CtrlK
BlogDocsLog inGet started
Tessl Logo

1k-pkg-upgrade-review

Reviews package version upgrades — diffs source between versions, traces call sites, and generates compatibility reports.

64

Quality

77%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.skillshare/skills/1k-pkg-upgrade-review/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

87%

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

The content is concise, highly actionable, and well-structured with properly signaled one-level references, but it pushes the validation/feedback-loop detail into a referenced file rather than surfacing the key checkpoints inline for the outward-facing PR-comment step.

Suggestions

Add an inline validation checkpoint before the 'Post report' step (e.g. verify the local report file exists and the diff was non-empty before running gh pr comment) to support a feedback loop.

Surface a brief 'if no call sites found / if diff is metadata-only, report accordingly' decision step inline so error recovery is visible without opening the reference.

DimensionReasoningScore

Conciseness

The body is lean and well-sectioned — it jumps straight into workflow, commands, and output without explaining concepts Claude already knows, so every token earns its place.

3 / 3

Actionability

Provides fully executable, copy-paste-ready commands (curl|tar for download, diff -rq, grep with include/exclude flags, npm view, gh pr comment) plus concrete output paths, matching the high anchor.

3 / 3

Workflow Clarity

The 10-step workflow is clearly sequenced, but explicit validation checkpoints and a validate→fix→retry feedback loop are not present in the body (they live in the referenced review-workflow.md); for an outward-facing operation like posting a PR comment this caps clarity at 2.

2 / 3

Progressive Disclosure

A clear overview with a Quick Reference table signals one-level-deep references to review-workflow.md, report-template.md, and example-report.md — all verified to exist as real files — and detailed content is appropriately split out.

3 / 3

Total

11

/

12

Passed

Description

67%

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, third-person, and clearly scoped to package upgrade review, but it lacks an explicit 'Use when...' trigger clause and the natural user-facing keywords that would surface it at the right moment.

Suggestions

Append an explicit trigger clause such as 'Use when reviewing Dependabot/Renovate PRs or changes to yarn.lock/package-lock.json' to lift completeness to 3.

Add natural user vocabulary (Dependabot, Renovate, lockfile bump, dependency upgrade) alongside the technical terms to improve trigger term quality.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'diffs source between versions', 'traces call sites', and 'generates compatibility reports' — matching the rubric's high anchor for listing several specific concrete actions.

3 / 3

Completeness

Clearly answers 'what' but contains no 'Use when...' clause or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 2.

2 / 3

Trigger Term Quality

Uses technical terms ('package version upgrades', 'compatibility reports') but omits the natural phrasings users actually say (Dependabot, Renovate, yarn.lock bump, npm update), so coverage is partial rather than comprehensive.

2 / 3

Distinctiveness Conflict Risk

'Reviews package version upgrades' carves out a clear niche unlikely to overlap with general code-review skills, and the scoped actions make accidental triggering unlikely.

3 / 3

Total

10

/

12

Passed

Validation

81%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

relative_links

Relative link issues: 2 deeper-than-1-level

Warning

referenced_paths_exist

Referenced path issues: 2 deeper-than-1-level

Warning

Total

13

/

16

Passed

Repository
OneKeyHQ/app-monorepo
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.