Skip to content
Agentmart
Submit a tool

review-local-changes

Review the local changes cold and report the findings to the user.

Skill by falcondev-oss

IndexedMIT★ 2
Write a review

Chalk Labs

Need help deploying review-local-changes?

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.

Book a call

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/falcondev-oss-review-local-changes

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.

We use your email only for this newsletter. Privacy

About

Review the local changes cold and report the findings to the user.

Use cases: documents

No 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-local-changes

What's inside

Skill name
review-local-changes
Description
Review the local changes cold and report the findings to the user.
License
MIT
Instructions
62 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Review Local Changes

Review the local changes and report to the user. Completion is the report.

The **local changes** are everything in the working tree that the default branch lacks: commits since the merge-base with the default branch, plus staged, unstaged, and untracked files. Review them all, whichever session made them.

## 1. Review cold

Dispatch `$code-review`, `$simplicity-review` and `$bug-review` in parallel as subagents, each handed the diff of the local changes and nothing else.

One cold round. Treat findings as hypotheses:

1. Verify each finding against the diff and current code.
2. Fix every valid, in-scope finding.
3. Record false positives and out-of-scope findings, leaving the change as it stands.
4. Re-run the checks your fixes touched, and re-review the fixes alone.

## 2. Report to the user

Open with a simple explanation of the problem the local changes solve, then briefly explain the solution. Do not lead with an implementation inventory:

BAD

> ❌ Removed implicit workspace carry-over from every "new thread" entry point (cmd+n / cmd+shift+o, sidebar v1/v2 buttons, command palette). New threads inherit only the project from context; branch, worktree, and env mode always come from the configured defaults. Delete buildContextualThreadOptions, startNewThreadInProjectFromContext, and the v1 sidebar's seed-context machinery.

GOOD

> ✅ My "new worktree" default was ignored when starting new threads on existing worktrees. Super unintuitive. Now your preferences always apply.

Use the applicable sections from this structure in this exact order. Replace every placeholder and omit sections that have no content:

```markdown
## 📝 Summary

<Explain the problem, then the solution in plain language. This should be short, concise, and human-readable.>

## 📦 Changes

- <Name user visible and main area changes>

## ✅ Verification

- `<command>`: <result>

## 🔍 Reviews

| Review   | Found   | Fixed   |
| -------- | ------- | ------- |
| <review> | <count> | <count> |

<Tell the user what you changed during the review loop>

- <Every finding with its verdict: fixed, false positive, or out of scope, and why.>

## ⚠️ Needs attention

<List follow-up work, known limitations, or other issues that need the user's attention.>
```

List every review that ran, including reviews that found nothing. Never claim a check or review ran unless it did.

From falcondev-oss/skills, MIT.

More from falcondev-oss/skills

Signals

Stars
2
Forks
0
Open issues
0
Last commit (this folder)
Sep 25, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from falcondev-oss

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-local-changes 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.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying review-local-changes?

CallGet help
Cite this page

review-local-changes skill. Agent Mart. https://agentmart.dev/skills/falcondev-oss-review-local-changes (last updated 2026-10-24)