trust-reliability-loop-lite
Scope, eval-first, tiered inference, recommend-first trust loop (see docs/TRUST_RELIABILITY_LOOP.md).
- License 许可
- MIT
- 最近更新
- 2026-11-09
- Stars
- ★ 1
- Forks
- 0
01 前言 Front Matter
- name
- trust-reliability-loop-lite
- description
- Scope, eval-first, tiered inference, recommend-first trust loop (see docs/TRUST_RELIABILITY_LOOP.md).
03 SKILL.md 正文
Skill: trust-reliability-loop-lite
Follow docs/TRUST_RELIABILITY_LOOP.md. Source: https://music.youtube.com/watch?v=Xa1jm2VWEHk
python3 scripts/trust_reliability_loop_gate.py --json
Rules:
- Narrow workflows only —
ops_daily_brief, paywall/WQTU/release/CI alerts. - Eval-first — log every candidate, action, correction, outcome; optimize precision by workflow.
- Tiered inference — rules → classify → extract → premium → confirm.
- Recommend-first — no unconfirmed external writes; progressive autonomy per action class.
- Alert budget — precision over coverage; provenance (
source_url) everywhere. - Cost per retained — never claim unit economics from tokens alone.
Defer do-anything chat, continuous always-on reasoning, and unbounded context windows.
04 同仓库更多 Skills
writing-plans
Use when you have a spec or requirements for a multi-step task, before touching code
workflow-economics-lite
Escape AI pilot purgatory: require completion-loop workflows with one owner, baseline, economic metric, system-of-record integration, and audit trail. Block orphan chatbots and interest-as-ROI claims.
verification-before-completion
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
value-center-lite
Apply InfoQ Rohrer value-center / VSM five questions (agency + coherence). Use when planning work, shipping releases, or auditing agent autonomy claims. Fail closed on product-only slogans without WQTU/paywall value.
using-superpowers
Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions
using-git-worktrees
Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback