一键导入
implement
Execute a pre-defined plan using implementation agents (no design changes)
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
Execute a pre-defined plan using implementation agents (no design changes)
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。
Generate a wide field of ideas, then pressure-test them. Five generators diverge, two challengers prune the weak ones, three synthesizers rank what survives.
Three-agent adversarial bug finder. Hunter overclaims every issue it can find, Skeptic disproves what it can, Referee arbitrates what survives. Scoring incentives force each role to behave honestly.
Dialectic process for reviewing, brainstorming, comparing tradeoffs, or stress-testing plans. Configurable modes, agent counts, and expert lenses.
Capture structured learnings (gotcha, pattern, decision, bug-fix) as JSONL per project. Cross-project searchable.
Assume the plan failed — then explain why. Three pessimists write failure narratives, two optimists rebut, a risk assessor weighs which failure modes are real.
Adversarial stress-test of code, a plan, or an argument. Three critics attack, one defender rebuts, a referee judges, then a hostile auditor attacks the synthesis itself.
基于 SOC 职业分类
| name | implement |
| description | Execute a pre-defined plan using implementation agents (no design changes) |
| user-invocable | true |
| disable-model-invocation | false |
| argument-hint | <plan reference or description> |
Execute a plan that has already been designed and approved. This is the "do" phase -- no redesigning.
Plan to implement: $ARGUMENTS
If no arguments, look for the most recently discussed plan in the conversation.
Find the plan to implement. Sources:
If no plan exists, STOP and tell the user: "No plan found. Run /plan-task first, or describe what to implement."
Before starting:
Assess the plan's scope and choose execution strategy:
Work through the plan's sub-tasks in order:
After each subagent returns, validate the report. See @subagent-validation.md for the full protocol.
Check the plan's success criteria:
Report results to the user.
See @rules.md for implementation guardrails.
After implementation completes, /verify is mandatory -- not optional. The /wrapup health check will flag sessions where /implement ran without /verify.