CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

squad-version-check

Internals of how @bradygaster/squad-cli stamps its version, how `squad upgrade` works (what it preserves vs overwrites), and how to probe the npm registry for the latest version from a coordinator prompt.

Quality

80%

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 ./.github/skills/squad-version-check/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

82%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 exemplar of dense, actionable reference knowledge — copy-paste commands, exact paths, and precise behavioral facts with zero padding. Its main weaknesses are inline time-sensitive version/date details and the absence of any progressive-disclosure structure to move lengthy cache-reading details out of the main file.

Suggestions

Move time-sensitive details (validation dates, example version numbers like '0.9.6-insider.2') into a clearly labeled versioned or deprecated section so they don't read as evergreen facts.

Extract the OS-specific cache paths and the long node -e one-liner into a references/ file (e.g., cache-probe.md) and link to it from a short section, tightening the main file.

Make the version-check decision flow an explicit numbered sequence (probe → timeout check → extract or fallback) so the workflow reads as a checklist rather than prose bullets.

DimensionReasoningScore

Conciseness

The body is dense and factual with no concept explanations Claude already knows — regexes, semver edge cases, and paths are stated bare. However, time-sensitive details (dates like 2026-05-26 and version numbers such as '0.9.6-insider.2') appear inline rather than in a deprecated/old-patterns section, which the guidelines say should penalize conciseness, keeping this below anchor 5.

4 / 5

Actionability

Guidance is fully executable and copy-paste ready: 'npm view @bradygaster/squad-cli dist-tags --json', a complete node -e one-liner for reading the update cache, per-package-manager self-upgrade commands, and exact regexes for version stamping — matching the 'copy-paste ready' anchor 5.

5 / 5

Workflow Clarity

The version-check probe section lays out a clear sequence with an explicit timeout ('Timeout: 5 seconds'), a success path ('extract dist-tags[channel]'), and error fallback ('On any error ... show normal greeting'). Most checkpoints are present, but the upgrade and cache sections are reference material without explicit sequencing, so this sits at anchor 4 rather than 5.

4 / 5

Progressive Disclosure

Sections are well-organized with clear headers and a key-file-paths table, and no bundle files are referenced (none exist). At ~160 lines it exceeds the under-50-line simple-skill exception, and some content (e.g., the OS-specific cache paths and the long node one-liner) could live in a separate reference file, so anchor 4 fits better than 5.

4 / 5

Total

17

/

20

Passed

Description

70%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, distinctive description that clearly conveys what the skill covers, but it entirely lacks a 'when to use' trigger clause, which caps its completeness. Adding an explicit 'Use when...' sentence with natural trigger phrases would lift the two weakest dimensions (completeness and trigger coverage).

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks about squad-cli versions, upgrading squad, or checking for a newer squad release.'

Include natural trigger variations such as 'squad update', 'latest version', and 'insider build' to broaden keyword coverage.

State the outcome the skill enables (e.g., deciding whether an upgrade prompt should be shown) so the 'what' answers what acting on this knowledge achieves.

DimensionReasoningScore

Specificity

The description names three concrete capability areas — 'stamps its version', 'how `squad upgrade` works (what it preserves vs overwrites)', and 'probe the npm registry for the latest version' — with only minor gaps (e.g., cache reading is unmentioned), matching the 'several specific actions; minor gaps' anchor rather than the comprehensive anchor 5.

4 / 5

Completeness

The 'what' is clearly and concretely stated, but there is no 'Use when...' clause or equivalent trigger guidance anywhere in the description; per the judging guidelines a missing explicit trigger clause caps completeness at 3.

3 / 5

Trigger Term Quality

Natural terms like 'squad upgrade', 'version', 'npm registry', and the package name '@bradygaster/squad-cli' give good keyword coverage a user would plausibly say, though common variations like 'update', 'latest', or 'insider' are missing — good but not comprehensive, so anchor 4 rather than 5.

4 / 5

Distinctiveness Conflict Risk

The description is pinned to a single niche package ('@bradygaster/squad-cli') with distinct triggers around version stamping and upgrades, giving it a clear niche with minimal conflict risk against other skills.

5 / 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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

microsoft/waza

Path

.github/skills/squad-version-check/SKILL.md

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.