Compare original and revised text to check whether protected content survived editing. It combines a bundled validator for structural checks with a separate meaning review, then reports errors, warnings, and specific repair targets.
中文简介正在准备中。当前显示英语简介。
Use when the user provides an original and rewritten version, asks whether a rewrite preserved protected content, or wants a deterministic check for code, frontmatter, quotes, tables, links, paths, numbers, headings, and residual AI-pattern regressions.
安装前可以查看交给 AI 代理的指令内容。
Verify that a rewrite or file edit kept the content the original ../avoid-ai-writing/SKILL.md says to protect.
For cross-Skill work, follow ../avoid-ai-writing-router/references/handoff-contract.md and ../avoid-ai-writing-router/references/skill-graph.json.
Accept before/after verification from:
avoid-ai-writing-router via ROUTE when the user directly supplies before and after material.voice-preserving-rewriter via VERIFY after returned-text rewriting.file-edit-in-place via VERIFY after an authorized named-file mutation.Require both original and current versions. If either is unavailable, return control to the router rather than inventing a comparison.
Update the handoff envelope with:
execution_evidence.verifier: executed only if the bundled validator ran, otherwise model_only.verification_summary.status: PASS, REVIEW, or FAIL.A FAIL is a blocking workflow result. The rewrite/edit stage is not complete merely because text was produced or a file write succeeded.
REPAIR to voice-preserving-rewriter when returned text failed preservation and the shared editing budget has room.REPAIR to file-edit-in-place when a named file failed preservation and the shared editing budget has room.RECHECK to ai-writing-detector only when convergence or a residual audit was part of the user's request.PASS unless another user-requested stage remains.Apply both encoded lenses from ../avoid-ai-writing-router/references/agency-role-lenses.md:
agency-software-architect: verification is a boundary gate with explicit ownership and bounded repair cycles.agency-senior-developer: execution claims require actual command evidence, errors propagate, and before/after state remains attributable to the correct target.The verifier does not rewrite content itself.
The bundled scripts/validate.js is an exact copy of the source repository's preservation validator. When Node execution is available, run:
node scripts/validate.js --residual-policy warn before.md after.md
For programmatic use:
const { validate } = require("./scripts/validate.js");
const result = validate(original, rewritten, { residualPolicy: "warn" });
Use the explicit warn residual policy for editorial verification. The validator exposes mechanical preservation results separately from quality diagnostics while retaining top-level errors, warnings, and stats. Residual growth stays visible as a warning; it is not proof of content damage and does not by itself authorize a repair. A skipped, unavailable, or unscored quality check is not a clean residual audit. It does not decide whether a semantic change was grounded in an explicit user correction or whether the user specifically authorized editing a normally protected span. Never claim it ran unless the current host executed it.
If execution is unavailable, compare the original and rewrite manually using the same preservation contract and label the result as model_only.
In addition to the canonical validator's structural checks, apply the canonical editing contract in a separate semantic review. Check remaining meaning, attribution, quantities and units, negation, conditions, causality, uncertainty, and speaker experience. Treat an explicit user correction as the intended change rather than an invention. If the user specifically placed a normally protected span in scope, verify that requested change and continue protecting its data and attribution; do not infer permission from a general cleanup, style, or voice request. Report this review as model-only rather than claiming the deterministic validator performed it.
When human_representation_sensitive: true, review identity and representation details protected by the agency-inclusive-visuals-specialist lens. A structurally valid rewrite may still require REVIEW or FAIL if it erased or genericized material cultural, geographic, disability, attire, skin-tone/lighting, physical-reality, or anti-stereotype constraints.
Do not claim the deterministic validator checked semantic representation details that it does not implement. Report that portion separately as model-only semantic review.
No blocking mechanical preservation error was found and no warning or semantic concern remains unresolved. If the user requested a residual audit, PASS also requires quality.status: checked; skipped, unavailable, or unscored requires REVIEW even when a number-spelling warning has been resolved. This does not prove semantic fidelity. Continue only if another requested stage remains.
Warnings or semantic changes need judgment but are not automatically blocking. Review number-added, number-missing, and residual-grew against the source and context; number spelling changes can be legitimate. Report unavailable or unscored residual analysis as incomplete when that audit was required. This includes a literal validator difference that corresponds to a specifically requested edit of normally protected content: review it against that scope and its remaining data and attribution constraints instead of automatically repairing it back to the original. Explain the exact uncertainty.
Protected content changed or disappeared. Identify the correct repair owner from source kind:
voice-preserving-rewriterfile-edit-in-placePass only the blocking repair scope and existing envelope. Do not ask the repair owner to redo clean parts. If pass.index has reached pass.max, report the unresolved failure instead of requesting another mutation.
At most one repair re-entry is allowed, and only while the requested editing budget has room. The repair consumes the next editing pass. Verification itself does not consume a pass. After repair, verify once more. If that check still fails, stop and report the unresolved errors. Never cycle indefinitely.
Return PASS, FAIL, or REVIEW, verifier execution status, blocking preservation errors, warnings, any separate semantic-guard review, the suggested repair owner, and whether the bounded repair opportunity has already been used.
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问，或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Review text for common AI writing patterns without changing it. When Node execution is available, a local detector supplies scores and matches; contextual review separates useful editorial findings from possible false positives.
中文简介正在准备中。当前显示英语简介。
Review English prose for formulaic phrases and other patterns associated with AI writing, then make targeted edits while preserving meaning and voice. Choose findings only, a rewritten version, or direct edits to a prose file.
中文简介正在准备中。当前显示英语简介。
Coordinate AI-style writing reviews, voice-preserving rewrites, file edits, and before-and-after checks. Route each request to the appropriate related skill, carry context between stages, and report which checks ran and whether the original meaning was preserved.
中文简介正在准备中。当前显示英语简介。
Interpret AI-writing flags without treating them as proof of authorship. Separate tool results from editorial observations, consider plausible human explanations, and identify drafts, revision histories, or other process evidence needed for consequential academic, hiring, or publication decisions.
中文简介正在准备中。当前显示英语简介。
Edit a specified local file to remove justified AI writing patterns through focused changes. It preserves voice, facts, protected content, and document structure, then rereads edits and reports file changes and verification status.
中文简介正在准备中。当前显示英语简介。
Revise text to remove formulaic AI phrasing while keeping the writer’s voice, facts, intent, and structure. It targets justified changes, preserves protected passages, and reports editing limits and any unresolved issues.
中文简介正在准备中。当前显示英语简介。