docs-impact-localizer

Use this skill to translate a classifier's in-place verdict into a precise, page-by-page work plan for the docs-sync panel. Activate after docs-impact-classifier returns verdict in_place; reads the candidate page list, fetches the actual page contents, narrows scope to specific sections within each page, and emits the per-page task brief the panel fans out against.

Quality

79%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/docs-impact-localizer/SKILL.md

Quality

Content

82%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 tightly written, highly actionable SKILL.md body with concrete output schemas, real verification commands, and explicit scope boundaries. It loses a little on workflow_clarity (no validate→fix→retry loop for its own cross-page consistency checks) and minor conciseness/structure redundancy.

Suggestions

Add an explicit feedback loop for the cross-page consistency checks (e.g. 'if two redrafts disagree, re-narrow and re-emit') to satisfy the batch-operation validation expectation.

Collapse the duplicated output schema in Step 4 and the Output contract into a single authoritative block referenced once.

Trim the role-delineation framing ('You are NOT the verdict-maker...') into the single responsibility line to save tokens.

Dimension	Reasoning	Score
Conciseness	The body is efficient and largely free of padding — it states the single responsibility, the inputs, and four numbered steps with compact YAML/JSON examples — though a few framing sentences ('You are NOT the verdict-maker...') could be trimmed without losing clarity.	4 / 5
Actionability	Provides fully concrete, copy-ready guidance: exact YAML and JSON output shapes, example line ranges ('lines 120-145'), real grep/help verify commands, and explicit field names — covering the common case end-to-end.	5 / 5
Workflow Clarity	A clear Step 1–4 sequence with an embedded validation hook (verify_claims[] consumed by the verifier) and an anti-patterns checklist, but there is no explicit validate-then-fix feedback loop for the cross-page consistency checks the skill itself flags.	4 / 5
Progressive Disclosure	Well-organized into focused sections (Inputs, Steps 1–4, Output contract, Anti-patterns) with no nested references and no bundle files needed; the only minor gap is that the full output schema appears twice (Step 4 and Output contract) where a single authoritative block would be cleaner.	4 / 5
	Total	17 / 20 Passed

Description

76%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, well-scoped description that explicitly pairs a concrete 'what' with an unambiguous 'when' trigger tied to a specific upstream verdict. Its main weakness is trigger-term naturalness — the vocabulary is pipeline-internal rather than phrased the way a user would actually ask for it.

Suggestions

Add user-natural trigger phrasing alongside the internal one, e.g. 'Use when you need to turn an in-place docs change verdict into per-page edit tasks'.

Consider naming the produced artifact type ('a JSON per-page task brief') in the description so consumers can match on it.

Add a brief synonym or two (e.g. 'docs localization', 'docs impact scoping') to broaden natural-keyword coverage.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'reads the candidate page list, fetches the actual page contents, narrows scope to specific sections within each page, and emits the per-page task brief' — with only minor gaps (it does not name the input/output artifact types as explicitly as a 5).	4 / 5
Completeness	Clearly answers both 'what' (translate an in-place verdict into a per-page work plan) and 'when' ('Activate after docs-impact-classifier returns verdict in_place') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Uses the explicit 'Activate after docs-impact-classifier returns verdict in_place' trigger, but the keywords are internal pipeline jargon ('classifier', 'docs-sync panel') rather than natural phrases a user would say, and it lacks synonyms/variations.	3 / 5
Distinctiveness Conflict Risk	It carves a clear niche scoped to the in_place verdict and explicitly separates itself from the classifier and doc-writer, leaving only minor overlap risk with adjacent docs-sync skills.	4 / 5
	Total	16 / 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: microsoft/apm
Path: .agents/skills/docs-impact-localizer/SKILL.md
Commit: 71a877c

Reviewed: ~4 hours 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.