review-code
Reports defects in one file without changing it.
Skill by YauhenBichel
Chalk Labs
Need help deploying review-code?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/yauhenbichel-review-code
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: productivity
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/review-code
What's inside
- Skill name
review-code- Description
- Reports defects in one file without changing it. Use when the task is review, check, or find bugs. Do not use when the task asks for a fix.
- License
- Apache-2.0
- Instructions
- 15 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
Read the file, then report. Reviews do not edit.
Action: read
Path: {{module}}
Then, for each problem, one line naming the symbol and what goes wrong:
Action: done
Summary: compute_total returns 0 for an empty list, so callers cannot tell
an empty input from a zero total.
Quote the code. Do not repeat this instruction back as the answer. If the
file has no defect, say so.From YauhenBichel/py-harness, Apache-2.0.
More from YauhenBichel/py-harness
- 0.564score
write-cli-app
YauhenBichel
One argparse GitHub PR CLI in pkg/ with urllib.
SkillBFreshness: B★ 3Claude Code +9 - 0.561score
use-archive
YauhenBichel
Adds one zipfile or tarfile helper that packs a folder or lists what an archive holds.
SkillBFreshness: B★ 3Claude Code +9 - 0.561score
call-http
YauhenBichel
Adds one urllib.request helper that GETs or POSTs JSON.
SkillBFreshness: B★ 3Claude Code +9 - 0.561score
compare-things
YauhenBichel
Adds one helper that reports the difference between two files, two folders, or two dicts.
SkillBFreshness: B★ 3Claude Code +9 - 0.559score
review-design
YauhenBichel
Reviews project structure from the harness design block, then one-split until the scan is clean.
SkillBFreshness: B★ 3Claude Code +9 - 0.559score
ask-when-unclear
YauhenBichel
Asks the user one short question when the task could mean two different things.
SkillBFreshness: B★ 3Claude Code +9 - 0.559score
fix-smell
YauhenBichel
Renames one opaque function to readable snake_case.
SkillBFreshness: B★ 3Claude Code +9 - 0.559score
new-package
YauhenBichel
Scaffolds pkg/ + tests/ with exports-only __init__.
SkillBFreshness: B★ 3Claude Code +9 - 0.559score
readable-layout
YauhenBichel
Reports why a project is hard to read — import cycles, an ungrouped package, a god module, no tests — and names one move.
SkillBFreshness: B★ 3Claude Code +9 - 0.559score
add-feature
YauhenBichel
Adds one requested function plus a test.
SkillBFreshness: B★ 3Claude Code +9 - 0.558score
open-pr
YauhenBichel
Opens a pull request after commit and push.
SkillBFreshness: B★ 3Claude Code +9 - 0.558score
stay-scoped
YauhenBichel
Stays in one folder on a large tree.
SkillBFreshness: B★ 3Claude Code +9
Signals
- Stars
- 3
- Forks
- 5
- Open issues
- 48
- Last commit (this folder)
- Aug 29, 2026 (2 months ago)
- Last release
- Sep 9, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- Repository
- github.com/YauhenBichel/py-harness
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from YauhenBichel
- 0.580score
when-free
YauhenBichel
Which days and times am I free?
ConnectorAFreshness: ALocalRead-only↓ 30/wkClaude Code +5 - 0.565score
estimate-and-risks
YauhenBichel
Gives an honest estimate with ranges and the risks behind it.
SkillAFreshness: AClaude Code +9 - 0.564score
write-cli-app
YauhenBichel
One argparse GitHub PR CLI in pkg/ with urllib.
SkillBFreshness: B★ 3Claude Code +9 - 0.564score
incident-response
YauhenBichel
Handles a production incident and writes the postmortem.
SkillAFreshness: AClaude Code +9 - 0.564score
explain-code
YauhenBichel
Explains code clearly to another developer.
SkillAFreshness: AClaude Code +9 - 0.564score
handle-errors-and-logging
YauhenBichel
Designs error handling and logs that make failures visible and diagnosable.
SkillAFreshness: AClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get review-code running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
review-code skill. Agent Mart. https://agentmart.dev/skills/yauhenbichel-review-code (last updated 2026-10-24)