Benchmark Agents
vercel/vercel-plugin
Advanced AI agent benchmark scenarios that push Vercel's cutting-edge platform features — Workflow SDK, AI Gateway, MCP, Chat SDK, Queues, Flags, Sandbox, and multi-agent orchestration.
Run parallel multi-agent review on completed knowledge work.
Install Workflow Review
$ npx skills add nabeelhyatt/coworkpowers --skill workflow-review -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install nabeelhyatt/coworkpowers workflow-review --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/nabeelhyatt/coworkpowers.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/workflow-review .claude/skills/workflow-review && rm -rf skills-srcUse ~/.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/
Install the "workflow-review" agent skill from https://github.com/nabeelhyatt/coworkpowers/tree/main/skills/workflow-review into .claude/skills/workflow-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "workflow-review", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/nabeelhyatt/coworkpowers/tree/main/skills/workflow-reviewType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add nabeelhyatt/coworkpowers --skill workflow-review -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install nabeelhyatt/coworkpowers workflow-review --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/nabeelhyatt/coworkpowers.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/workflow-review .agents/skills/workflow-review && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "workflow-review" agent skill from https://github.com/nabeelhyatt/coworkpowers/tree/main/skills/workflow-review into .agents/skills/workflow-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "workflow-review", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add nabeelhyatt/coworkpowers --skill workflow-review -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install nabeelhyatt/coworkpowers workflow-review --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/nabeelhyatt/coworkpowers.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/workflow-review .cursor/skills/workflow-review && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "workflow-review" agent skill from https://github.com/nabeelhyatt/coworkpowers/tree/main/skills/workflow-review into .cursor/skills/workflow-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "workflow-review", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/nabeelhyatt/coworkpowers.git --path skills/workflow-review--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add nabeelhyatt/coworkpowers --skill workflow-review -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install nabeelhyatt/coworkpowers workflow-review --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/nabeelhyatt/coworkpowers.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/workflow-review .gemini/skills/workflow-review && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "workflow-review" agent skill from https://github.com/nabeelhyatt/coworkpowers/tree/main/skills/workflow-review into .gemini/skills/workflow-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "workflow-review", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install nabeelhyatt/coworkpowers workflow-reviewInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add nabeelhyatt/coworkpowers --skill workflow-review -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/nabeelhyatt/coworkpowers.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/workflow-review .github/skills/workflow-review && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "workflow-review" agent skill from https://github.com/nabeelhyatt/coworkpowers/tree/main/skills/workflow-review into .github/skills/workflow-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "workflow-review", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add nabeelhyatt/coworkpowers --skill workflow-review -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install nabeelhyatt/coworkpowers workflow-review --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/nabeelhyatt/coworkpowers.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/workflow-review .opencode/skills/workflow-review && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "workflow-review" agent skill from https://github.com/nabeelhyatt/coworkpowers/tree/main/skills/workflow-review into .opencode/skills/workflow-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "workflow-review", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
workflow-review- GitHub stars
- 113
- Token cost
- ~1.3k tokens
- SKILL.md length
- 438 words
- Files
- 1
- Skills in repo
- 4
- Repo updated
- First seen
- Licence
- MIT
At a glance
Run parallel multi-agent review on completed knowledge work.
- Works in 4 steps: Determine Review Scope → Parallel Agent Review → Synthesize Findings → …
- Requests like review this
- SKILL.md covers Process, Review Principles, Next Step and Anti-Patterns to Avoid
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Workflow Review is an agent skill from nabeelhyatt/coworkpowers. Run parallel multi-agent review on completed knowledge work. Use after the work phase to evaluate output quality from multiple specialized perspectives before finalizing. Triggers on requests like 'review this', 'check this before I send it', 'stress-test this recommendation', or when quality assurance is needed on a deliverable.
Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Testing & QA, covering Load testing, QA and bug reports and Multi-agent orchestration. The repository describes itself as: Superpowers for knowledge work in Claude Code. The licence is MIT.
When your agent uses it
- Requests like review this
- Check this before I send it
- Stress-test this recommendation
- Quality assurance is needed on a deliverable
Example prompts
- “review this”
- “check this before I send it”
- “stress-test this recommendation”
- “/workflow-review”
Workflow steps
4 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 65a1fb7. 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
No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
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
Workflow Review loads about 1.3k tokens when it runs. Until then it costs about 87 tokens; SKILL.md has 438 words of instructions outside code blocks.
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 nabeelhyatt/coworkpowers at commit 65a1fb7, republished under its MIT licence (© nabeelhyatt). 438 words, ~1,344 tokens.
