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

81%

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

75%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.

The content is a well-structured, mostly lean verification workflow with concrete commands and a clear sequence plus re-run feedback loop. The main gaps are implicit project commands in Step 3 and inline detail that could be split into a reference file for tighter progressive disclosure.

Suggestions

In Step 3, name a concrete discovery command (e.g. 'cat package.json scripts' or 'run the project's configured check command') instead of leaving lint/type-check/test invocation unspecified, to push actionability toward 5.

Move the cross-layer checklists (Step 5, sections A-D) into a references/ file and link to it from SKILL.md, improving both conciseness and progressive_disclosure.

Replace the quoted self-prompt in Spec Sync with a one-line imperative checklist item to trim the mild over-explanation.

Dimension	Reasoning	Score
Conciseness	The body is lean — checklists and short bash blocks with no concept explanations Claude already knows — but the quoted 'If I fixed a bug...' prompt and a few full-sentence asides are mild over-explanation that keep it just below the score-5 'every token earns its place' anchor.	4 / 5
Actionability	Concrete executable commands are provided (git diff, get_context.py, cat index.md, grep -r), but Step 3 ('Run the project's lint, type-check, and test commands') leaves the exact commands implicit and the checklists are questions rather than runnable steps, leaving minor gaps versus the fully copy-paste-ready 5 anchor.	4 / 5
Workflow Clarity	Six clearly sequenced steps with feedback loops ('Fix any failures before proceeding', 'Re-run project checks after fixes') and a gating checklist, but checkpoints are stated inline rather than as explicit validate->fix->retry blocks, placing it just below the score-5 anchor; the destructive/batch cap does not apply since the skill verifies rather than mutates.	4 / 5
Progressive Disclosure	No bundle files exist and the ~88-line body is well-organized into numbered steps and labeled sub-sections (A-D), so structure is good and self-contained; it scores 4 rather than 5 because it exceeds the <50-line simple-skill threshold and carries inline detail (cross-layer checklists) that a reference file could absorb.	4 / 5
	Total	16 / 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.

The description is strong: it enumerates concrete capabilities, explicitly pairs a 'what' with a 'when' trigger clause, and uses third-person voice throughout. Its main weakness is trigger-term breadth, relying on a few generic phrases rather than a comprehensive set of natural synonyms.

Suggestions

Broaden trigger terms with natural user phrases such as 'run the quality gate', 'review code before a PR', or 'run lint and tests' to lift trigger_term_quality toward 5.

Tighten 'needs quality verification' to a more distinctive phrase (e.g. 'verify code against the trellis spec') to reduce overlap with generic code-review skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'spec compliance, lint, type-check, tests, cross-layer data flow, code reuse, and consistency checks' — giving comprehensive coverage of what the skill does, matching the score-5 anchor rather than the 4 anchor's 'minor gaps'.	5 / 5
Completeness	Explicitly answers both what ('Comprehensive quality verification: spec compliance, lint, type-check, tests...') and when ('Use when code is written and needs quality verification, before committing changes, or to catch context drift'), matching the score-5 anchor for both what and when with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural user-facing phrases like 'before committing changes' and 'catch context drift during long sessions' are present, but 'quality verification' is somewhat generic and common synonyms (e.g. 'run tests', 'review code', 'before PR') are not covered as triggers, so it sits above the 3 anchor but below 5.	4 / 5
Distinctiveness Conflict Risk	The trellis-spec and cross-layer focus gives it a clear niche, but 'before committing changes' and general 'quality verification' framing create minor overlap risk with generic code-review or commit-message skills, placing it at 4 rather than 5.	4 / 5
	Total	18 / 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: .omp/skills/trellis-check/SKILL.md
Commit: 64e6636

Reviewed: 5 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.