CtrlK
BlogDocsLog inGet started
Tessl Logo

devx-ux

Activate when designing or modifying CLI command surfaces, command help text, install/init/run flows, error wording, or first-run experience in the APM CLI -- even when the user does not say "UX" explicitly.

63

Quality

75%

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/devx-ux/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

76%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 instruction skill that wastes no tokens and points cleanly to a persona reference. Its weakness is the absence of an explicit review/verification workflow with a validation checkpoint, which caps workflow clarity, and the lack of any worked example or template for its most concrete rule (error wording).

Suggestions

Add a short validation step to the workflow — e.g., after rewording an error, re-read it as a first-run user and confirm it states the failure, cause, and one next action — to lift workflow_clarity above 3.

Include one worked error-message example (before/after) so the 'name the failure, cause, and one next action' rule is copy-paste ready, pushing actionability toward 5.

Make the persona-agent link a clearly signaled reference ('See [Developer Tooling UX expert persona](...) for detailed review heuristics') to strengthen the one-level-deep navigation signal.

DimensionReasoningScore

Conciseness

The body is lean and presumes Claude's competence: bullet lists of concrete file paths and rules with no concept explanations, no padding, and no restating of what a CLI or UX is — every token earns its place.

5 / 5

Actionability

It points to concrete files ('src/apm/cli.py', 'help=` strings, named commands) and gives actionable rules ('Every error names the failure, the cause, and one next action'), but offers no executable code/command examples or a worked error-message template, leaving a minor gap versus the copy-paste-ready 5.

4 / 5

Workflow Clarity

The 'When to activate' list gives a recognizable trigger sequence and 'Key rules' a checklist, but there is no explicit multi-step workflow (e.g., audit help -> rewrite error -> verify wording) and no validation checkpoint to confirm the UX change reads correctly, capping it at 3.

3 / 5

Progressive Disclosure

Content is well organized into short sections and links one level deep to a persona agent file; there are no nested or buried references, though the single link is not a clearly labeled 'see X for details' reference block, a minor organization gap.

4 / 5

Total

16

/

20

Passed

Description

75%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, third-person description with concrete capability surfaces and an explicit activation clause that reaches beyond the literal 'UX' keyword. It is held back from full marks by trigger-term breadth (missing synonyms/shorthand) and a 'when' clause that describes load-time conditions rather than user-stated needs.

Suggestions

Add natural synonyms and file targets users actually say, e.g. 'command-line interface, CLI flags, --help output, exit codes, error messages', to lift trigger term coverage toward 5.

Reframe the 'when' clause around user-stated needs ('Use when the user is editing CLI commands, flags, help text, or error messages') in addition to the meta 'Activate when...' trigger.

Tighten the APM-CLI scoping into the trigger phrase itself so the distinctiveness is reinforced in the keywords, not only the domain clause.

DimensionReasoningScore

Specificity

The description enumerates concrete surfaces ('CLI command surfaces, command help text, install/init/run flows, error wording, first-run experience') — several specific actions with only minor coverage gaps (no mention of flags/exit codes), fitting the 'lists several specific actions' anchor rather than the comprehensive 5.

4 / 5

Completeness

It explicitly answers 'what' (designing/modifying CLI UX surfaces) and 'when' ('Activate when... even when the user does not say UX explicitly'), but the 'when' trigger is a meta-instruction about when to load rather than a concrete user-need phrase, so it stops short of the fully explicit 5.

4 / 5

Trigger Term Quality

Natural trigger phrases like 'CLI command surfaces', 'help text', 'install/init/run flows', 'error wording', and 'first-run experience' are terms a user would say, but it lacks synonyms/file extensions and the common shorthand 'CLI UX'; good coverage with a few natural terms missing.

4 / 5

Distinctiveness Conflict Risk

The APM-CLI-specific scope ('in the APM CLI') and explicit deferral of logging-architecture decisions to a sibling skill carve a clear niche with minimal overlap, though 'CLI UX' broadly could lightly overlap with a general CLI skill, keeping it just below the distinct-niche 5.

4 / 5

Total

16

/

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

relative_links

Relative link issues: 1 suspicious

Warning

Total

15

/

16

Passed

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.