Skip to content

Adonis0123/adonis-skills / skills/goal-gate

goal-gate

Verified

Gate whether a coding-agent task benefits from a durable, verifiable contract, then draft, validate, start, continue, or close it for Codex, Grok, Claude Code, Cursor CLI, or an unknown host. Use for explicit goal or /goal requests and autonomous multi-checkpoint coding work with one checkable end state. Native Goal creation or mutation requires an explicit user or system request. Do not use for quick one-shot work, unrelated backlogs, OKRs, reminders, or token-budget-only changes.

FileKindSize
SKILL.mdskill md14.5 KB
agents/openai.yamlconfig386 B
evals/evals.jsonconfig46.5 KB
evals/trigger-eval.jsonconfig3.7 KB
references/copy-ready-goals.mdmarkdown10.9 KB
references/examples.mdmarkdown26.7 KB
references/runtime-actions.mdmarkdown10.8 KB
scripts/lint-goal-prompt.pyexecutablescript6.2 KB
scripts/test-lint-goal-prompt.pyexecutablescript10.8 KB

evals/trigger-eval.json

View on GitHub
[
  {
    "query": "给 Codex 创建一个 durable goal:按 docs/PLAN.md 完成迁移,直到 pnpm test 和 pnpm build 都通过。这个 goal 的 token budget 设为 50000。",
    "should_trigger": true
  },
  {
    "query": "把这个仓库里所有过期的 ESLint disable 清完,范围只限 apps/web,结束条件是 pnpm lint 零 warning;我先离开,你设个 goal 做到闭环。",
    "should_trigger": true
  },
  {
    "query": "帮我写一个能直接复制到 Grok 的 /goal,按 RFC 完成数据库迁移,每一步都要展示 rollback 测试证据。",
    "should_trigger": true
  },
  {
    "query": "Should I set a durable goal for this multi-checkpoint refactor, or is it small enough to keep in one turn?",
    "should_trigger": true
  },
  {
    "query": "当前 Codex goal 的验收证据已经齐了,请检查后把同一个 goal 标成 complete。",
    "should_trigger": true
  },
  {
    "query": "给 Claude Code 写一个 /goal:实现 docs/design.md 的全部验收项,失败时最多迭代五轮,并明确何时暂停问我。",
    "should_trigger": true
  },
  {
    "query": "我在 Cursor CLI 里,帮我设一个 goal 把 docs/PLAN.md 做完,直到测试和构建都通过;中断后要能从同一个 chat 继续。",
    "should_trigger": true
  },
  {
    "query": "Set up a goal to improve prompts/support-agent.md until the support-agent eval score reaches 0.92, without changing fixtures.",
    "should_trigger": true
  },
  {
    "query": "我下线两个小时。把 auth flaky test 的根因找出来并修到 CI 重跑通过;这是长调试任务,帮我用 goal 管起来。",
    "should_trigger": true
  },
  {
    "query": "把支付 provider 重构计划做完,包含实现、测试、迁移文档和最终全量验证;先判断是否适合 set-now goal。",
    "should_trigger": true
  },
  {
    "query": "Make a portable coding-agent goal contract with exact write boundaries, checkpoints, verification, and pause conditions for this release cleanup.",
    "should_trigger": true
  },
  {
    "query": "Validate this plain Cursor CLI goal contract before I use it; keep the documented resume semantics and do not execute it.",
    "should_trigger": true
  },
  {
    "query": "把 Codex 的 goal token budget 从 30000 改成 50000,任务内容不要动。",
    "should_trigger": false
  },
  {
    "query": "以后有空把前端 typo、后端慢查询、README 翻译、设计稿整理和旧分支删除都处理一下,没有固定范围和结束时间。",
    "should_trigger": false
  },
  {
    "query": "把 README 里的 recieve 改成 receive,其他都不要动。",
    "should_trigger": false
  },
  {
    "query": "运行一次 pnpm test,把失败结果告诉我。",
    "should_trigger": false
  },
  {
    "query": "帮产品团队制定下季度 OKR,目标是提升留存率。",
    "should_trigger": false
  },
  {
    "query": "每周五提醒我看一次项目进度。",
    "should_trigger": false
  },
  {
    "query": "根据这个 staged diff 写一条 Conventional Commit message。",
    "should_trigger": false
  },
  {
    "query": "先开放探索一下整个仓库的架构问题,不用设范围,也不需要停止条件。",
    "should_trigger": false
  },
  {
    "query": "这个 UI 重设计应该走 Challenge 还是 Plan?只帮我选 workflow。",
    "should_trigger": false
  },
  {
    "query": "把这段产品需求改写成一句目标说明,给周报用;不需要 coding agent 持续执行、验证或创建 durable goal。",
    "should_trigger": false
  },
  {
    "query": "Rewrite this customer-support system prompt for a friendlier tone; it is not a durable goal contract.",
    "should_trigger": false
  }
]
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall