CtrlK
BlogDocsLog inGet started
Tessl Logo

testland/graphql-schema-regression

Diffs two GraphQL schemas with `graphql-inspector diff`, classifies each change as BREAKING / DANGEROUS / NON_BREAKING, and applies opt-in rules (suppress-removal-of-deprecated-field, consider-usage, ignore-description-changes) to gate CI on schema regressions. Use when reviewing GraphQL schema changes in a PR or evaluating Federation supergraph drift.

77

Quality

97%

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

Overview
Quality
Evals
Security
Files

Quality

Content

92%

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

The body is concise, highly actionable, and presents well-sequenced workflows with explicit gating and verification checkpoints. Its only weakness is progressive disclosure: everything lives inline in one longer file with no bundle-file split for the denser reference material.

Suggestions

Move the full GitHub Actions workflow YAML and the per-subgraph Federation loop into a dedicated reference file (e.g. references/ci-integration.md), keeping SKILL.md as an overview that links to it, so the denser material is one level deep rather than inline.

Extract the rules table (dangerousBreaking, suppressRemovalOfDeprecatedField, ignoreDescriptionChanges, safeUnreachable, considerUsage) plus the custom-rule module example into a references/rules.md file, with SKILL.md summarizing the canonical two rules inline and pointing to the rest.

List the bundle files you create in a References section with clear one-level-deep links (e.g. 'CI integration: see ci-integration.md'), signaling the split explicitly to aid navigation.

DimensionReasoningScore

Conciseness

The body is lean and table-driven (classification and rules tables), assumes GraphQL/CI competence without explaining basics, and uses compact prose; it earns its tokens rather than padding, matching the 'lean and efficient' anchor over the 'mostly efficient but could be tightened' level 2.

3 / 3

Actionability

Provides fully executable, copy-paste-ready guidance — `npm install`/`npx` commands, `graphql-inspector diff`/`introspect` invocations, a complete GitHub Actions YAML, and `--rule` flag examples — satisfying the 'fully executable code/commands' anchor rather than the pseudocode/incomplete level 2.

3 / 3

Workflow Clarity

The CI workflow is explicitly sequenced (checkout with fetch-depth 0, setup-node, extract base via `git merge-base`, diff) with the exit-code gate stated as the validation checkpoint, and the Federation batch loop is paired with `rover supergraph compose` verification; this meets the 'clear sequence with explicit validation steps' anchor rather than the implicit-checkpoint level 2.

3 / 3

Progressive Disclosure

Sections are well-organized and the external doc links ([gqi-overview], [gqi-diff]) are clearly signaled one level deep, but the ~190-line body keeps all detail inline (full CI YAML, rules table, Federation loop) with no split into bundle files; this fits 'content that should be separate is inline' (level 2) rather than the 'content appropriately split' level 3.

2 / 3

Total

11

/

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.

The description is specific, action-oriented, and includes an explicit 'Use when' trigger with natural keywords, cleanly answering both what the skill does and when to use it. It occupies a distinct niche with low conflict risk.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — diffs schemas with `graphql-inspector diff`, classifies changes into BREAKING/DANGEROUS/NON_BREAKING, and applies named opt-in rules (suppress-removal-of-deprecated-field, consider-usage, ignore-description-changes) to gate CI — matching the 'lists multiple specific concrete actions' anchor rather than the 'names domain and some actions' level 2.

3 / 3

Completeness

Explicitly states what it does (diff/classify/apply-rules/gate-CI) and when to use it via an explicit 'Use when...' trigger, satisfying the 'clearly answers both what AND when' anchor; not level 2 because the when is explicit, not implied.

3 / 3

Trigger Term Quality

The 'Use when reviewing GraphQL schema changes in a PR or evaluating Federation supergraph drift' clause uses natural terms a user would actually say when reviewing schema PRs, meeting the 'good coverage of natural terms' anchor rather than missing common variations.

3 / 3

Distinctiveness Conflict Risk

It carves a clear GraphQL schema-regression gating niche with distinct triggers (GraphQL schema changes, Federation supergraph drift), unlikely to fire for the wrong skill; not level 2 because the scope is sharply specific rather than broadly overlapping.

3 / 3

Total

12

/

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.

Reviewed

Table of Contents