ci-schema-invariant-gate

Ensures correct execution order of migrations, seeders, and tests in CI

Quality

64%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/ci-schema-invariant-gate/SKILL.md

Quality

Content

72%

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

The content is concise and well-organized for a simple skill, but its workflow lacks the validation/feedback checkpoint expected for destructive database operations, capping workflow clarity and actionability at 2.

Suggestions

Add an explicit validation step after migrate:fresh --seed (e.g., confirm migrations applied cleanly) and a feedback loop ('if migration or seed fails, stop and defer to data-layer-contracts') before running tests.

Replace assertions like 'No cached or partial state is allowed' with concrete enforceable guidance, such as a command to clear cached state or a precondition check.

Clarify how CI should detect and report which stage failed (migration vs seed vs test) rather than stating it 'does NOT interpret or classify failures' without an actionable handoff.

Dimension	Reasoning	Score
Conciseness	The body is lean and direct with no concept-padding; every line states a concrete constraint or command, matching the 'lean and efficient; every token earns its place' anchor.	3 / 3
Actionability	Provides two concrete executable commands but pairs them with non-instructive assertions ('No deviations allowed', 'No cached or partial state is allowed') and omits verification details, fitting 'some concrete guidance but incomplete'.	2 / 3
Workflow Clarity	A strict sequence is given (migrate:fresh --seed then test), but migrate:fresh is destructive and no validation/feedback checkpoint is provided, which the scoring notes cap at 2 for destructive DB operations.	2 / 3
Progressive Disclosure	Under 50 lines with no need for external references and well-organized sections (Purpose, Execution Order, Responsibility, Failure Behavior, Determinism, Core Principle), which the simple-skills note allows to score 3.	3 / 3
	Total	10 / 12 Passed

Description

57%

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 and distinctive about CI execution ordering but lacks an explicit 'when to use' trigger clause and broader trigger-term coverage, capping completeness and trigger quality at 2.

Suggestions

Add an explicit 'Use when...' clause stating when Claude should invoke this skill (e.g., 'Use when setting up or debugging CI pipeline order for migrations, seeders, and tests').

Expand trigger terms with natural variations users would say, such as 'CI pipeline', 'test suite order', 'seed before tests', or 'fresh database in CI'.

List multiple concrete actions instead of a single verb, e.g., 'Sequences migrations, seeders, and test runs in CI; enforces a fresh-seeded database before tests'.

Dimension	Reasoning	Score
Specificity	Names the CI domain and concrete items (migrations, seeders, tests) but uses a single action verb ('Ensures correct execution order') rather than listing multiple distinct actions, matching the 'names domain and some actions' anchor.	2 / 3
Completeness	Answers 'what' (ensures execution order) but provides no explicit 'Use when...' trigger, which the guidelines cap at 2 for missing when-guidance.	2 / 3
Trigger Term Quality	Includes relevant natural terms ('migrations, seeders, and tests in CI') a user might say, but lacks common variations and explicit trigger phrasing, fitting the 'some relevant keywords but missing common variations' anchor.	2 / 3
Distinctiveness Conflict Risk	Targets a narrow CI execution-ordering niche with specific triggers (migrations, seeders, tests) unlikely to fire for unrelated skills, matching the 'clear niche with distinct triggers' anchor.	3 / 3
	Total	9 / 12 Passed

Validation

100%

Warnings & errors only

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: Bottelet/DaybydayCRM
Path: .claude/skills/ci-schema-invariant-gate/SKILL.md
Commit: fb83b36

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.