l-update-deps

Update a single dependency by reading its full changelog and assessing impact. Safe updates are applied directly, major updates are flagged for design review. Use when updating packages.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

77%Weight 40%Scale 1-3

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

The body is a well-sequenced, highly actionable dependency-update workflow with executable commands and real validation/feedback checkpoints. Its weaker points are token efficiency (a verbose illustrative block) and the absence of any progressive-disclosure structure — everything lives in one inline file.

Suggestions

Trim or collapse the large sample 'pnpm outdated' output block to a compact schema, keeping only enough to convey the grouping format.

Move the changelog-research detail (GitHub releases / CHANGELOG.md / git-commits sources) into a references file and link to it from SKILL.md to add one-level-deep progressive disclosure.

Replace the empty 'Find all imports/requires' bash block with a concrete Grep command (e.g. a ripgrep pattern for the package name) so the impact-assessment step is fully copy-paste ready.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean instruction with executable commands, but the large illustrative outdated-package listing and phrases like 'This distinction is critical for risk assessment' add padding that could be tightened, fitting the mostly-efficient-but-could-be-tighter anchor.	2 / 3
Actionability	Provides concrete, copy-paste-ready commands throughout — 'pnpm outdated -r --no-color', 'gh api repos/{owner}/{repo}/releases ...', 'pnpm update {package}@{version} -r', 'pnpm --filter=... test' — meeting the fully-executable anchor.	3 / 3
Workflow Clarity	A clearly sequenced 6-step process with explicit checkpoints ('If already up to date, say so and stop', 'Stop unless user wants to proceed') and a validate-then-fix test feedback loop ('If tests fail, investigate and fix'), matching the clear-sequence-with-validation anchor.	3 / 3
Progressive Disclosure	No bundle files exist and the skill is a single ~180-line monolithic document with all detail inline; it is well-sectioned but content like the example output and changelog-research detail could be split out, fitting the some-structure-but-could-be-better-organized anchor rather than the under-50-line simple-skill exemption.	2 / 3
	Total	10 / 12 Passed

Description

85%Weight 40%Scale 1-3

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 third-person, concrete, and explicitly pairs a what-statement with a 'Use when' trigger, giving it strong specificity and completeness. Its main weakness is trigger-term breadth — only 'updating packages' is offered, missing common phrasings like upgrade, bump, or outdated.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'reading its full changelog and assessing impact', 'Safe updates are applied directly', 'major updates are flagged for design review' — matching the multiple-specific-actions anchor.	3 / 3
Completeness	Explicitly answers both what (update a dependency via changelog review and impact assessment, apply safe, flag major) and when via the explicit 'Use when updating packages' clause, satisfying the both-what-and-when anchor.	3 / 3
Trigger Term Quality	Includes the relevant keyword 'updating packages' but omits common variations a user would naturally say ('upgrade', 'bump', 'outdated', 'dependency', 'version'), so it lands at 'some relevant keywords but missing common variations' rather than full coverage.	2 / 3
Distinctiveness Conflict Risk	The changelog-driven, impact-assessed dependency-update niche with major-update flagging is a clear, distinctive trigger set unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 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: lowdefy/lowdefy
Path: .claude/skills/l-update-deps/SKILL.md
Commit: d638cf7

Reviewed: 27 days 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.