self-review
Use when implementation is complete and verification has passed — dispatches the sensei agent for fresh-context quality review
Skill by thesyntaxninja
Chalk Labs
Need help deploying self-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/thesyntaxninja-self-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/self-review
What's inside
- Skill name
self-review- Description
- Use when implementation is complete and verification has passed — dispatches the sensei agent for fresh-context quality review
- License
- MIT
- Instructions
- 89 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Self-Review ## Quick Reference After implementation + verification, dispatch the sensei for a fresh-context review of the actual `git diff`. The sensei has no memory of writing the code — pure quality signal. ## When to Use - After `verification-before-completion` passes - Before committing or creating a PR - After any non-trivial implementation (>5 lines changed) ## When NOT to Use - Single-line typo fixes - Comment-only changes - Changes the user explicitly marked as "skip review" ## Core Process ### Step 1: Check the diff Run `git diff` (or `git diff --staged` if changes are staged) to see what changed. If the diff is empty, nothing to review. ### Step 2: Assess review level | Change Size | Action | |-------------|--------| | < 20 lines, single file | Quick inline self-check (no agent needed) | | 20-100 lines | Dispatch sensei at configured strictness | | > 100 lines or 3+ files | Dispatch sensei at MEDIUM minimum | ### Step 3: Quick self-check (small changes) For changes under 20 lines, ask yourself: - Does this introduce any obvious issues? - Is there dead code, debug prints, or TODOs? - Does it match the project's existing patterns? If all clear, proceed. ### Step 4: Dispatch the sensei (larger changes) Use the Agent tool to dispatch the sensei review agent: ``` Agent: review/sensei Task: Review the following git diff for quality, simplicity, and pattern compliance. Context: [brief description of what was implemented and why] ``` The sensei reviews the actual diff and returns: - REMOVE: things to delete - SIMPLIFY: things to make simpler - PATTERN MISMATCH: pattern violations by severity - VERDICT: PASS | SIMPLIFY_FIRST | RETHINK ### Step 5: Act on sensei feedback | Verdict | Action | |---------|--------| | PASS | Proceed to commit/PR | | PASS_WITH_NOTES | Proceed to commit/PR. Show advisory notes to user for awareness. No simplification loop. | | SIMPLIFY_FIRST | Apply simplifications, re-verify, re-review (max 2 rounds) | | RETHINK | Discuss with user before proceeding | ### Simplification Loop ``` Round 1: Sensei review → Apply fixes → Re-verify Round 2: Sensei review → Apply fixes → Done (show remaining items to user) ``` Maximum 2 simplification rounds. After round 2, show any remaining items to the user and proceed. ## Anti-Patterns | Anti-Pattern | Why It's Wrong | |--------------|----------------| | Skipping review for "obvious" changes | Obvious changes often have subtle bugs | | Reviewing from memory instead of the diff | Memory is biased. The diff is truth. | | Infinite polish loops | 2 rounds max. Ship it. | | Ignoring sensei feedback because "it works" | Working != good. Quality matters. | ## Chaining OPTIONAL: syntaxninja-dojo:compound-docs (when a hard problem was solved)
From thesyntaxninja/syntaxninja-dojo, MIT.
More from thesyntaxninja/syntaxninja-dojo
- 0.443score
receiving-code-review
thesyntaxninja
Use when receiving code review feedback — requires technical verification of each suggestion before implementing, not blind agreement
SkillDFreshness: D★ 2Claude Code +9 - 0.443score
requesting-code-review
thesyntaxninja
Use when implementation is complete and a comprehensive code review is needed — dispatches parallel review agents and merges findings
SkillDFreshness: D★ 2Claude Code +9 - 0.443score
executing-plans
thesyntaxninja
Use when an approved plan exists and implementation should begin — executes steps sequentially with verification checkpoints
SkillDFreshness: D★ 2Claude Code +9 - 0.443score
propose-skill-update
thesyntaxninja
Use when 3+ distinct occurrences suggest a skill should be updated with a new trigger, anti-pattern, or verification step
SkillDFreshness: D★ 2Claude Code +9 - 0.443score
ralph-loop
thesyntaxninja
Use when task scope exceeds one context window and decomposes into independent pass/fail stories with clean iteration boundaries
SkillDFreshness: D★ 2Claude Code +9 - 0.443score
subagent-driven-development
thesyntaxninja
Use when executing an implementation plan with independent tasks that can be delegated to subagents within the current session
SkillDFreshness: D★ 2Claude Code +9 - 0.443score
verification-before-completion
thesyntaxninja
Use when about to claim work is complete, fixed, or passing — requires running verification commands and confirming output before making any success claims
SkillDFreshness: D★ 2Claude Code +9 - 0.442score
writing-plans
thesyntaxninja
Use when a task requires multiple steps and benefits from a structured plan before implementation begins
SkillDFreshness: D★ 2Claude Code +9 - 0.442score
prd-generator
thesyntaxninja
Use when a structured PRD document is needed for the ralph loop — generates prd.json and progress.txt
SkillDFreshness: D★ 2Claude Code +9 - 0.442score
story-decomposition
thesyntaxninja
Use when a large task needs to be broken into independent, verifiable stories with pass/fail acceptance criteria
SkillDFreshness: D★ 2Claude Code +9 - 0.442score
brainstorming
thesyntaxninja
Use when requirements are unclear, ambiguous, or have multiple valid interpretations — before planning or implementing
SkillDFreshness: D★ 2Claude Code +9 - 0.442score
compound-docs
thesyntaxninja
Use when a hard problem was just solved and the solution should be captured as a learning for future reference
SkillDFreshness: D★ 2Claude Code +9
Signals
- Stars
- 2
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Mar 4, 2026 (8 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from thesyntaxninja
- 0.443score
ralph-loop
thesyntaxninja
Use when task scope exceeds one context window and decomposes into independent pass/fail stories with clean iteration boundaries
SkillDFreshness: D★ 2Claude Code +9 - 0.443score
executing-plans
thesyntaxninja
Use when an approved plan exists and implementation should begin — executes steps sequentially with verification checkpoints
SkillDFreshness: D★ 2Claude Code +9 - 0.443score
requesting-code-review
thesyntaxninja
Use when implementation is complete and a comprehensive code review is needed — dispatches parallel review agents and merges findings
SkillDFreshness: D★ 2Claude Code +9 - 0.443score
propose-skill-update
thesyntaxninja
Use when 3+ distinct occurrences suggest a skill should be updated with a new trigger, anti-pattern, or verification step
SkillDFreshness: D★ 2Claude Code +9 - 0.443score
receiving-code-review
thesyntaxninja
Use when receiving code review feedback — requires technical verification of each suggestion before implementing, not blind agreement
SkillDFreshness: D★ 2Claude Code +9 - 0.443score
subagent-driven-development
thesyntaxninja
Use when executing an implementation plan with independent tasks that can be delegated to subagents within the current session
SkillDFreshness: D★ 2Claude 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 self-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
self-review skill. Agent Mart. https://agentmart.dev/skills/thesyntaxninja-self-review (last updated 2026-10-24)