infra-drift-audit
Compare declared infrastructure against what a state refresh reports, and list the divergences without resolving them.
- License 许可
- Apache-2.0
- 最近更新
- 2026-11-05
- Stars
- ★ 212
- Forks
- 33
01 前言 Front Matter
- name
- infra-drift-audit
- description
- Compare declared infrastructure against what a state refresh reports, and list the divergences without resolving them.
03 SKILL.md 正文
Audit infrastructure drift
Steps
- Ask which working directory holds the configuration, and confirm it contains
.tffiles before going further. - Read the declared resources from the configuration. Read the observed resources from a state refresh output the user supplies. Never assume one from the other.
- Report three lists, in this order: declared but absent, present but undeclared, and present with differing attributes. Include the resource address in every entry.
- For the third list, name each differing attribute with its declared and observed values side by side. An entry with no named attribute is not a drift finding — leave it out.
What not to do
- Do not import, taint or remove anything from state. This skill reports divergence; changing state is a human decision made after reading the report.
- Do not treat a formatting difference as drift.
- Do not report a total drift count without the per-resource lists behind it.
04 同仓库更多 Skills
web-verify
Verify a built web page or app actually renders and works — drive it in a real browser, check the console and network, confirm the thing you changed is the thing being served, and capture evidence. Use before claiming a frontend change works.
visual-output
Emit rich visual output in chat via <widget> tags — styled HTML cards, charts, tables, interactive tools, and drawn SVG/canvas diagrams, illustrations, and animations — theme-aware, centered, and responsive instead of clashing or cramped.
task-and-project
Track work as Tasks (the /api/tasks CRUD + native task provider), and decompose larger projects into independent, verifiable units — fanning parallel investigation out to subagents while keeping one coherent plan; hand open-ended goal-driven work to a goal loop.
research-campaign
Run a multi-cycle research campaign — grill the question, decompose it into answerable sub-questions, investigate each against sources, then synthesize with confidence and gaps stated. Use for open questions that need real investigation rather than one lookup.
memory-discipline
When and how to persist durable memory — save genuine user preferences, facts, and corrections; NEVER persist transient environment failures (a failed command, a flaky network call, a one-off tool error) as lessons; recall before re-asking.
loop-worker
Per-cycle protocol for an autonomous goal loop worker — the unified autonomous goal engine that runs one self-directed cycle per turn until its goal is met, then self-retires. Drives one cycle against a loop's file interface (status.json gate, brief.md goal, guidance.txt nudges, findings/cycle_NNN.json, FINDINGS.md, the type-appropriate deliverable, STOP sentinel). The worker produces work and reports evidence; a deterministic check or a separate judge — never the worker — decides done-ness.