Skip to content
Agentmart
Submit a tool

tech-review

Review a lane/branch before opening (or while awaiting) a PR in any PlatformRelay repo.

Skill by PlatformRelay

IndexedMIT★ 1
Write a review

Chalk Labs

Need help deploying tech-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/platformrelay-tech-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

Review a lane/branch before opening (or while awaiting) a PR in any PlatformRelay repo. Runs the gate matrix and TDD/correctness/quality/security/docs review plus an AI-code failure-mode pass, and returns APPROVE / REQUEST CHANGES / BLOCK. Must run before every PR. Use when asked to "review the lane / check before merging".

Use cases: testing, 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/tech-review

What's inside

Skill name
tech-review
Description
Review a lane/branch before opening (or while awaiting) a PR in any PlatformRelay repo. Runs the gate matrix and TDD/correctness/quality/security/docs review plus an AI-code failure-mode pass, and returns APPROVE / REQUEST CHANGES / BLOCK. Must run before every PR. Use when asked to "review the lane / check before merging".
License
MIT
Instructions
32 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# tech-review — pre-PR technical review

The shared review gate for the workspace. Runs the `tech-reviewer` role in fresh context, posts a
structured verdict, and **never self-approves**. Repo-specific wrappers (`/mkurator-review`,
`/kollect-mr-review`) call into this with the repo's gate set pre-filled.

## Step 1 — gather inputs
Target repo, lane name, branch, worktree path, base SHA (`origin/main`), and the story/board scope.
Run from inside the worktree.

## Step 2 — dispatch the tech-reviewer
Spawn the `tech-reviewer` subagent with those inputs and pointers to the repo's `AGENTS.md` +
`GUIDELINES.md`. It orients on intent, runs the gate matrix, reviews all dimensions + the AI-code
failure-mode pass, adversarially prunes its own findings, and returns a REVIEW block with a verdict.

## Step 3 — post and stop
- Post the REVIEW block to `agent-context/coordination/OPERATOR-BOARD.md` under RESULTS (audit trail).
- If a PR is open, post the same as a **PR comment** (`gh pr comment` — never `gh pr review
  --approve`). This is what the maintainer reads to decide.
- Update the board row to the verdict:
  - **APPROVE** — `🟢 PR open … reviewed APPROVE, awaiting maintainer merge`. Do nothing further, and
    append a **PR** line to the INBOX so the merge is on the operator's queue.
  - **REQUEST CHANGES** — leave `🔶 In flight`; list required items; worker fixes and re-runs this.
  - **BLOCK** — `🔴 BLOCKED`; escalate in SESSION-HANDOFF Blockers; do not re-run until the maintainer
    weighs in.

## Do not
- Let the review approve or merge — it produces findings; the maintainer merges.
- Skip it before a PR, or open a PR on a REQUEST CHANGES / BLOCK verdict.
- Re-review the same lane without a fresh gate run between changes.

From PlatformRelay/Kaddy, MIT.

More from PlatformRelay/Kaddy

Signals

Stars
1
Forks
0
Open issues
0
Last commit (this folder)
Jul 20, 2026 (3 months ago)
Last release
Jul 21, 2026 (3 months ago)

From GitHub (fetched Oct 24, 2026).

Details

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

More from PlatformRelay

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 tech-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 tech-review?

CallGet help
Cite this page

tech-review skill. Agent Mart. https://agentmart.dev/skills/platformrelay-tech-review (last updated 2026-10-24)