Name: squad-version-check
Rating: 50.4 (1 reviews)
Author: bradygaster

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

55%

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

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable with concrete commands, code, and exact paths, and is tightly written. Its main gaps are time-sensitive specifics that aren't segregated into a deprecated section, missing validation feedback loops around the destructive upgrade overwrite, and inline reference density that would benefit from external reference files.

Suggestions

Add a validation/recovery checkpoint around `squad upgrade`'s full overwrite of `squad.agent.md` (e.g. back up the existing file before overwrite, then verify the stamped version reads back correctly via `readInstalledVersion`).

Move time-sensitive specifics (version numbers like '0.9.6-insider.2', the 2026-05-26 date) into an explicit 'Version-specific notes / old patterns' section so the core guidance stays durable.

Split the dense reference material (cache schemas, the OS-cache one-liner, the full file-path table) into a `references/` file and link to it one level deep to improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence with no padding, but it embeds time-sensitive specifics (version '0.9.6-insider.2', date '2026-05-26', pre-release comparisons) that the rubric penalizes unless housed in a deprecated/old-patterns section.	2 / 3
Actionability	Provides copy-paste-ready, executable guidance: an `npm view ... dist-tags --json` one-liner, a full `node -e` cache-reader, concrete stamp/regex patterns, and exact file paths — fully actionable rather than abstract.	3 / 3
Workflow Clarity	Steps are clearly sequenced per topic (stamp, read, upgrade, probe), and the probe has explicit error-handling branches, but there is no validate→fix→retry feedback loop for destructive/overwrite operations like the full `squad.agent.md` overwrite, capping workflow clarity at 2.	2 / 3
Progressive Disclosure	The ~155-line single-file body is well-organized into headed sections, but with no references/scripts/assets bundle present, dense reference material (cache schemas, semver internals, full file-path tables) that would benefit from a one-level-deep split is kept inline.	2 / 3
	Total	9 / 12 Passed

Description

45%

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 third-person with concrete named actions, but it omits any explicit trigger guidance and uses internal jargon over natural user-facing keywords. Adding a 'Use when...' clause with natural terms would raise both completeness and trigger quality.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the user asks how squad-cli stamps or checks its version, runs `squad upgrade`, or needs to probe the npm registry for the latest @bradygaster/squad-cli release.'

Replace internal jargon like 'coordinator prompt' and 'stamps its version' with natural phrases users would actually say, such as 'check the squad version' or 'upgrade the squad CLI'.

Lead with the user-facing capability (version checking / upgrading squad-cli) before the internal-mechanics framing to improve distinctiveness.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions: "stamps its version", "how `squad upgrade` works (what it preserves vs overwrites)", and "probe the npm registry for the latest version" — three distinct specific behaviors rather than vague language.	3 / 3
Completeness	The "what" is covered concretely, but there is no "Use when..." clause or equivalent trigger guidance, so the "when" is only implied — capping completeness at 2 per the rubric guideline.	2 / 3
Trigger Term Quality	Terms lean on internal jargon ("coordinator prompt", "stamps its version", "version-stamping") rather than natural phrases a user would say; no user-facing trigger keywords like "upgrade squad", "check squad version", or "squad-cli" variations.	1 / 3
Distinctiveness Conflict Risk	The niche (squad-cli internals) is fairly distinct once read, but the phrasing could overlap with generic CLI/version skills and lacks explicit triggers that would reliably route the right skill.	2 / 3
	Total	8 / 12 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: bradygaster/squad
Path: .squad/skills/squad-version-check/SKILL.md
Commit: e23dd92

Reviewed: 1 day ago

Table of Contents

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.