preservation-verifier

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.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

73%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, actionable verification skill with strong workflow clarity and a real bundled validator. Its main weakness is redundancy — the repair-loop limit is stated in three places — which hurts both conciseness and organization.

Suggestions

Consolidate the repair-loop limit into a single section; the "Stop and report on a second verification failure" rule currently appears in both "Outgoing" and "Repair-loop limit".

Move the FAIL repair-owner routing (returned text -> voice-preserving-rewriter; named file -> file-edit-in-place) into one place rather than splitting it across "Outgoing" and "Result handling".

Add a one-line note distinguishing which protected structures `scripts/validate.js` checks mechanically versus which require model-only semantic review, so the boundary is actionable at a glance.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and procedural without explaining basics Claude already knows, but the repair-loop rule is restated in three places ("Outgoing", the dedicated "Repair-loop limit" section, and implied in "Result handling"), which could be consolidated. Not a 4 because the repetition is noticeable rather than minor.	3 / 5
Actionability	Provides an executable command (`node scripts/validate.js before.md after.md`) and a real programmatic import (`const { validate } = require("./scripts/validate.js")`), with concrete PASS/REVIEW/FAIL routing. Not a 5 because the semantic-review and repair-owner guidance is instructional rather than copy-paste executable.	4 / 5
Workflow Clarity	Clear sequence (Incoming → Produce → Outgoing → Result handling) with the verifier itself as an explicit validation gate and a bounded repair→re-verify→stop feedback loop, satisfying the destructive/batch validation requirement.	5 / 5
Progressive Disclosure	Well-organized sections with a clearly signaled one-level-deep reference to the bundled `scripts/validate.js` (a real file), plus cross-skill references. Not a 5 because the repair-loop and FAIL-handling content is scattered across multiple sections rather than consolidated, creating minor organization gaps.	4 / 5
	Total	16 / 20 Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, specific description that clearly states what the skill does and when to use it, with a comprehensive list of protected structures. It loses a little on trigger-term quality where some phrasing leans technical rather than conversational.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete protected structures to check — "code, frontmatter, quotes, tables, links, paths, numbers, headings, and residual AI-pattern regressions" — giving comprehensive coverage of what the skill verifies.	5 / 5
Completeness	Explicitly answers both what (a deterministic preservation check over named structures) and when ("Use when the user provides an original and rewritten version, asks whether a rewrite preserved protected content, or wants a deterministic check...") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good natural-term coverage ("rewrite", "preserved", "headings", "links", "code") but interleaved with jargon ("deterministic check", "residual AI-pattern regressions") and missing some common synonyms. Not a 5 because a few natural phrasings users would actually say are absent.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche — before/after preservation verification — with distinct triggers (original + rewritten pair) and minimal overlap risk against rewriter or editor skills.	5 / 5
	Total	19 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: conorbronsdon/avoid-ai-writing
Path: skills/preservation-verifier/SKILL.md
Commit: 0c2a936

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.