一键导入
readonly-review
Run a no-network read-only review practice with two explorer steps and one synthesis step.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Run a no-network read-only review practice with two explorer steps and one synthesis step.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Use when a Codex CLI/Desktop root should fan out subagents, delegate to Pixir workers, run parallel workers, or manage a resident delegation daemon via Pixir Delegate; covers Codex preflight, AGENTS.md, approvals/sandbox, dry-run, daemon start/status/attach/cancel, closure evidence, and audited single-run execution (one bounded pixir run with an evidence bundle and verdict).
Use Pixir as a headless subagent runtime from Claude Code or any harness with skill `!` preprocessing (Codex roots and other no-hydration hosts use pixir-delegate-codex instead) — one-shot workers (`pixir --json`), parallel fan-out to N children (`pixir delegate --spec`), resumable steering (`pixir resume`), evidence drill-down. Use when the user wants to fan out subagents or parallel workers, delegate analysis or bounded coding tasks to GPT/OpenAI models, run cheap background workers, or steer and retry a worker across turns.
Delegate work to subagents from INSIDE a Pixir session using the native Subagent tools (spawn_agent, wait_agent, close_agent, list_agents, send_input) instead of shelling out to the pixir CLI. Use when you are a Pixir session that needs to fan out parallel workers, steer a child, or run skill-backed workflow templates — in-VM, without spawning nested pixir processes.
Diagnose Pixir and T3 Code Pixir incidents from local canonical evidence. Use when a Pixir run, ACP/T3 thread, subagent/workflow, provider replay, or daily-driver dogfood session appears stuck, inconsistent, missing tool output, or hard to classify.
| name | readonly-review |
| description | Run a no-network read-only review practice with two explorer steps and one synthesis step. |
Use this Skill when the task needs a bounded read-only review with independent perspectives before synthesis.
For a structural Workflow version of this practice, inspect:
workflows/parallel_review.json
Then instantiate it through run_workflow with:
template_id: readonly-review/parallel_reviewtemplate_args.topic: the thing being reviewedtemplate_args.focus_a: the first explorer focustemplate_args.focus_b: the second explorer focusThe template requests read-only explorer steps and contains no scripted side effects. When using it as an example, inspect the instantiated workflow before execution.