spec-review
Multi-person spec review with line-by-line comments and resolution tracking
Skill by zxdxjtu
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.
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.
About
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/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
- 0.466score
tdd-align
zxdxjtu
Generate three-layer tests from spec — tests are the alignment contract
SkillDFreshness: D★ 8Claude Code +9 - 0.466score
entropy-clean
zxdxjtu
Post-wave entropy cleanup — remove debug artifacts, enforce style, ensure git hygiene
SkillDFreshness: D★ 8Claude Code +9 - 0.466score
eval-fix
zxdxjtu
Adversarial fix loop: read eval report → fix gaps → re-evaluate → repeat until convergence
SkillDFreshness: D★ 8Claude Code +9 - 0.466score
evaluate
zxdxjtu
Adversarial evaluation: compare dev product against reference baseline using Playwright MCP
SkillDFreshness: D★ 8Claude Code +9 - 0.466score
harness-init
zxdxjtu
Initialize Harness for your project — learn repo, team norms, generate customized framework
SkillDFreshness: D★ 8Claude Code +9 - 0.466score
harness-status
zxdxjtu
Restore state, health check, determine current phase, suggest next step
SkillDFreshness: D★ 8Claude Code +9 - 0.466score
proposal
zxdxjtu
Start a new feature proposal — guided spec + design generation
SkillDFreshness: D★ 8Claude Code +9 - 0.466score
sdd-init
zxdxjtu
Initialize SDD harness for a project — scan codebase, generate config, full-spec, full-design
SkillDFreshness: D★ 8Claude Code +9 - 0.466score
steward
zxdxjtu
Module stewardship guardian — check code changes against AGENT.md boundaries and contracts
SkillDFreshness: D★ 8Claude Code +9 - 0.466score
archive
zxdxjtu
Phase 3: merge spec/design deltas, code review, atomic commits, push, and trigger self-evolution
SkillDFreshness: D★ 8Claude Code +9 - 0.466score
baseline
zxdxjtu
Capture baseline of a reference product using Playwright MCP for clone/replicate scenarios
SkillDFreshness: D★ 8Claude Code +9 - 0.463score
help
zxdxjtu
Explain Harness plugin and available commands
SkillDFreshness: D★ 8Claude Code +9
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
- Repository
- github.com/zxdxjtu/harness
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from zxdxjtu
- 0.466score
eval-fix
zxdxjtu
Adversarial fix loop: read eval report → fix gaps → re-evaluate → repeat until convergence
SkillDFreshness: D★ 8Claude Code +9 - 0.466score
evaluate
zxdxjtu
Adversarial evaluation: compare dev product against reference baseline using Playwright MCP
SkillDFreshness: D★ 8Claude Code +9 - 0.466score
baseline
zxdxjtu
Capture baseline of a reference product using Playwright MCP for clone/replicate scenarios
SkillDFreshness: D★ 8Claude Code +9 - 0.466score
entropy-clean
zxdxjtu
Post-wave entropy cleanup — remove debug artifacts, enforce style, ensure git hygiene
SkillDFreshness: D★ 8Claude Code +9 - 0.466score
archive
zxdxjtu
Phase 3: merge spec/design deltas, code review, atomic commits, push, and trigger self-evolution
SkillDFreshness: D★ 8Claude Code +9 - 0.466score
harness-init
zxdxjtu
Initialize Harness for your project — learn repo, team norms, generate customized framework
SkillDFreshness: D★ 8Claude 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 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.
Cite this page
spec-review skill. Agent Mart. https://agentmart.dev/skills/zxdxjtu-spec-review (last updated 2026-10-24)