gsd-review
Peer review system that delegates phase plan validation to other AI agents.
Install
mkdir -p .claude/skills/gsd-review && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/13487" && unzip -o skill.zip -d .claude/skills/gsd-review && rm skill.zipInstalls to .claude/skills/gsd-review
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.
Request cross-AI peer review of phase plans from external AI CLIsKey capabilities
- →Invoke external AI CLIs for review
- →Translate `AskUserQuestion` to `request_user_input`
- →Translate `Task()` to `spawn_agent`
- →Collect responses from agents
- →Write `REVIEWS.md` with feedback
How it works
The skill translates GSD workflow commands to Codex tools, spawns agents for review based on specified CLIs, collects their responses, and compiles them into a `REVIEWS.md` file.
Inputs & outputs
When to use gsd-review
- →Peer review my plan
- →Request cross-agent feedback
- →Validate phase architecture
About this skill
<codex_skill_adapter>
A. Skill Invocation
- This skill is invoked by mentioning
$gsd-review. - Treat all user text after
$gsd-reviewas{{GSD_ARGS}}. - If no arguments are present, treat
{{GSD_ARGS}}as empty.
B. AskUserQuestion → request_user_input Mapping
GSD workflows use AskUserQuestion (Claude Code syntax). Translate to Codex request_user_input:
Parameter mapping:
header→headerquestion→question- Options formatted as
"Label" — description→{label: "Label", description: "description"} - Generate
idfrom header: lowercase, replace spaces with underscores
Batched calls:
AskUserQuestion([q1, q2])→ singlerequest_user_inputwith multiple entries inquestions[]
Multi-select workaround:
- Codex has no
multiSelect. Use sequential single-selects, or present a numbered freeform list asking the user to enter comma-separated numbers.
Execute mode fallback:
- When
request_user_inputis rejected (Execute mode), present a plain-text numbered list and pick a reasonable default.
C. Task() → spawn_agent Mapping
GSD workflows use Task(...) (Claude Code syntax). Translate to Codex collaboration tools:
Direct mapping:
Task(subagent_type="X", prompt="Y")→spawn_agent(agent_type="X", message="Y")Task(model="...")→ omit (Codex uses per-role config, not inline model selection)fork_context: falseby default — GSD agents load their own context via<files_to_read>blocks
Parallel fan-out:
- Spawn multiple agents → collect agent IDs →
wait(ids)for all to complete
Result parsing:
- Look for structured markers in agent output:
CHECKPOINT,PLAN COMPLETE,SUMMARY, etc. close_agent(id)after collecting results from each agent </codex_skill_adapter>
Flow: Detect CLIs → Build review prompt → Invoke each CLI → Collect responses → Write REVIEWS.md </objective>
<execution_context> @/home/swiftiepi/Desktop/incuba/.codex/get-shit-done/workflows/review.md </execution_context>
<context> Phase number: extracted from {{GSD_ARGS}} (required)Flags:
--gemini— Include Gemini CLI review--claude— Include the agent CLI review (uses separate session)--codex— Include Codex CLI review--opencode— Include OpenCode review (uses model from user's OpenCode config)--all— Include all available CLIs </context>
When not to use it
- →When the task is not about requesting cross-AI peer review of phase plans
- →When `request_user_input` is rejected in Execute mode
Limitations
- →Codex has no `multiSelect` for `AskUserQuestion` translation
- →Model selection is per-role config, not inline for `Task()` translation
How it compares
This skill automates the process of requesting and consolidating peer reviews from multiple external AI CLIs, unlike a manual review process.
Compared to similar skills
gsd-review side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| gsd-review (this skill) | 0 | 4mo | No flags | Intermediate |
| multi-agent-brainstorming | 1 | 4mo | No flags | Intermediate |
| flow-next-prime | 0 | 2mo | Review | Intermediate |
| claude-automation-recommender | 47 | 2mo | Review | Beginner |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
multi-agent-brainstorming
sickn33
Use this skill when a design or idea requires higher confidence, risk reduction, or formal review. This skill orchestrates a structured, sequential multi-agent design review where each agent has a strict, non-overlapping role. It prevents blind spots, false confidence, and premature convergence.
flow-next-prime
gmickel
Comprehensive codebase assessment for agent and production readiness. Scans 8 pillars (48 criteria), verifies commands work, checks GitHub settings. Reports everything, fixes agent readiness only. Triggers on /flow-next:prime.
claude-automation-recommender
anthropics
Analyze a codebase and recommend Claude Code automations (hooks, subagents, skills, plugins, MCP servers). Use when user asks for automation recommendations, wants to optimize their Claude Code setup, mentions improving Claude Code workflows, asks how to first set up Claude Code for a project, or wants to know what Claude Code features they should use.
subagent-driven-development
davila7
Use when executing implementation plans with independent tasks in the current session
coding-agent
openclaw
Run Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control.
requesting-code-review
obra
Use when completing tasks, implementing major features, or before merging to verify work meets requirements