Tessl • The package manager for agent skills

SkillPublic

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.

Quality

73%

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 ./.apm/skills/devx-ux/SKILL.md

Quality

Content

78%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 crisp, token-efficient policy skill with genuinely actionable UX rules and a clean two-section structure. Its main defects are the missing persona file behind its only reference link and the absence of any worked example or verification step showing the rules applied.

Suggestions

Fix or inline the broken reference ../../agents/devx-ux-expert.agent.md — the linked file does not exist, so the persona content is unreachable.

Add one compact before/after example per rule family (e.g., a rewritten error message showing failure, cause, and one next action) to lift actionability to fully executable.

Add a brief verification step, such as re-checking `--help` output and each user-facing error after changes, to close the workflow_clarity gap.

Dimension	Reasoning	Score
Conciseness	At ~30 lines the body is lean with zero padding: every line is either an activation trigger or a rule ("Default output is for humans; `--verbose` is for agents"), and it explains nothing Claude would already know.	5 / 5
Actionability	The key rules are concrete and checkable ("Compare every flow against `npm` / `pip` / `cargo` / `gh` mental models -- justify any deviation", "Every error names the failure, the cause, and one next action"), but no examples — such as a before/after error message or a help-text snippet — are given, leaving minor gaps below the fully executable anchor 5.	4 / 5
Workflow Clarity	As a simple single-purpose policy skill under 50 lines, the activation list and rule set are unambiguous and well-organized, qualifying for the simple-skill exception; however there is no sequencing or verification checkpoint (e.g., how to confirm help output or error wording after a change), so it sits at anchor 4 rather than 5.	4 / 5
Progressive Disclosure	Sections are well-organized and the body is appropriately short, but the skill's only outbound reference — [Developer Tooling UX expert persona](../../agents/devx-ux-expert.agent.md) — does not exist in the bundle, so the clearly signaled link is dangling and navigation fails.	3 / 5
	Total	16 / 20 Passed

Description

56%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 trigger-side description that is unusually explicit about when to activate (including the case where the user doesn't say "UX"), but it completely omits the capability statement — a reader cannot tell what the skill does once activated. Scoping to the APM CLI makes conflict risk minimal.

Suggestions

Add a 'what' clause before the trigger, e.g. "Reviews and improves CLI command surfaces, help text, and error wording against expert UX standards for the APM CLI. Activate when..."

Include natural trigger synonyms users would actually say: "flags", "subcommands", "arguments", "error messages", and "command UX".

State the outcome the skill produces (e.g., applying the npm/pip/cargo mental-model rules and the failure/cause/next-action error format) so the description answers both what and when.

Dimension	Reasoning	Score
Specificity	The description names the domain and concrete trigger surfaces ("CLI command surfaces", "command help text", "install/init/run flows", "error wording", "first-run experience") but lists no capability actions — it never states what the skill actually does, matching anchor 3 rather than 4.	3 / 5
Completeness	It has an explicit and specific 'when' ("Activate when designing or modifying CLI command surfaces...") but the 'what' is entirely absent — no statement of what the skill does or provides — matching anchor 2 ('only when is present without what') rather than 3 where the what is present but weak.	2 / 5
Trigger Term Quality	Good natural keyword coverage ("command help text", "error wording", "first-run experience", "install/init/run flows") with explicit anticipation of users who don't say "UX"; a few common synonyms like "flags", "subcommands", and "error messages" are missing, keeping it below anchor 5.	4 / 5
Distinctiveness Conflict Risk	The description is scoped to a specific tool ("the APM CLI") and to concrete UX surfaces, giving it a clear niche with distinct triggers and minimal overlap risk with neighboring skills.	5 / 5
	Total	14 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 1 suspicious	Warning

	Total	15 / 16 Passed

Repository: microsoft/apm
Path: .apm/skills/devx-ux/SKILL.md
Revision: 0495ced

Reviewed: 24 days ago

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.

devx-ux

Table of Contents

Is this your skill?