Skip to content
Agentmart
Submit a tool

spec-review

Multi-person spec review with line-by-line comments and resolution tracking

Skill by zxdxjtu

IndexedMIT★ 8
Write a review

Chalk Labs

Need help deploying spec-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/zxdxjtu-spec-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

Multi-person spec review with line-by-line comments and resolution tracking

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/spec-review

What's inside

Skill name
spec-review
Description
Multi-person spec review with line-by-line comments and resolution tracking
License
MIT
Instructions
181 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Spec Review — Collaborative Specification Review

You are facilitating a structured review of a feature spec. Multiple reviewers (human or agent) can add line-by-line comments, and you track resolutions.

**Parameter**: $ARGUMENTS — feature ID (e.g. F001)

## Step 1: Load Spec

```bash
ls .harness/specs/ 2>/dev/null | grep "$FEATURE_ID"
```

Read the spec file `.harness/specs/FXXX-*.md`. If not found or status is not `approved`, inform user.

## Step 2: Initialize Review

Create or read `.harness/reviews/FXXX-review.md`:

```bash
ls .harness/reviews/ 2>/dev/null | grep "$FEATURE_ID"
```

If review file doesn't exist, generate it:

```markdown
---
feature: FXXX
status: in-review
reviewers: []
created: {ISO timestamp}
open_comments: 0
resolved_comments: 0
---

# Spec Review — FXXX: {feature name}

## Review Status
- Total comments: 0
- Open: 0
- Resolved: 0

## Sections Under Review

{For each major section of the spec (User Story, each AC, each INV, Technical Constraints, Zero-Decision-Point), create a review anchor:}

### User Story
> {quoted content from spec}

---

### AC-1: {content}
> {quoted content from spec}

---

### AC-2: {content}
> {quoted content from spec}

---

{... for all ACs, INVs, and other sections}
```

## Step 3: Collect Reviews

Ask user how they want to review:

1. **Self-review** — User reviews the spec themselves, adding comments interactively
2. **Agent review** — Launch reviewer sub-agents with different perspectives:
   - **Completeness reviewer**: Are all edge cases covered? Missing ACs?
   - **Feasibility reviewer**: Is this technically achievable within constraints?
   - **Consistency reviewer**: Does this conflict with existing features or full-spec?
3. **Collaborative** — Both user and agent reviewers

### For Agent Reviews

Launch up to 3 reviewer sub-agents in parallel:

```
Agent(subagent_type: "general-purpose", run_in_background: true,
  prompt: "You are a COMPLETENESS REVIEWER for spec FXXX.
  Read .harness/specs/FXXX-*.md
  Read .harness/full-spec.md (if exists) for existing feature context.

  For each AC and INV, ask:
  1. Are boundary conditions covered?
  2. Are error/failure scenarios defined?
  3. Are there implicit assumptions not stated?
  4. Could an implementer interpret this ambiguously?

  Output your review as:
  SECTION: {section name}
  COMMENT: {your finding}
  SEVERITY: critical|major|minor|suggestion")
```

### For User Reviews

Present the spec section by section, asking for each:
> "对于 AC-1,你有什么意见或补充吗?(输入评论,或说'通过'跳过)"

## Step 4: Record Comments

Add comments to `.harness/reviews/FXXX-review.md` under the relevant section:

```markdown
### AC-1: {content}
> {quoted content from spec}

**COMMENT** [{reviewer}] [{timestamp}] [severity: {critical|major|minor|suggestion}]
{comment content}
**STATUS**: open

**COMMENT** [{reviewer}] [{timestamp}] [severity: {minor}]
{another comment}
**STATUS**: open
```

Update the review frontmatter counters.

From zxdxjtu/harness, MIT.

More from zxdxjtu/harness

Signals

Stars
8
Forks
3
Open issues
1
Last commit (this folder)
Mar 28, 2026 (7 months ago)

From GitHub (fetched Oct 24, 2026).

Details

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

More from zxdxjtu

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 spec-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 spec-review?

CallGet help
Cite this page

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