CtrlK
BlogDocsLog inGet started
Tessl Logo

verify

Verify changes to the claude-for-msft-365-install admin scripts and commands by driving them against an isolated fake $HOME.

64

Quality

76%

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 ./claude-for-msft-365-install/.claude/skills/verify/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

96%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.

The body is an exemplary lean, executable verification runbook with strong validation feedback loops for destructive operations; its only minor gap is that all content lives in one file with no progressive-reference structure.

Suggestions

Consider extracting the Gotchas section into a references/GOTCHAS.md with a one-line pointer, to give the overview a cleaner progressive-disclosure shape.

Add a short 'Prerequisites' line stating the macOS-only constraint up front so Windows-only paths are signaled before the reader reaches the Gotchas.

DimensionReasoningScore

Conciseness

The body is dense and load-bearing throughout — executable commands and concrete failure modes with no padding, and it assumes Claude's competence (no explaining of $HOME, bash, or PowerShell basics).

5 / 5

Actionability

Provides fully executable, copy-paste-ready bash (sandbox seeding, list/dry-run/apply invocations), a working snap/diff function, and a PowerShell tokenize check covering the common verification cases.

5 / 5

Workflow Clarity

Clear sequence (lint gate → fake-$HOME drive → storage-retain diff → gotchas) with explicit validation checkpoints (snapshot-diff before/after, restore-and-re-diff, parse check before behavioural tests, arg-parser probe), satisfying the destructive-operation feedback-loop requirement.

5 / 5

Progressive Disclosure

Well-organized into clear sections with no nested or buried references and no bundle files to navigate, but it is a single longer document with no external references, so it sits just below the clean one-level-deep reference ideal.

4 / 5

Total

19

/

20

Passed

Description

57%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.

The description is specific and highly distinct, but it lacks an explicit 'Use when...' trigger clause and relies on plugin-specific jargon over natural user keywords, which caps completeness and trigger-term quality.

Suggestions

Add a 'Use when...' clause naming concrete triggers, e.g. 'Use when verifying changes to claude-for-msft-365-install admin scripts or before committing script edits.'

Surface natural synonyms users might say (e.g. 'Office add-in cache clearing', 'addin manifest scripts') alongside the plugin name.

Mention the macOS/Windows split and the key destructive-vs-dry-run distinction to broaden trigger coverage.

DimensionReasoningScore

Specificity

Names the domain ('claude-for-msft-365-install admin scripts and commands') and one concrete action ('Verify changes ... by driving them against an isolated fake $HOME'), but coverage is narrow rather than comprehensive.

3 / 5

Completeness

The 'what' is clear (verify changes by driving scripts against an isolated fake $HOME), but there is no 'Use when...' trigger clause, so per the rubric guideline completeness is capped at 3.

3 / 5

Trigger Term Quality

Includes relevant terms ('verify', 'changes', 'admin scripts', 'commands') but leans on plugin-specific jargon ('claude-for-msft-365-install', 'fake $HOME') rather than natural user phrasings and synonyms.

3 / 5

Distinctiveness Conflict Risk

Scoped to a single named plugin with a distinct verification niche; effectively no overlap risk with other skills.

5 / 5

Total

14

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 2 missing

Warning

Total

15

/

16

Passed

Repository
anthropics/financial-services
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.