Skip to content
Agentmart
Submit a tool

ai-codebase-review

Audit a whole codebase for bottlenecks.

Skill by cristiano-pacheco

IndexedMIT★ 1
Write a review

Chalk Labs

Need help deploying ai-codebase-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.

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/cristiano-pacheco-ai-codebase-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.

We use your email only for this newsletter. Privacy

About

Audit a whole codebase for bottlenecks.

Use cases: security

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/ai-codebase-review

What's inside

Skill name
ai-codebase-review
Description
Audit a whole codebase for bottlenecks.
License
MIT
Instructions
58 lines in SKILL.md · view on GitHub

Files (2)

  • SKILL.md
  • report-format.md · references/

SKILL.md (first lines)

You are a principal software engineer reviewing a production codebase. Produce a **surgical, evidence-based** report with only the most important findings — the few issues that materially affect scalability, reliability, correctness, latency, database load, queue/job throughput, external service pressure, operational cost, data consistency, and maintainability of critical paths.

This is distinct from `ai-code-review`, which reviews a single branch's diff. This skill scans the whole codebase (or a named flow/system within it).

## How to run the review

1. **Load the method and format.** Read `references/report-format.md` in full — it defines the inputs to focus on, the precision rules (evidence-backed findings, facts vs assumptions), the analysis method, the exact output structure, and the quality bar. Follow it exactly.
2. **Analyze the repository** currently available. If the user named a specific feature/flow/system, use it as the reference scenario; otherwise infer the most important production-critical flows and state your assumptions.
3. **Write the report** in the exact structure from the format file. Keep it to a maximum of 5 findings (prefer 2–4).
4. **Save it** to the vault and report the path.

## Output to Obsidian

All output goes to the user's Obsidian vault, written **directly on the local filesystem** (no MCP), grouped by project.

**Vault root:** `$OBSIDIAN_AI_VAULT` (defaults to `$HOME/Documents/obsidian/obsidian` if unset). Everything below lives under `<vault>/engineering/...`. Use the `Read`/`Write`/`Edit` tools (and `ls` via Bash) with the **absolute** path, e.g. `$OBSIDIAN_AI_VAULT/engineering/<project>/...`. Wikilink text inside notes stays vault-root-relative and unchanged (`[[engineering/...]]`) — never put the absolute path inside `[[...]]`.

**Commit to the vault repo (after writing).** Once this run's files are written (the note plus any `index.md` updates), delegate the vault commit to the `ai-commit` skill (see `ai-commit/SKILL.md`). Pass the commit message:

```
ai-codebase-review: <system>
```

`ai-commit` resolves the vault root from `$OBSIDIAN_AI_VAULT`, stages, commits, and pushes. Never run `git add` / `git commit` / `git push` directly here. If `ai-commit` reports nothing staged, no `origin`, or a push failure, report it briefly and finish — don't abort the skill. `ai-setup` configures the repo and its `origin`.

### Resolve the project base path

1. Run `git rev-parse --show-toplevel`; the basename is the project name.
2. If not a git repo, propose a name from `basename "$PWD"` (kebab-cased) and **confirm with the user**.
3. Base path: `engineering/<project>`.

### Write the file (one new file per review, never overwrite)

Every review creates a **new** file directly in `engineering/<project>/codebase-reviews/` — never a subfolder, and never overwriting a previous report.

Build the file name as `<timestamp>-<system>.md`:

1. `<timestamp>` = output of `date +%Y-%m-%d-%H%M%S` (e.g. `2026-05-29-143052`). The leading timestamp keeps the folder sorted chronologically.
2. `<system>` = a kebab-case slug for the feature/system reviewed (e.g. `dispatch-hot-path`), with every character outside `[A-Za-z0-9._-]` replaced by `-`.

Full path example: `<vault>/engineering/<project>/codebase-reviews/2026-05-29-143052-dispatch-hot-path.md`.

Write the file with the `Write` tool (it creates missing parent folders). The second-level timestamp makes each run a distinct file, so you never overwrite a previous report.

Below the report's H1, add a related-links blockquote: `> **Project:** [[engineering/<project>/index|<project>]]`.

### Maintain the index (keep the graph connected)

After saving, wire the note into the Obsidian graph with append-if-missing. Wikilinks use vault-root-relative paths + alias; use the filename without `.md` as both target and alias.

1. **Project index** — `engineering/<project>/index.md`: read it (if missing, create it with `# <project>` and a `↑ [[engineering/index|Engineering]]` back-link); add a bullet `- [[engineering/<project>/codebase-reviews/<timestamp>-<system>|<timestamp>-<system>]]` under a `## Codebase Reviews` heading with the `Edit` tool (each review is a new file, so always add one).
2. **Root index** — `engineering/index.md`: ensure a bullet `- [[engineering/<project>/index|<project>]]` exists under `## Projects` (create it if missing).

`ai-reindex` rebuilds all indexes deterministically; this step just keeps the graph live.

Report the final vault path when done.

From cristiano-pacheco/ai-tools, MIT.

More from cristiano-pacheco/ai-tools

Signals

Stars
1
Forks
1
Open issues
0
Last commit (this folder)
Aug 22, 2026 (2 months ago)

From GitHub (fetched Oct 24, 2026).

Details

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

More from cristiano-pacheco

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 ai-codebase-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.

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

Need help deploying ai-codebase-review?

CallGet help
Cite this page

ai-codebase-review skill. Agent Mart. https://agentmart.dev/skills/cristiano-pacheco-ai-codebase-review (last updated 2026-10-24)