Chalk Labs
Need help deploying review?
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/phobologic-review
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: agent-building
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
What's inside
- Skill name
review- Description
- Quick code review using an adversarial sub-agent. Surfaces Critical and High issues first. Creates tk tickets for Critical/High/Medium findings if tk is available.
- License
- MIT
- Instructions
- 69 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
You are orchestrating a fast pre-merge code review. A dedicated adversarial sub-agent does the actual reviewing so it brings a fresh, unbiased perspective.
## Step 1: Collect context
Run in a single Bash call:
```bash
mkdir -p .code-review
rm -f .code-review/changed-files.txt .code-review/claude-md-context.txt
git status --porcelain | awk '{print $NF}' > .code-review/changed-files.txt
TK_AVAILABLE=false
command -v tk >/dev/null 2>&1 && TK_AVAILABLE=true
SESSION_TAG="review-$(date +%Y%m%d-%H%M)"
echo "TK_AVAILABLE=$TK_AVAILABLE"
echo "SESSION_TAG=$SESSION_TAG"
echo "--- Files to review ---"
cat .code-review/changed-files.txt
```
## Step 2: Collect CLAUDE.md context
Run this to give the critic project convention awareness:
```bash
[ -f CLAUDE.md ] && { echo "=== CLAUDE.md (root) ==="; cat CLAUDE.md; echo; } > .code-review/claude-md-context.txt
while IFS= read -r file; do
dir=$(dirname "$file")
if [ "$dir" != "." ] && [ -f "$dir/CLAUDE.md" ]; then
echo "=== CLAUDE.md ($dir) ===" >> .code-review/claude-md-context.txt
cat "$dir/CLAUDE.md" >> .code-review/claude-md-context.txt
echo >> .code-review/claude-md-context.txt
fi
done < .code-review/changed-files.txt
[ ! -s .code-review/claude-md-context.txt ] && rm -f .code-review/claude-md-context.txt
```
## Step 3: Guard
If `.code-review/changed-files.txt` is empty, tell the user there are no uncommitted changes to review and stop.
## Step 4: Launch the code-critic sub-agent
Use the Task tool to invoke the `code-critic` sub-agent. Pass `REVIEW_CMD`, and tk parameters when available.
### tk mode (TK_AVAILABLE=true)
```
Task: Adversarial code review
Prompt: TK_MODE=true SESSION_TAG=<session_tag> REVIEW_CMD=git diff HEAD -- Review ONLY the files listed in .code-review/changed-files.txt and nothing else
SubagentType: code-critic
```
### non-tk mode (TK_AVAILABLE=false)
```
Task: Adversarial code review
Prompt: REVIEW_CMD=git diff HEAD -- Review ONLY the files listed in .code-review/changed-files.txt and nothing else
SubagentType: code-critic
```
## Step 5: Present results
The critic's output is the review. Display it.
In tk mode, additionally tell the user:
- The session tag used: `<session_tag>`
- How to find all tickets from this review: `tk query '.tags | contains(["<session_tag>"])'`From phobologic/claude_code, MIT.
More from phobologic/claude_code
- 0.469score
setup-python-project
phobologic
Scaffold a new Python project with uv, ruff, pytest, and GitHub Actions CI.
SkillDFreshness: D★ 7Claude Code +9 - 0.468score
implement-ticket
phobologic
Implement one or more tk tickets.
SkillDFreshness: D★ 7Claude Code +9 - 0.466score
multi-review
phobologic
Perform a comprehensive code review using multiple specialized sub-agents in parallel.
SkillDFreshness: D★ 7Claude Code +9 - 0.466score
spec
phobologic
Turns a rough idea into a structured implementation plan with tk epics and tickets.
SkillDFreshness: D★ 7Claude Code +9 - 0.463score
migrate-beads
phobologic
Migrate this project's issue tracking from beads (bd) to tickets (tk).
SkillDFreshness: D★ 7Claude Code +9 - 0.458score
use-railway
phobologic
Set up Railway CLI rules for this project by creating a symlink into .claude/rules/.
SkillDFreshness: D★ 7Claude Code +9 - 0.458score
use-sqlalchemy
phobologic
Set up SQLAlchemy async + Alembic rules for this project by creating a symlink into .claude/rules/.
SkillDFreshness: D★ 7Claude Code +9
Signals
- Stars
- 7
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Mar 30, 2026 (7 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/phobologic/claude_code
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from phobologic
- 0.469score
setup-python-project
phobologic
Scaffold a new Python project with uv, ruff, pytest, and GitHub Actions CI.
SkillDFreshness: D★ 7Claude Code +9 - 0.468score
implement-ticket
phobologic
Implement one or more tk tickets.
SkillDFreshness: D★ 7Claude Code +9 - 0.466score
multi-review
phobologic
Perform a comprehensive code review using multiple specialized sub-agents in parallel.
SkillDFreshness: D★ 7Claude Code +9 - 0.466score
spec
phobologic
Turns a rough idea into a structured implementation plan with tk epics and tickets.
SkillDFreshness: D★ 7Claude Code +9 - 0.463score
migrate-beads
phobologic
Migrate this project's issue tracking from beads (bd) to tickets (tk).
SkillDFreshness: D★ 7Claude Code +9 - 0.458score
use-railway
phobologic
Set up Railway CLI rules for this project by creating a symlink into .claude/rules/.
SkillDFreshness: D★ 7Claude 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 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 skill. Agent Mart. https://agentmart.dev/skills/phobologic-review (last updated 2026-10-24)