Agent skill

Requesting Code Review

by t1mmen in t1mmen/srtd

Structured code review workflow for SRTD development. An agent skill from t1mmen/srtd.

MITAuto-check passedDevelopment

Install Requesting Code Review

skills CLI
$ npx skills add t1mmen/srtd --skill requesting-code-review -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install t1mmen/srtd requesting-code-review --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/t1mmen/srtd.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/requesting-code-review .claude/skills/requesting-code-review && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
requesting-code-review
GitHub stars
105
Token cost
~807 tokens
SKILL.md length
342 words
Files
2
Skills in repo
3
Repo updated
First seen
Licence
MIT

At a glance

Structured code review workflow for SRTD development. An agent skill from t1mmen/srtd.

  • Works in 3 steps: Identify the Change Range → Dispatch the Code Reviewer → Address Feedback by Severity
  • Tasks that involve Code review
  • SKILL.md covers When to Request Review, How to Request Review, Responding to Feedback and SRTD-Specific Review Focus, plus 2 more sections
  • Calls git

What it does

Requesting Code Review is an agent skill from t1mmen/srtd. Structured code review workflow for SRTD development. Use after implementing features, fixing bugs, or before merging to main. Ensures production-readiness through systematic review.

Its SKILL.md is about 810 tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `code-reviewer.md`).

It sits in Development, covering Code review and Literature review. It works with Supabase, PostgreSQL and SQL. The repository describes itself as: 🪄 Supabase migrations made magical: Live-reloading SQL + Sane, reviewable diffs + Maintainable templates = Delightful DX. The licence is MIT.

When your agent uses it

  • Tasks that involve Code review
  • Tasks that involve Literature review

Example prompts

  • “/requesting-code-review”

Workflow steps

3 steps, taken from the step headings in SKILL.md.

  1. Identify the Change Range
  2. Dispatch the Code Reviewer
  3. Address Feedback by Severity

What it can do on your machine

Read from SKILL.md and the folder at commit 271b138. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Requesting Code Review loads about 807 tokens when it runs. Until then it costs about 51 tokens; SKILL.md has 342 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~51
When it runs · the whole SKILL.md, loaded when a task matches
~807

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from t1mmen/srtd at commit 271b138, republished under its MIT licence (© t1mmen). 342 words, ~807 tokens.

Download SKILL.mdSave it as .claude/skills/requesting-code-review/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
requesting-code-review
description
Structured code review workflow for SRTD development. Use after implementing features, fixing bugs, or before merging to main. Ensures production-readiness through systematic review.

Requesting Code Review

Review early, review often. Catch issues before they compound across multiple changes.

When to Request Review

Mandatory
  • After completing a feature or bug fix
  • Before merging to main
  • After significant refactoring
  • When security-sensitive code is modified
  • When stuck on a design decision
  • After complex debugging sessions
  • Before deleting or deprecating code

How to Request Review

Step 1: Identify the Change Range
bash
# Get the commits to review
git log --oneline main..HEAD

# Or specific commit range
BASE_SHA=$(git merge-base main HEAD)
HEAD_SHA=$(git rev-parse HEAD)
Step 2: Dispatch the Code Reviewer

Use the code-reviewer reference to conduct the review:

Review the changes from ${BASE_SHA} to ${HEAD_SHA}.

What was implemented: [brief description]
Requirements: [link to issue or spec]

See: .claude/skills/requesting-code-review/code-reviewer.md
Step 3: Address Feedback by Severity
SeverityAction Required
CriticalSTOP. Fix immediately before any other work.
ImportantFix before merging or proceeding to next task.
MinorNote for later. Can merge with these outstanding.

Responding to Feedback

When You Agree

Fix the issue, then request re-review of the fix.

When You Disagree

You may push back IF you have:

  1. Technical justification (not just preference)
  2. Evidence (code, tests, benchmarks)
  3. Clear explanation of trade-offs

Example: "I kept the nested structure because flattening would require N+1 queries. See benchmark in test/perf/nested-vs-flat.ts showing 3x slowdown."

SRTD-Specific Review Focus

When reviewing SRTD code, pay extra attention to:

Service Boundaries
  • Is state mutation only in StateService?
  • Is file I/O only in FileSystemService?
  • Is database access only in DatabaseService?
State Machine Integrity
  • Are template states transitioning correctly? (UNSEEN → CHANGED → APPLIED/BUILT → SYNCED)
  • Is hash comparison working correctly?
Build Log Handling
  • Are both .buildlog.json and .buildlog.local.json updated appropriately?
  • Is the distinction maintained? (built vs applied)
Error Handling
  • Are database errors properly categorized?
  • Is retry logic correct (3 attempts, exponential backoff)?
  • Are advisory locks used for concurrent access?

Anti-Patterns (Red Flags)

  • "This change is too simple to review" → Simple changes break production
  • "I'll fix that in a follow-up" for Critical/Important issues → Fix now
  • Ignoring review feedback without justification → Explain or fix
  • Reviewing your own code without fresh eyes → Request external review

Integration with Development Flow

After Each Task

Request review before marking task complete.

Before PR Creation

Run full review to catch issues before they're public.

After CI Feedback

Re-review if CI reveals issues not caught initially.

© t1mmen, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in .claude/skills/requesting-code-review of t1mmen/srtd.

