CtrlK
BlogDocsLog inGet started
Tessl Logo

docs-impact-architect

Use this skill when the docs-impact-classifier returns a structural verdict, signalling that the documentation TOC must change to accommodate the PR. Proposes TOC deltas (new pages, moves, merges) and emits new-page outline stubs that the doc-sync panel later fleshes out. Holds the 3-promise narrative (consume / produce / govern) and the persona ramps as hard constraints.

61

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/docs-impact-architect/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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 tight, well-structured architect skill that gives concrete templates, a clear step sequence, and an explicit validation gate against hard rules. It could move from strong to excellent by adding an executable verification step for the structural-shape match and tightening a few redundant framing sentences.

Suggestions

Add an explicit verify/retry loop after Step 4 (e.g. re-run the promise-validation checks against the emitted JSON before returning) to push workflow clarity toward a 5 for this design-pass skill.

Trim framing redundancies like 'You are NOT the writer... You are the TOC architect' and 'The structural shape drives the TOC delta shape' which restate what the steps already make concrete.

DimensionReasoningScore

Conciseness

The body is efficient and assumes Claude's competence (e.g. 'Load .apm/docs-index.yml entirely. Inspect chapters[], pages[], promises[]. This is your map.'), with only minor spots that could be trimmed.

4 / 5

Actionability

Provides concrete, copy-paste-ready YAML and JSON templates for new_page, moved_page, retired_page, and the final report schema, with minor gaps around exact command invocation.

4 / 5

Workflow Clarity

Five clearly sequenced steps with an explicit validation checkpoint in Step 4 ('Apply these hard rules. If any fails, redesign') and a feedback loop, though it is guidance-level rather than a verify-and-retry command loop.

4 / 5

Progressive Disclosure

Well-organized sections (When to invoke, Inputs, Steps 1-5, Output contract, Anti-patterns) with no bundle files needed; structure is clear and navigable, just shy of the ideal 'overview pointing to one-level-deep references' shape.

4 / 5

Total

16

/

20

Passed

Description

67%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 specific, well-bounded description that clearly states both what the skill does and when it runs, anchored to a concrete upstream signal. Its main weakness is trigger-term quality: the trigger is an internal verdict rather than natural user-language keywords.

Suggestions

Add natural-language trigger phrases a user might say (e.g. 'when documentation structure, TOC, or page organization needs to change for a PR') alongside the internal classifier-verdict trigger.

Name the concrete output artifacts more directly (e.g. 'a JSON architect report with TOC deltas and page outline stubs') to sharpen the 'what' further.

DimensionReasoningScore

Specificity

Lists several concrete actions ('Proposes TOC deltas (new pages, moves, merges) and emits new-page outline stubs') and names the domain precisely, with only minor gaps in the full output inventory.

4 / 5

Completeness

Both 'what' (proposes TOC deltas, emits outline stubs, holds narrative constraints) and 'when' (when the classifier returns a structural verdict) are present and explicit, though the 'when' is internal-signal-driven rather than user-trigger-driven.

4 / 5

Trigger Term Quality

The trigger is the internal classifier verdict ('docs-impact-classifier returns a structural verdict') rather than natural user-language phrases; it lacks synonyms a user would actually say.

3 / 5

Distinctiveness Conflict Risk

The skill occupies a clear niche (TOC architect downstream of a specific classifier) with distinct triggers; minor overlap risk only with adjacent doc-writer skills.

4 / 5

Total

15

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
microsoft/apm
Reviewed

Table of Contents

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.