trellis-check

Comprehensive quality verification: spec compliance, lint, type-check, tests, cross-layer data flow, code reuse, and consistency checks. Use when code is written and needs quality verification, before committing changes, or to catch context drift during long sessions.

Quality

90%

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

Quality

Content

92%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.

Well-structured, lean, action-oriented quality checklist with clear sequencing and feedback loops. Only minor gap is the generic Step 3 command placeholder.

Suggestions

In Step 3, replace the generic instruction with a concrete example command for running lint/type-check/tests, or point to where the project's command set is defined.

Optionally note how to discover the project's actual lint/test commands if they vary, so Claude does not guess.

Dimension	Reasoning	Score
Conciseness	Lean and checklist-driven with no padding; assumes Claude's competence and avoids explaining concepts Claude already knows.	5 / 5
Actionability	Concrete executable commands (git diff, get_context.py, grep) plus specific checklists, but Step 3's 'Run the project's lint, type-check, and test commands' is left generic rather than giving the specific command(s).	4 / 5
Workflow Clarity	Clearly sequenced six-step flow with explicit feedback loops (fix then re-run project checks; stop-vs-fix decision rules in Step 6) covering a destructive-adjacent verification task.	5 / 5
Progressive Disclosure	Single-level overview well-organized into labeled steps pointing to external spec files at .trellis/spec/<package>/<layer>/index.md; no nesting and references are clearly signaled.	5 / 5
	Total	19 / 20 Passed

Description

88%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.

Strong, concrete description with explicit trigger guidance and a clear niche. Trigger-term coverage is good but could add a few more natural user phrases.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions (spec compliance, lint, type-check, tests, cross-layer data flow, code reuse, consistency checks) with comprehensive coverage.	5 / 5
Completeness	Explicitly answers both what (enumerated verification categories) and when ('Use when code is written and needs quality verification, before committing changes...').	5 / 5
Trigger Term Quality	Natural triggers present ('before committing changes', 'catch context drift during long sessions') but missing common synonyms a user would naturally say like 'quality check', 'verify my code', or 'pre-commit'.	4 / 5
Distinctiveness Conflict Risk	The Trellis-specific workflow and cross-layer/data-flow framing carves a clear niche distinct from generic lint/test skills with minimal conflict risk.	5 / 5
	Total	19 / 20 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: mindfold-ai/Trellis
Path: .agents/skills/trellis-check/SKILL.md
Commit: 88f4834

Reviewed: 1 day 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.