Adonis0123/adonis-skills / skills/task-completion-loop
task-completion-loop
UnverifiedFinish an existing named plan/spec or clearly bounded unfinished non-trivial coding task through the explicit task-completion-loop: work ledger, Goal, implementation proof, agentic review, architecture hardening, and a fresh Claude audit. Use only for the whole requested pipeline, not ordinary implementation, planning, or review.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 18.3 KB |
| agents/openai.yaml | config | 456 B |
| evals/check_wait_rule.py | script | 4.5 KB |
| evals/evals.json | config | 28.9 KB |
| evals/trigger-eval.json | config | 4.5 KB |
| references/decision-and-terminal-gates.md | markdown | 9.5 KB |
evals/trigger-eval.json
View on GitHub[
{
"query": "Use task-completion-loop on docs/plans/project-persistence.md: reconcile every ledger item with real Grok and Claude, manage one Goal, implement all PENDING work, run review, architecture hardening, and a fresh final Claude audit.",
"should_trigger": true
},
{
"query": "对已经批准的 docs/specs/payments-migration.md 走完整 completion loop;三方先交叉质疑,然后实现、真实运行验收、review-fix、架构复扫和最终盲审。",
"should_trigger": true
},
{
"query": "这个 persistence plan 做了一半。我需要完整 task-completion-loop,把 VERIFIED_DONE/PENDING 账本对齐,同一个 Goal 下把所有剩余项和三道终态门禁做完。",
"should_trigger": true
},
{
"query": "I am stepping away. Finish the named auth RFC through the whole host + Grok Build + Claude Code convergence pipeline, not just implementation, and prove the final evidence is clean.",
"should_trigger": true
},
{
"query": "把 docs/plans/video-export.md 的所有 pending item 收口;要求 Goal、浏览器/runtime 验收、Grok auto review、同 scope architecture hardening 和新的 Claude 只读终审。",
"should_trigger": true
},
{
"query": "请显式执行 task-completion-loop,范围是 packages/core/** 和 plan 中列出的必要测试;没有授权 commit/push/deploy,其他门禁全部跑到最终证据一致。",
"should_trigger": true
},
{
"query": "现有 checkout rewrite spec 已决定产品行为,但代码只完成一半。用三 agent convergence + work ledger + Goal + implementation + review + architecture + blind audit 完整交付。",
"should_trigger": true
},
{
"query": "Run the explicit full completion loop for docs/rfcs/042-search-index.md, including transitive dependency preflight and a fresh hard-read-only Claude audit after every final fix.",
"should_trigger": true
},
{
"query": "对 unfinished release checklist 走整套多 agent finish sequence:先核对 plan 和现状,处理全部 PENDING,最终只有同一 evidence id 的测试与三道审查都通过才完成 Goal。",
"should_trigger": true
},
{
"query": "这个任务之前停在 architecture checkpoint 的用户 Decision Closure;现在按 task-completion-loop 恢复同一个 parent Goal,继续复扫、刷新验证并完成 fresh Claude audit。",
"should_trigger": true
},
{
"query": "packages/persistence/** 是一个范围清楚但只完成一半的非平凡编码任务;没有单独 plan/spec。请走完整 task-completion-loop:从当前代码建账本,在同一 Goal 下实现全部 PENDING,再做 agentic review、架构复扫和 fresh Claude audit。",
"should_trigger": true
},
{
"query": "按 docs/specs/signup-validation.md 实现 Zod 校验并跑单测,改动只有两个文件;不需要多 agent convergence 或终局盲审。",
"should_trigger": false
},
{
"query": "给 Codex 设一个 Goal,把 PLAN.md 做到 pnpm test 和 pnpm build 通过;不用 Grok、Claude 或 architecture hardening。",
"should_trigger": false
},
{
"query": "review 当前 PR,发现问题就修并 re-review 到 PASS;不要做三方方案收敛、Goal 或 architecture rescan。",
"should_trigger": false
},
{
"query": "把范围冻在 packages/core/**,只跑 architecture scan-fix-review-rescan 直到 NO_ACTIONABLE_FINDINGS,不需要完成某个 plan。",
"should_trigger": false
},
{
"query": "先只读检查 docs/plans/persistence.md 还有哪些项目没做,给状态报告,不要启动实现或外部 agent。",
"should_trigger": false
},
{
"query": "我们要不要从 REST 换 GraphQL?产品和 API owner 还没决定,先把 tradeoff 和领域边界讨论清楚,不写代码。",
"should_trigger": false
},
{
"query": "对 docs/plans/persistence.md 的改动跑 review-fix-re-review 到 PASS,再做同范围 architecture rescan;不需要 Goal、三方收敛或最终盲审。",
"should_trigger": false
},
{
"query": "修一下 README 的命令 typo,然后告诉我改了哪一行;不要跑完整测试。",
"should_trigger": false
},
{
"query": "CI 的 login.test.ts 只在 Ubuntu 偶发失败,先系统定位根因和修复,不需要三 agent completion pipeline。",
"should_trigger": false
},
{
"query": "把我飞书任务清单里今天未完成的个人待办都标记完成;这不是 coding plan,也没有 Git 仓库。",
"should_trigger": false
}
]
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit. | Stars: 467k | Updated | Claude CodeCodex | Verified | Install |
| rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure. | Stars: 467k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 467k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 193k | Updated | Claude CodeCodex | Verified | Install |