Pre-action boundary checking — validates agent tool calls against declared capabilities and task contracts
中文简介正在准备中。当前显示原文说明。
Disciplined goal-to-execution workflow for any user task. Parses objective, asks only for materially missing requirements via ambiguity-gate, inspects repo via idea, plans via sdd-dev or deep-plan, executes safely under project conventions, verifies completion per R020, and reports changed files with evidence. Use when user invokes /goal <task>.
中文简介正在准备中。当前显示原文说明。
查看安装方法安装前可以查看交给 AI 代理的指令内容。
Apply project discipline (planning, verification, cleanup, review) to any user-provided task. Acts as a thin orchestrator that routes to existing oh-my-customcode skills rather than duplicating logic.
/goal <task description>
Example: /goal Add a /weekly-summary command that aggregates last 7 days of git activity
<task> as the concrete goal. Do NOT expand scope beyond what was asked.ambiguity-gate skill. Ask only for materially missing or risky requirements — no over-clarification on details that can be inferred.idea skill (NL-intent codebase analysis) to identify relevant files, dependencies, and existing assets.sdd-dev or deep-plan for research-validated planning.[Done]. Run task-type-specific checks (lint, build, test).[Goal] {original task verbatim}
[Plan] {brief plan or reference to deep-plan/sdd-dev output}
[Changes] {file list with paths}
[Verified] {evidence — exit codes, test counts, build output}
[Risks] {remaining concerns or "none"}
| Scenario | Use Instead |
|---|---|
| Pure research/analysis | research, idea, memory-recall |
| Specialist domain task | Routing skills (dev-lead-routing, de-lead-routing, qa-lead-routing) |
| Trivial single-file edit | Delegate directly to specialist agent |
| Bug debugging | superpowers:systematic-debugging |
| Stage | Skill | Role |
|---|---|---|
| Gap detection | ambiguity-gate | Score request clarity, ask only critical gaps |
| Repo inspection | idea | NL-intent codebase analysis |
| Planning (research-validated) | deep-plan | research → plan → verify cycle |
| Planning (SDD discipline) | sdd-dev | Stage gates with planning-first workflow |
| Verification | superpowers:verification-before-completion | Evidence before assertions |
| Reporting | result-aggregation | Concise output composition |
This skill is intentionally a thin wrapper / orchestrator. It does NOT duplicate planning, gap-detection, or verification logic. Its value:
If a future skill replaces idea or sdd-dev, only the integration table updates — /goal remains stable.
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Pre-action boundary checking — validates agent tool calls against declared capabilities and task contracts
中文简介正在准备中。当前显示原文说明。
Auto-detect project context and optimize harness — deactivate unused agents/skills, suggest missing experts, generate project profile
中文简介正在准备中。当前显示原文说明。
Adversarial code review using attacker mindset — trust boundary, attack surface, business logic, and defense evaluation
中文简介正在准备中。当前显示原文说明。
Apache Airflow best practices for DAG authoring, testing, and production deployment
中文简介正在准备中。当前显示原文说明。
Alembic migration patterns for naming conventions, safety checks, expand-contract, env.py configuration, and CI integration
中文简介正在准备中。当前显示原文说明。
Pre-routing ambiguity analysis — scores request clarity and asks clarifying questions when needed (inspired by ouroboros)
中文简介正在准备中。当前显示原文说明。