundaries, evaluating API designs, analyzing data models, checking pattern conformance, tracing decisions, or reviewing frontend architecture. Triggers: "architecture", "module design", "API design", "data model", "boundaries", "patterns", "decisions", "frontend architecture".

日本語の概要は準備中です。原文の説明を表示しています。

joaquimscosta/arkhe-claude-plugins212026年8月14日 更新

Converts natural-language descriptions or UI spec files into optimized Google Stitch prompts. Use when creating, refining, or validating design directives for Google Stitch. Use when user says "create a Stitch prompt", "optimize this for Stitch", "convert this spec to a Stitch prompt", "write a UI prompt", or mentions Google Stitch prompt authoring. Follows Stitch best practices with short, directive prompts focused on screens, structure, and visual hierarchy.

日本語の概要は準備中です。原文の説明を表示しています。

joaquimscosta/arkhe-claude-plugins212026年8月14日 更新

Zero-dependency live-preview server providing an agent↔browser bidirectional companion. Watches a content directory, wraps HTML fragments in a frame template, broadcasts live-reload over WebSocket, and captures browser-side click events to a JSONL file. Use when an agent needs to show HTML to the user in a browser and react to clicks — mockups, design exploration, gallery browsing, multi-select choices, prototype iteration. Triggered by "live preview", "browser companion", "preview server", "browser mockup", "show in browser", "arkhe-preview", or any skill that wants to write HTML fragments and have the user see them reload in real time.

日本語の概要は準備中です。原文の説明を表示しています。

joaquimscosta/arkhe-claude-plugins212026年8月14日 更新

Deletes merged git branches (local and remote) and flags stale unmerged branches for manual review. Use when user mentions "cleanup branches", "delete merged branches", "prune old branches", "remove stale branches", "branch cleanup", or runs /cleanup-branches command.

日本語の概要は準備中です。原文の説明を表示しています。

joaquimscosta/arkhe-claude-plugins212026年8月14日 更新

Interactive Claude Code environment setup wizard. Detects existing configuration, guides through best-practice setup for Global CLAUDE.md, project scaffolding, MCP servers, hooks, custom agents, keybindings, and settings. Use when user runs /devtools:code-env-setup, mentions "setup claude code", "configure claude", "claude code setup", "environment setup", or "initialize claude code".

日本語の概要は準備中です。原文の説明を表示しています。

joaquimscosta/arkhe-claude-plugins212026年8月14日 更新

joaquimscosta のスキルをすべて見る

このスキルの問題を報告する