Download SKILL.mdSave it as
.claude/skills/workflow-review/SKILL.md (or your agent's skills folder).- name
- workflow-review
- description
- Run parallel multi-agent review on completed knowledge work. Use after the work phase to evaluate output quality from multiple specialized perspectives before finalizing. Triggers on requests like 'review this', 'check this before I send it', 'stress-test this recommendation', or when quality assurance is needed on a deliverable.
Review: Multi-Agent Knowledge Work Review
You are orchestrating the Review phase of the Compound Knowledge Work loop. Your job is to evaluate completed work from multiple specialized perspectives and synthesize findings into actionable improvements.
Different perspectives catch different issues. A single reviewer misses things that parallel review catches.
Process
Phase 1: Determine Review Scope
- Read the completed work thoroughly.
- Identify the work type to select appropriate reviewers:
| Work Type | Standard Reviewers | Conditional Reviewers |
|---|---|---|
| Communication | clarity-reviewer, tone-calibrator, completeness-auditor | sensitivity-scanner (if sensitive topic), strategic-alignment-checker (if strategic) |
| Decision | completeness-auditor, risk-assessor, devil's-advocate, actionability-validator | strategic-alignment-checker (if organizational), sensitivity-scanner (if political) |
| Analysis | completeness-auditor, clarity-reviewer, actionability-validator | risk-assessor (if recommendations included), devil's-advocate (if controversial) |
| Meeting prep | completeness-auditor, actionability-validator, clarity-reviewer | stakeholder-mapper (if complex dynamics), sensitivity-scanner (if contentious topics) |
| Coaching notes | clarity-reviewer, actionability-validator | tone-calibrator (if shared with coachee) |
- Check if the plan specified reviewers. If so, use those as the baseline.
Phase 2: Parallel Agent Review
Launch all selected review agents in parallel using the Task tool.
Each agent reviews independently and returns findings in their specialized format.
Agent Instructions:
- Each agent receives the complete work output
- Each agent applies its specialized lens
- Each agent returns findings with severity levels
Phase 3: Synthesize Findings
After all agents return, synthesize their findings:
Output Format:
## Review Summary
### Overall Assessment
**Quality Score**: [1-10]
[2-3 sentence assessment of overall quality and readiness]
### Critical Issues (Must Fix)
Issues that would cause real problems if not addressed.
#### Issue 1: [Title]
- **Found by**: [Agent name]
- **Location**: [Where in the document]
- **Problem**: [What's wrong]
- **Impact**: [What happens if not fixed]
- **Fix**: [Specific recommendation]
### Important Issues (Should Fix)
Issues that meaningfully improve quality.
#### Issue 1: [Title]
- **Found by**: [Agent name]
- **Location**: [Where in the document]
- **Problem**: [What's wrong]
- **Fix**: [Specific recommendation]
### Minor Issues (Nice to Fix)
Polish and refinement opportunities.
- [Issue]: [Quick fix] _(found by [agent])_
- [Issue]: [Quick fix] _(found by [agent])_
### What's Working Well
- [Strength 1] _(noted by [agent])_
- [Strength 2] _(noted by [agent])_
### Conflicting Feedback
[If agents disagree, note the conflict and recommend resolution]
### Recommended Action
- [ ] Fix critical issues (estimated: [time])
- [ ] Fix important issues (estimated: [time])
- [ ] Fix minor issues (estimated: [time])
- [ ] Ready to finalize after fixesPhase 4: Apply Fixes
If the user approves:
- Fix critical issues first.
- Fix important issues.
- Fix minor issues if time permits.
- Present the revised version with a summary of changes made.
If issues conflict, present the tradeoff to the user and let them decide.
Review Principles
Show full SKILL.md (182 more words)Show less
Severity Calibration
- Critical: Would cause real damage - wrong tone in sensitive email, missing key stakeholder concern, factual error in analysis, flawed logic in decision
- Important: Meaningful quality improvement - unclear structure, missing context, weak evidence, incomplete consideration
- Minor: Polish - word choice, formatting, small redundancies
Independence Matters
- Each agent reviews independently
- Don't let one agent's findings influence another
- Conflicts between agents are valuable signal
Review Should Be Proportional
- Quick internal note: clarity-reviewer only
- Important email: clarity + tone + completeness
- Board presentation: all standard + conditional reviewers
- Strategic decision: all reviewers including devil's-advocate
The Devil's Advocate is Special
- Always include for decisions and recommendations
- Its job is to find the strongest counterargument
- Don't dismiss its findings just because you disagree
- If the devil's advocate can't find a good counterargument, that's strong validation
Next Step
When the work is finalized, capture what you learned: /coworkpowers:workflow-compound
Anti-Patterns to Avoid
- Running review on low-stakes work (wastes time)
- Ignoring conflicting feedback instead of resolving it
- Treating all findings as equal severity
- Over-revising based on minor feedback
- Not running devil's advocate on important decisions
- Applying fixes without user awareness of what changed
© nabeelhyatt, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/workflow-review of nabeelhyatt/coworkpowers.