  • SKILL.md
  • code-reviewer.md

Open the folder on GitHubat commit 271b138

Compare with similar skills

Requesting Code Review next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Requesting Code Review compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Requesting Code Review this skillt1mmen/srtd105—~807Automated safety check: PassMIT
PR Bot Reviewspgplex/pgconsole155—~2.1kAutomated safety check: PassApache-2.0
New Lintsupabase/splinter280—~2.9kAutomated safety check: NotesNone
Mz PR ReviewMaterializeInc/materialize6.4k—~1.6kAutomated safety check: NotesCustom licence
SQL Code Reviewtotvs/engpro-advpl-tlpp-skills141—~3.5kAutomated safety check: PassMIT
SQL Code Reviewgithub/awesome-copilot40k1 repos~2.2kAutomated safety check: PassMIT

Similar skills

  • PR Bot Reviews

    pgplex/pgconsole

    Triage, verdict, and reply to automated PR review comments from GitHub Copilot and Greptile, then iterate until the bots have nothing left to say.

    155 GitHub stars~2.1k tokensUpdated 1 mo ago
    DevelopmentAuto-check passed
  • New Lint

    supabase/splinter

    Official

    Create a new splinter lint — a SQL view that checks for a database anti-pattern.

    280 GitHub stars~2.9k tokensUpdated 8 days ago
    DevelopmentAuto-check: notes
  • Mz PR Review

    MaterializeInc/materialize

    Local code review of current branch vs Materialize standards.

    6.4k GitHub stars~1.6k tokensUpdated today
    DevelopmentAuto-check: notes
  • SQL Code Review

    totvs/engpro-advpl-tlpp-skills

    Universal SQL code review assistant that performs comprehensive security, maintainability, and code quality analysis across SQL databases (PostgreSQL, SQL Server, Oracle).

    141 GitHub stars~3.5k tokensUpdated 2 days ago
    DatabasesAuto-check passed
  • SQL Code Review

    github/awesome-copilot

    Official

    Universal SQL code review assistant that performs comprehensive security, maintainability, and code quality analysis across all SQL databases (MySQL, PostgreSQL, SQL Server, Oracle).

    40k GitHub starsUsed in 1 repo~2.2k tokens
    DatabasesAuto-check passed
  • Nubase

    OtterMind/Nubase

    A skill your agent uses when the user mentions Nubase broadly, wants a backend for an AI-generated app, or needs to deploy/publish generated code online — across Database, Auth, Storage, Assets…

    624 GitHub stars~2.2k tokensUpdated 9 days ago
    Backend & APIsAuto-check: notes

More from t1mmen/srtd

  • Srtd Dev

    t1mmen/srtd

    Expert knowledge for developing the SRTD codebase itself. An agent skill from t1mmen/srtd.

    105 GitHub stars~2.3k tokensUpdated 1 mo ago
    Auto-check passed
  • Srtd CLI

    t1mmen/srtd

    This skill should be used when the user mentions "srtd", "sql templates", "migrations-templates", "live reload sql", "supabase functions", when working with files in supabase/migrations-templates/…

    105 GitHub stars~360 tokensUpdated 1 mo ago
    Auto-check passed

Categories

Questions about Requesting Code Review

What does Requesting Code Review do?

Structured code review workflow for SRTD development. An agent skill from t1mmen/srtd. Requesting Code Review is an agent skill from t1mmen/srtd. Structured code review workflow for SRTD development.

When should I use Requesting Code Review?

Requesting Code Review fits situations like: tasks that involve Code review; tasks that involve Literature review.

How do I install Requesting Code Review in Claude Code?

Run `npx skills add t1mmen/srtd --skill requesting-code-review -a claude-code`. Or copy the skill folder (.claude/skills/requesting-code-review in t1mmen/srtd) into .claude/skills/requesting-code-review in your project. Claude Code loads it when a task matches its description.

How do I install Requesting Code Review in Codex?

Run `npx skills add t1mmen/srtd --skill requesting-code-review -a codex`. Or copy the skill folder (.claude/skills/requesting-code-review in t1mmen/srtd) into .agents/skills/requesting-code-review in your project. Codex loads it when a task matches its description.

Can I use Requesting Code Review in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add t1mmen/srtd --skill requesting-code-review -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/requesting-code-review, .gemini/skills/requesting-code-review, .github/skills/requesting-code-review and .opencode/skills/requesting-code-review in your project.

What does Requesting Code Review need to run?

Going by SKILL.md and its folder, Requesting Code Review needs the command-line tools its instructions call (git).

Does Requesting Code Review access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Requesting Code Review safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Requesting Code Review use?

Requesting Code Review is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Requesting Code Review use?

About 807 tokens (SKILL.md is roughly 3.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Requesting Code Review?

Skills that share tags, products or a category with Requesting Code Review: PR Bot Reviews (pgplex/pgconsole, 155 stars), New Lint (supabase/splinter, 280 stars), Mz PR Review (MaterializeInc/materialize, 6.4k stars) and SQL Code Review (totvs/engpro-advpl-tlpp-skills, 141 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Requesting Code Review?

t1mmen (a GitHub user) maintains it in t1mmen/srtd, which has 105 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on September 5, 2026.

Source: t1mmen/srtd on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.