菜单
Audit technical docs for weak claims, AI slop, unclear product boundaries, false promises, and prose that misleads builders or buyers.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Raise the ceiling, don't climb toward it. When a target is nearly hit or a metric has plateaued, question the target itself: name the binding constraint, separate the physics floor from the assumed floor, design the regime change that makes 10x reachable, commit through the valley. Triggers: 'breakout', '10x this', 'raise the ceiling', 'why are we capped', 'think way bigger', 'this metric is a cage'.
Prove that a merged change is actually live and production behavior is measured against the deployed artifact. Use after merge, before claiming deployed/live/validated, for Cloudflare Pages/Workers deploys, cache claims, perf claims, and release closeout.
Diagnose and improve eval harnesses built on @tangle-network/agent-eval or similar trace-first systems. Use when success/failure rates, scorecard deltas, judge outputs, promotion gates, benchmark rows, or improvement campaigns may be contaminated by harness bugs, evaluator drift, routing/auth failures, missing traces, or invalid baselines.
Goal-pursuit loop: measure, diagnose, experiment, verify, compare, and iterate against a measurable target. Triggers: evolve, optimize, make this better, push to target.
Split one messy experiment branch into N clean, independent branches — one logical change each, built from the merge-base, disjoint change-sets, each an isolated reviewable PR. Triggers: 'finalize', 'split this branch', 'atomize this', 'make reviewable PRs', 'decompose this mess'.
Read repo/session state and choose the single next skill: exploit (evolve/polish), explore (pursue/meta-harness/breakout), bootstrap (eval-agent), diagnose (diagnose/eval-harness-diagnose), or step back (reflect). One dispatch, then exit.
| name | docs-slop-audit |
| description | Audit technical docs for weak claims, AI slop, unclear product boundaries, false promises, and prose that misleads builders or buyers. |
Use this for technical docs, READMEs, whitepapers, launch notes, product pages, and generated MDX.
The goal is truth and reader utility, not prettier prose.
For public writing, blog, research, marketing, or product pages, also read the relevant docs/anti-patterns/ file before editing.
scan-docs-slop.mjs when available.Return findings with file:line, risk, evidence, and suggested edit. If editing, make the changes and run the repo's doc/check commands.
Use references/patterns.md and references/full-reference.md for scanner details.
Use docs/anti-patterns/ for durable anti-slop doctrine.
humanizer for non-technical voice cleanup after facts are fixed.critical-audit when docs expose API or SDK contract risk.