Open the folder on GitHubat commit 65a1fb7
Compare with similar skills
Workflow 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Workflow Review this skillnabeelhyatt/coworkpowers | 113 | — | ~1.3k | Automated safety check: Pass | MIT | |
| Benchmark Agentsvercel/vercel-plugin | 301 | — | ~3.6k | Automated safety check: Pass | Custom licence | |
| Harness DesignAnastasiyaW/codex-claude-code-config | 154 | — | ~2.6k | Automated safety check: Pass | MIT | |
| Clawteam DevHKUDS/ClawTeam | 5.5k | 1 repos | ~1.1k | Automated safety check: Pass | MIT | |
| Acceptance Evidence for Deliverieslobehub/lobehub | 83k | — | ~9.7k | Automated safety check: Pass | Apache-2.0 | |
| Senpi Agent QA Harnesscode-yeongyu/senpi | 474 | — | ~2.7k | Automated safety check: Notes | MIT |
Similar skills
- Official
Harness Design
AnastasiyaW/codex-claude-code-config
Design a scoped multi-agent harness for a requested long-running AI workflow.
Clawteam Dev
HKUDS/ClawTeam
A skill your agent uses when working inside the ClawTeam repository itself: local development, debugging, reviewing, testing, validating multi-agent flows, or checking whether a code change actually…
Acceptance Evidence for Deliveries
lobehub/lobehub
Verifies a delivery end to end by driving the real product on a CLI, web, desktop or iOS Simulator surface, capturing evidence and publishing a round with the lh CLI.
Senpi Agent QA Harness
code-yeongyu/senpi
Checks changes to the senpi coding agent by driving the real CLI from source in an isolated sandbox, over RPC, terminal UI, mock model and CLI smoke channels.
tmux Real User Testing
QwenLM/qwen-code
Drives Qwen Code in a real tmux session the way a user would and saves a readable step-by-step transcript of each screen for maintainers to review.
More from nabeelhyatt/coworkpowers
Workflow Compound
nabeelhyatt/coworkpowers
Extract and store learnings from completed knowledge work to make the next task easier.
Workflow Research
nabeelhyatt/coworkpowers
Research and plan a knowledge work task thoroughly before execution.
Workflow Work
nabeelhyatt/coworkpowers
Execute a knowledge work plan efficiently while maintaining quality.
Related
Categories
Questions about Workflow Review
What does Workflow Review do?
Run parallel multi-agent review on completed knowledge work. Workflow Review is an agent skill from nabeelhyatt/coworkpowers. Run parallel multi-agent review on completed knowledge work.
When should I use Workflow Review?
Workflow Review fits situations like: requests like review this; check this before I send it; stress-test this recommendation; quality assurance is needed on a deliverable.
How do I install Workflow Review in Claude Code?
Run `npx skills add nabeelhyatt/coworkpowers --skill workflow-review -a claude-code`. Or copy the skill folder (skills/workflow-review in nabeelhyatt/coworkpowers) into .claude/skills/workflow-review in your project. Claude Code loads it when a task matches its description.
How do I install Workflow Review in Codex?
Run `npx skills add nabeelhyatt/coworkpowers --skill workflow-review -a codex`. Or copy the skill folder (skills/workflow-review in nabeelhyatt/coworkpowers) into .agents/skills/workflow-review in your project. Codex loads it when a task matches its description.
Can I use Workflow 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 nabeelhyatt/coworkpowers --skill workflow-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/workflow-review, .gemini/skills/workflow-review, .github/skills/workflow-review and .opencode/skills/workflow-review in your project.
What does Workflow Review need to run?
SKILL.md names no scripts, command-line tools or credentials: Workflow Review is instructions for the agent only.
Does Workflow Review access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Workflow 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 Workflow Review use?
Workflow 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 Workflow Review use?
About 1.3k tokens (SKILL.md is roughly 5.4k 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 Workflow Review?
Skills that share tags, products or a category with Workflow Review: Benchmark Agents (vercel/vercel-plugin, 301 stars), Harness Design (AnastasiyaW/codex-claude-code-config, 154 stars), Clawteam Dev (HKUDS/ClawTeam, 5.5k stars) and Acceptance Evidence for Deliveries (lobehub/lobehub, 83k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Workflow Review?
nabeelhyatt (a GitHub user) maintains it in nabeelhyatt/coworkpowers, which has 113 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on February 15, 2026.
Source: nabeelhyatt/coworkpowers on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.