Index of every page on this site: llms.txt
All skills
Run it yourself

Use when preparing a PR or completing a phase of work and needing a full-spectrum code review. Runs security, API audit, and scope reviewers in parallel and synthesizes findings into a single go/no-go report. Read-only — no file modifications. Keywords: pre-PR review, security audit, API audit, scope review, code review, merge check. Triggers on "review all changes" or "run pre-PR review".

Use this Skill: https://skilld.dev/gh/acedergren/agentic-tools/review-all

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈102 tokens for metadata: the name and description. ≈597 when used: this file.

Description uses 5.1% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈405 characters, or 5.1%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

Review All

When to Use

Load this skill when the user request matches the frontmatter description for Review All.

Comprehensive pre-PR review: run specialized reviewers in parallel, synthesize into a single report. Read-only — no changes.

NEVER

  • Never let any reviewer edit files during this pipeline — read-only is non-negotiable.
  • Never report duplicate findings separately when two reviewers flag the same line — merge into one finding.
  • Never review the whole repository when the user only changed a narrow diff — scope to changed files.
  • Never use this as a substitute for lint, typecheck, or tests — it complements them, runs after them.
  • Never run this for implementation tasks or auto-remediation requests — wrong tool.

Pipeline

Step 1: Identify changed files

git diff --name-only main...HEAD
# On main: git diff --name-only HEAD~5
# Or: bash scripts/detect-review-range.sh

Step 2: Launch parallel review agents

Spawn all agents simultaneously via Task tool:

Agent Type Scope Checks
Security Reviewer security-reviewer (custom) Changed files only OWASP Top 10, IDOR, injection, auth gaps
API Route Auditor Explore agent Routes + types dirs Schema coverage, type drift, auth hooks
Scope Auditor Explore agent git diff output Out-of-scope modifications, formatting-only noise

Add project-specific reviewers as needed (DB query reviewer, framework reviewer).

Step 3: Synthesize report

## Pre-PR Review Report

### Summary
| Reviewer  | Findings | Critical | Warnings |
|-----------|----------|----------|----------|
| Security  | 2        | 0        | 2        |
| API Audit | 3        | 1        | 2        |
| Scope     | 1        | 0        | 1        |

### Critical Issues (must fix before merge)
[CRITICAL/HIGH findings with file:line references]

### Warnings (consider fixing)
[MEDIUM/LOW findings]

### Clean Areas
[What passed with no issues]

Step 4: Verdict

End with one clear statement:

  • READY TO MERGE — No critical issues, warnings acceptable
  • NEEDS FIXES — Critical issues found; list exactly what must change
  • NEEDS DISCUSSION — Architectural concerns or ambiguous scope

Arguments

  • (empty): Review changes vs main
  • HEAD~3: Review last 3 commits
  • --security-only: Only security reviewer

Source: SKILL.md on GitHub

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

1 warning7mo5 checks · Risk SAFE
  • Gen Agent Trust Hub8mo

    This skill is a pre-PR review pipeline that coordinates specialized agents to audit code changes identified via Git. It operates in a read-only manner and does not perform any network requests, credential access, or file modifications, making it safe for use in development environments.

  • Socket8mo

    No alerts

  • Snyk8mo

    Risk: LOW · No issues

  • Runlayer8mo

    1/2 files flagged

  • ZeroLeaks7mo

    Score: 93/100 · 2 sections analyzed

Signed by skilld at 641a79b. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub last month.

Steadyupdated 6 months ago

README badge

README badge for acedergren/agentic-tools/review-all