CtrlK
BlogDocsLog inGet started
Tessl Logo

anthropic-sdk-upgrader

Use this agent when the user needs to upgrade Anthropic SDK packages. This includes: upgrading @anthropic-ai/sdk or @anthropic-ai/claude-agent-sdk to newer versions, migrating between SDK versions, resolving SDK-related dependency conflicts, updating SDK types and interfaces, or asking about SDK upgrade procedures. Examples: 'Upgrade the Anthropic SDK to the latest version', 'Help me migrate to the latest claude-agent-sdk', 'What's the process for upgrading Anthropic packages?'

72

Quality

90%

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

SKILL.md
Quality
Evals
Security

Quality

Content

88%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.

A highly actionable, well-sequenced upgrade workflow with executable commands, validation checkpoints, and a concrete commit template. Minor gains available from trimming explanatory prose and splitting long sections into reference files.

Suggestions

Tighten the explanatory bullet lists under steps 2-3 (e.g., 'Look for: Removed or renamed exports / Changed function signatures') into shorter cues, since Claude can infer these from a diff.

Consider moving the detailed type-diff bash block (step 5) and/or the Troubleshooting section into a reference file, keeping SKILL.md as a lean overview with a one-level-deep pointer.

Add a brief validation note at the end of step 4 (after npm install) confirming the install succeeded before proceeding to the diff step.

DimensionReasoningScore

Conciseness

Mostly efficient with concrete commands, file paths, and a commit template that earn their tokens, but several explanatory prose lists (e.g., 'Look for: Removed or renamed exports...') could be trimmed; above the midpoint but not fully lean.

4 / 5

Actionability

Fully executable guidance throughout — copy-paste npm install/compile/test commands, a runnable type-diff bash loop, specific file paths to fix, and a complete example commit message covering the common cases.

5 / 5

Workflow Clarity

Nine clearly sequenced steps with explicit validation checkpoints (npm run compile for type errors, run tests and fix failures before proceeding) and an emphasized ordering constraint (snapshot before install); feedback loops are present.

5 / 5

Progressive Disclosure

Well-organized into clear sections with no nested or buried references (no bundle files exist), but the body is fairly long and monolithic — the type-diffing detail or troubleshooting could be split into reference files.

4 / 5

Total

18

/

20

Passed

Description

92%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 strong, specific description that clearly defines a narrow niche with concrete actions and explicit use-when guidance plus example trigger phrases. Only minor room to add a couple more natural synonym terms.

DimensionReasoningScore

Specificity

Lists multiple concrete actions (upgrading to newer versions, migrating between SDK versions, resolving dependency conflicts, updating types/interfaces, asking about procedures) across two named packages — comprehensive coverage matching the 5 anchor.

5 / 5

Completeness

Explicitly answers both 'what' (upgrade Anthropic SDK packages with enumerated sub-actions) and 'when' ('Use this agent when the user needs to upgrade...') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Includes natural user phrases via the Examples ('Upgrade the Anthropic SDK to the latest version', 'Help me migrate...', 'What's the process for upgrading...') and named packages, but a few natural variants like 'update' are only implied rather than explicit.

4 / 5

Distinctiveness Conflict Risk

A clear niche (Anthropic SDK packages, two specific named packages) with distinct triggers unlikely to fire for unrelated skills.

5 / 5

Total

19

/

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.

Validation15 / 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
posit-dev/positron
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.