CtrlK
BlogDocsLog inGet started
Tessl Logo

stitch-sdk-readme

Generate or update the README for the Stitch SDK. Use the Bookstore Test structure and source the current API from the codebase. Use when the README needs to be written or updated.

75

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

100%

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

The content is lean and directive, highly actionable with specific file paths and concrete examples, clearly sequenced with an explicit validation checklist, and well-organized as a self-contained single file. It does not pad with concepts Claude already knows and every section serves the README-generation task.

DimensionReasoningScore

Conciseness

The body is directive and assumes competence ('Do not hard-code the API surface', 'Show this as the first code block', 'No setup first') with no padding of basic concepts Claude already knows. The Bookstore Test metaphor is a load-bearing structuring device rather than decorative exposition, so tokens earn their place. Not a 2 because it lacks the editorializing filler of the anchor-2 example.

3 / 3

Actionability

Provides concrete, executable guidance: exact file paths ('packages/sdk/src/index.ts'), a sourcing table, a fixed class ordering, and specific snippets to show ('project(id) → generate → getHtml', 'npm install @google/stitch-sdk'). For an instruction-only generator skill this is copy-paste-ready direction. Not a 2 because guidance is complete and specific, not pseudocode or abstract.

3 / 3

Workflow Clarity

Clear sequence — source the API (table) → structure via Bookstore Test (Cover → Inner Flap → Reading the Book) → validate — with an explicit Validation checklist acting as verification checkpoints. README generation is not destructive/batch, so the missing-feedback-loop cap does not apply. Not a 2 because validation checkpoints are explicit, not implicit.

3 / 3

Progressive Disclosure

No bundle files are present and none are needed; the skill is a self-contained single file with well-organized sections (headings, tables, checklist) and no nested references. Per the simple-skill note, well-organized single-file content with no external-reference need scores 3. Not a 2 because it is cohesive and navigable rather than a monolithic wall or a split candidate with missing signals.

3 / 3

Total

12

/

12

Passed

Description

85%

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, complete with an explicit 'Use when' trigger, and tied to a distinct niche via the Stitch SDK and Bookstore Test. Its main weakness is narrow trigger-term coverage — it states one triggering condition rather than enumerating the natural phrasings a user would say.

Suggestions

Broaden the 'Use when' clause to enumerate natural user phrasings, e.g. 'Use when the user asks to write, update, or generate a README, document an SDK, or refresh stale docs for @google/stitch-sdk.'

Consider mentioning the key artifact terms users actually say ('README', 'docs', 'documentation') together in the trigger to improve natural-keyword coverage.

DimensionReasoningScore

Specificity

Quotes 'Generate or update the README', 'Use the Bookstore Test structure', and 'source the current API from the codebase' — three concrete actions, matching the anchor for listing multiple specific actions. Not a 2 because it goes beyond naming a domain to enumerating concrete operations.

3 / 3

Completeness

Explicitly states what ('Generate or update the README for the Stitch SDK') and when ('Use when the README needs to be written or updated'), matching the anchor for clearly answering both with an explicit 'Use when' clause. Not a 2 because the 'Use when' trigger is present, not implied.

3 / 3

Trigger Term Quality

The only trigger phrase is 'Use when the README needs to be written or updated' — a single condition missing common natural variations a user would say (e.g. 'docs', 'document my SDK', 'write a readme'). Not a 3 because keyword coverage is narrow, not a 1 because 'README' is a genuine natural term.

2 / 3

Distinctiveness Conflict Risk

Tied to a specific product ('Stitch SDK') and a named strategy ('Bookstore Test'), giving it a clear niche unlikely to trigger for unrelated skills. Not a 2 because the SDK-specific framing and distinct structural marker narrow the conflict surface.

3 / 3

Total

11

/

12

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
google-labs-code/stitch-sdk
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.