Collaborative, research-focused development workflow using spec files and tiered reviews.
Install
mkdir -p .claude/skills/zoo && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/17193" && unzip -o skill.zip -d .claude/skills/zoo && rm skill.zipInstalls to .claude/skills/zoo
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Lightweight spec-driven workflow: collaborative spec, top-level TDD implementation, tiered parallel review gate, one commit per subtask. Use only when explicitly requested.Key capabilities
- →Follow `.zoo/zoo.md` workflow
- →Log events to task file
- →Conduct research via subagents
- →Split work into subtasks
- →Perform tiered parallel reviews
- →Generate screenshots and input/output examples
How it works
The skill follows a spec-driven workflow, logging events to a task file, conducting research, splitting work into subtasks, performing reviews, and generating evidence before committing code.
Inputs & outputs
When to use zoo
- →Implement features using Zoo workflow
- →Run collaborative spec reviews
- →Document subtask research
About zoo
Follows a structured workflow for research, spec definition, and TDD-based implementation. Features tiered parallel review gates and evidence-based reporting for every subtask.
Lightweight spec-driven workflow: collaborative spec, top-level TDD implementation, tiered parallel review gate, one commit per subtask. Use only when explicitly requested.
When not to use it
- →When not explicitly requested to use the Zoo workflow
- →When not needing a spec-driven workflow
- →When not requiring tiered parallel review gates
Limitations
- →Requires a `.zoo/zoo.md` file for workflow definition
- →Task file (`.spec/YYYYMMDD-<task>.md`) is central to the workflow
- →Screenshots must be real and representative
How it compares
This skill enforces a structured, spec-driven workflow with explicit research, subtasking, and tiered reviews, which is more formalized than ad-hoc development.
Compared to similar skills
zoo side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| zoo (this skill) | 0 | 3mo | No flags | Advanced |
| code-review-checklist | 3 | 2mo | No flags | Beginner |
| openspec-verify-change | 3 | 8mo | Review | Advanced |
| superpowers-finish | 1 | 8mo | No flags | Beginner |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
code-review-checklist
vudovn
Code review guidelines covering code quality, security, and best practices.
openspec-verify-change
studyzy
验证实现是否与变更产出物匹配。当用户想要在归档前验证实现是否完整、正确且一致时使用。
superpowers-finish
anthonylee991
Finalizes work: runs verification, summarizes changes, notes follow-ups, and ensures repo hygiene. Use at the end of an implementation or debugging session.
positron-qa-verify
posit-dev
Generates clear, actionable verification guides for QA testing of Positron bug fixes and features
categorize-revdep-issues
r-lib
Write revdep/issue.md to group packages by common error categories
pr-review
microsoft
Multi-dimensional review of a PR or feature branch in the microsoft/winappcli repo. Activate when a contributor asks to "review my PR", "review my changes", "vet my branch before pushing", "do a full review", "PR review", "review this feature", or similar. Fans out parallel sub-agents covering secur