CtrlK
BlogDocsLog inGet started
Tessl Logo

up-to-date

Use when writing, editing, or refactoring code that calls any third-party SDK, API, or library; installing or importing external packages; debugging when an API call returns success but the expected side-effect doesn't happen; hitting 4xx errors from an external API; or when something 'doesn't work' and the code involves an external service.

60

Quality

70%

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 ./SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

77%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 a well-structured, validated workflow with strong progressive disclosure and concrete tooling, but it repeats its own key points across several sections and leaves the doc-fetching step at a high level.

Suggestions

Consolidate the overlapping 'Common Failure Patterns' and 'Anti-Patterns' tables — the '200 OK' and 'don't write from memory' points each recur 3-4 times across sections.

Make Step 2 (Fetch Real Docs) executable: show the exact Context7/WebFetch invocation syntax rather than a one-line flow description.

Trim 'When This Triggers' to only the subcategories not already covered by the frontmatter description to remove the duplication.

DimensionReasoningScore

Conciseness

The body is instruction-focused and does not explain basics Claude already knows, but core points repeat across sections — the '200 OK' / 'trusting a 200' concept and 'don't write from memory' each appear 3-4 times in the rule, failure-patterns table, anti-patterns table, and after-changes step, and 'When This Triggers' reiterates the frontmatter description.

3 / 5

Actionability

Step 1 and the bundled script give copy-paste-ready bash commands and concrete examples, but Step 2 (Fetch Real Docs) stays abstract ('resolve-library-id → query-docs', 'Fetch the official API reference page') without executable invocation syntax, so it is mostly rather than fully executable.

4 / 5

Workflow Clarity

A clear four-step Mandatory Steps sequence with explicit validation checkpoints ('If 1+ major versions behind, read the changelog/migration guide', 'Build to verify types', 'Test live and verify the actual downstream effect') plus a decision flowchart that provides feedback loops and an upfront confirm-checklist.

5 / 5

Progressive Disclosure

Well-organized sections with two clearly-signaled, one-level-deep bundle resources — scripts/check_versions.py and references/doc-urls.md — each described with usage; the bulky doc-URL table and version checker are appropriately split out rather than inlined.

5 / 5

Total

17

/

20

Passed

Description

62%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.

The description has strong, concrete trigger coverage and a clear "Use when" clause, but it never states what the skill does, leaving the capability implicit and slightly blurring its distinctiveness.

Suggestions

State what the skill does (e.g., 'Fetches current SDK/API documentation and verifies code against it before writing or debugging') before the 'Use when' clause so the description answers 'what' as well as 'when'.

Sharpen distinctiveness by leading with the unique angle — keeping external-service code current against real docs — rather than the broad 'writing/editing/refactoring code that calls any third-party library' trigger.

Add natural synonyms like 'outdated dependency', 'deprecated API', or 'version mismatch' to broaden trigger-term coverage.

DimensionReasoningScore

Specificity

Names the domain ("third-party SDK, API, or library") and several concrete scenarios ("writing, editing, or refactoring", "installing or importing", "debugging", "hitting 4xx errors"); not quite a 5 because the listed items are trigger contexts rather than a comprehensive statement of the skill's own actions.

4 / 5

Completeness

The "Use when..." clause gives an exceptionally explicit "when", but no "what" is stated — the skill's actual capability is only inferable from the name "up-to-date", and the rubric says to score only what is explicit, not inferred.

3 / 5

Trigger Term Quality

Includes natural phrases users actually say ("something 'doesn't work'", "4xx errors", "installing", "importing external packages"); good coverage but a few obvious synonyms (outdated dependency, deprecated API, version mismatch) are missing.

4 / 5

Distinctiveness Conflict Risk

The external-service focus is a recognizable niche, but the lead trigger "writing, editing, or refactoring code that calls any third-party SDK, API, or library" is broad and the description does not convey the skill's distinctive freshness/docs-verification angle, so overlap with general coding skills remains.

3 / 5

Total

14

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
LeonMelamud/up-to-date-skill
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.