CtrlK
BlogDocsLog inGet started
Tessl Logo

cli-logging-ux

Use this skill when editing or creating CLI output, logging, warnings, error messages, progress indicators, or diagnostic summaries in the APM codebase. Activate whenever code touches console helpers (_rich_success, _rich_warning, _rich_error, _rich_info, _rich_echo), DiagnosticCollector, STATUS_SYMBOLS, CommandLogger, or any user-facing terminal output — even if the user doesn't mention "logging" or "UX" explicitly.

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 ./.agents/skills/cli-logging-ux/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

65%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.

Highly actionable and codebase-specific with strong concrete examples, but held back by rules/anti-patterns redundancy, absent validation feedback loops for batch operations, and a monolithic structure with a broken external reference. The reference architecture is thorough but lives entirely in one file.

Suggestions

Collapse the Anti-patterns section into a short 'common mistakes' checklist that cross-references the rules above, rather than re-stating each rule in full, to cut redundant tokens.

Add an explicit validate-then-fix feedback loop for batch/multi-package operations (e.g. collect diagnostics -> check counts -> re-run with --force guidance) so workflow clarity clears the batch cap.

Move the CommandLogger/InstallLogger method tables into a references/COMMAND_LOGGER_API.md file and link to it from the body, and fix or remove the broken persona link at the top of the file.

DimensionReasoningScore

Conciseness

Mostly efficient and free of generic concept padding, but the 12-item Anti-patterns section largely restates rules already given in the Decision framework and Console helper sections, which is more than minor over-explanation.

3 / 5

Actionability

Provides copy-paste-ready Python imports, exact method signatures (e.g. download_complete(name, ref=, sha=, cached=)), concrete file paths, and a worked Click command example covering the common cases.

5 / 5

Workflow Clarity

A clear logger lifecycle (start -> do work -> render_summary) and collect-then-render pattern are present, but there are no explicit validation/error-recovery feedback loops, and the batch-operation context (multi-package loops) triggers the cap at 3.

3 / 5

Progressive Disclosure

Section headers give good in-file structure, but the large CommandLogger/InstallLogger method API tables are inlined rather than split into a reference file, and the sole external reference (the persona link at the top) points to a non-existent file.

3 / 5

Total

14

/

20

Passed

Description

87%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, specific description that clearly answers both what the skill does and when to activate it, anchored to concrete codebase symbols. The only gap is slightly limited action-verb variety and missing synonyms/extensions, which keeps specificity and trigger quality at 4 rather than 5.

DimensionReasoningScore

Specificity

Lists several concrete targets (console helpers, DiagnosticCollector, STATUS_SYMBOLS, CommandLogger) applied across six output types, but the action verbs themselves are limited to 'editing or creating', so it is above the 1-2-action anchor yet short of fully comprehensive multi-action coverage.

4 / 5

Completeness

Explicitly states what the skill does ('editing or creating CLI output, logging, warnings...') and when to use it ('Use this skill when...', 'Activate whenever code touches...') with concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

Includes natural user-facing terms like 'CLI output', 'logging', 'warnings', 'error messages', 'progress indicators', and explicitly notes users may not say 'logging' or 'UX', but it lacks synonyms and file extensions that would make coverage exhaustive.

4 / 5

Distinctiveness Conflict Risk

Tied to a specific codebase (APM) and named internal artifacts (_rich_* helpers, DiagnosticCollector, CommandLogger), giving it a clear niche with minimal overlap risk.

5 / 5

Total

18

/

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.