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

88%

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

77%

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 runbook with concrete commands, project-specific file paths, and validation feedback loops. Its weaknesses are moderate verbosity in the example/template sections and a monolithic inline structure with no progressive disclosure via reference files.

Suggestions

Tighten the example commit message (step 9) and the step-5 diff-report category descriptions to reduce token overhead without losing the template value.

Move the troubleshooting section and the full example commit message into a reference file (e.g. references/TROUBLESHOOTING.md) and link to it from SKILL.md so the main file stays a lean overview with one-level-deep references.

Consider extracting the step-5 type-diff procedure into a scripts/ helper or references/ doc, keeping SKILL.md focused on the high-level 9-step flow.

DimensionReasoningScore

Conciseness

Mostly efficient and project-specific, but the lengthy example commit message (lines 207-233) and the verbose diff-report category descriptions in step 5 could be tightened; it does not pad with concepts Claude already knows, so it stays above 1.

2 / 3

Actionability

Provides fully executable bash commands (npm install, .d.ts diff loop, npm run compile, test:unit) and names specific project files to fix, making guidance copy-paste ready.

3 / 3

Workflow Clarity

A clearly sequenced 9-step process with explicit validation checkpoints (compile check in step 6, test run with 'Fix any test failures before proceeding' in step 7) and a snapshot-before-install guard in step 5.

3 / 3

Progressive Disclosure

Well-organized into headed sections rather than a wall of text, but no bundle/reference files exist and the ~250-line body is entirely inline; the long commit-message example and troubleshooting section could be split into reference files. Not score 1 because sections are clear and navigation is easy; not score 3 because there is no one-level-deep reference structure.

2 / 3

Total

10

/

12

Passed

Description

100%

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 description: concrete actions, natural trigger phrasings with example user quotes, explicit what-and-when guidance, and a distinct niche. Third-person/agent voice is maintained and it avoids vague fluff.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — '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' — rather than vague language.

3 / 3

Completeness

Explicitly answers both what (upgrade/migrate/resolve conflicts/update types) and when via 'Use this agent when the user needs to upgrade Anthropic SDK packages' plus concrete example triggers.

3 / 3

Trigger Term Quality

Includes natural user phrasings as 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?') covering common variations users would actually say.

3 / 3

Distinctiveness Conflict Risk

Targets a clear niche — Anthropic SDK package upgrades specifically — with distinct triggers unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

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.