theaisingularity/hermesclaw/code-review

Claude Code and agent skill by theaisingularity/hermesclaw

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Local code review — analyzes a file, function, or git diff for bugs, security issues, edge cases, and style using your project's conventions from memory

Install

npx vskill@latest install theaisingularity/hermesclaw/code-review

SKILL.md

code-review

This skill performs a thorough local code review, using your codebase conventions from MEMORY.md to give context-aware feedback.

When to invoke

  • When the user provides a file path, function name, or git diff to review
  • When the user says "review this", "check this code", or "find bugs in"
  • When triggered from VS Code via the ACP integration

Steps to execute

  1. Load codebase context from memory
  • Check MEMORY.md for recorded codebase conventions (language, framework, testing patterns, style guide)
  • Note any previously flagged patterns to watch for in this project
  1. Read the target
  • If a file path is given: read the full file
  • If a function is highlighted (via ACP): read only that function plus its immediate callers/callees
  • If reviewing a diff: read the diff plus surrounding context (±20 lines)
  1. Analyze for issues — check all of the following:
  • Correctness: logic errors, off-by-one errors, incorrect conditionals
  • Edge cases: null/undefined inputs, empty collections, type mismatches, integer overflow
  • Security: injection risks (SQL, command, path traversal), unvalidated inputs, hardcoded secrets, insecure defaults
  • Error handling: unhandled exceptions, missing error propagation, silent failures
  • Performance: O(n²) loops, missing indexes, repeated expensive operations, memory leaks
  • Style: naming conventions, function length, unnecessary complexity (check against MEMORY.md conventions)
  • Tests: missing test coverage for edge cases identified above
  1. Prioritize findings
  • P0: bugs that will cause failures in production (fix immediately)
  • P1: security or correctness issues that need fixing before merge
  • P2: code quality issues that should be addressed
  • P3: suggestions (optional improvements)
  1. Write a structured review
  • Start with a one-line verdict: "Looks good — 2 minor issues" or "Needs changes — 1 security issue"
  • List findings by priority (P0 first)
  • For each finding: file:line, description, concrete fix
  • End with a code block showing the corrected version (for P0/P1 only)
  1. Update memory if patterns are notable
  • If a recurring bug pattern is found (e.g., "always uses bare except in this codebase"), note it in MEMORY.md
  • This makes future reviews more accurate

Output format

Code Review — [filename or description]
Verdict: [one-line summary]
P0 — Must fix:
1. [file:line] [description]
Fix: [concrete fix or code block]
P1 — Should fix:
...
P2 — Consider:
...
Overall: [1-2 sentence summary]

Notes

  • This skill works best after the user has oriented Hermes to the codebase (language, framework, conventions)
  • For large files (>500 lines), ask which section to focus on first
  • The review respects project conventions from memory — it won't flag valid patterns just because they look unusual

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
70
Repository forks
10
7-day trend score
21

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/theaisingularity/hermesclaw/code-review/badge)](https://verified-skill.com/skills/theaisingularity/hermesclaw/code-review)

Something wrong with this skill or its page? Tell us.