trellis-before-dev

Discovers and injects project-specific coding guidelines from .trellis/spec/ before implementation begins. Reads spec indexes, pre-development checklists, and shared thinking guides for the target package. Use when starting a new coding task, before writing any code, switching to a different package, or needing to refresh project conventions and standards.

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

78%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 body is a tight, actionable, well-sequenced preparation workflow with concrete commands and a strong change-boundary checklist. Its main gap is the absence of explicit verification/validation checkpoints, which is acceptable here because the task is non-destructive.

Suggestions

Add a lightweight verification checkpoint after reading the guidelines (e.g., confirm the applicable checklist items were read before declaring the step complete) to push workflow_clarity toward 5.

Replace placeholder paths with a concrete worked example (e.g., cat .trellis/spec/cli/backend/index.md) to make the commands fully copy-paste ready.

Trim the closing summary line 'Understand the coding standards and patterns you need to follow, then proceed with your development plan.' since it restates the step's intent without adding guidance.

Dimension	Reasoning	Score
Conciseness	The body is largely lean and assumes Claude's competence, with concrete commands and no padding about basic concepts; only minor closing prose like 'Understand the coding standards and patterns you need to follow, then proceed' could be trimmed, keeping it just below a 5.	4 / 5
Actionability	It provides executable commands (get_context.py, cat index.md) and a concrete change-boundary checklist, but the commands use placeholders like <package>/<layer> and the conditional branches ('if present', 'for a non-trivial task') leave minor gaps versus copy-paste-ready guidance.	4 / 5
Workflow Clarity	Eight clearly sequenced steps with a mandatory gate ('This step is mandatory before writing any code') and a scope-escalation feedback note; it lacks explicit validation checkpoints, but as a read/prepare task it is not destructive, so the destructive cap does not apply and it sits at 4 rather than 5.	4 / 5
Progressive Disclosure	The skill is a single under-50-line SKILL.md with no bundle files and no need for external references, yet is well organized into clearly numbered steps, qualifying for the simple-skill exception that allows a 5 on structure alone.	5 / 5
	Total	17 / 20 Passed

Description

83%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 clearly and concretely communicates what the skill does and when to trigger it, with a well-structured 'Use when...' clause. It is held back only by slightly abstract action verbs and a lack of synonym/extension trigger terms.

Suggestions

Make the actions more concrete by naming what 'injects guidelines' produces (e.g., 'loads them into context before you write code') so specificity reaches a 5.

Add natural synonyms or the .trellis path as trigger terms (e.g., 'Use when you see a .trellis/spec/ directory or are asked to follow trellis conventions') to broaden trigger coverage.

Sharpen distinctiveness by foregrounding the trellis-specific toolchain up front so it cannot be confused with general coding-convention skills.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('Discovers and injects project-specific coding guidelines', 'Reads spec indexes, pre-development checklists, and shared thinking guides') with only minor abstraction in 'injects guidelines'; not quite the comprehensive, fully concrete action list of a 5.	4 / 5
Completeness	It explicitly states both what it does (discover/inject guidelines, read spec indexes, checklists, guides) and when to use it with concrete trigger phrases in a 'Use when...' clause, matching the 5 anchor.	5 / 5
Trigger Term Quality	Natural trigger phrases are present ('starting a new coding task', 'before writing any code', 'switching to a different package', 'refresh project conventions and standards'), but it lacks synonyms or the .trellis file extension as additional natural terms that would push it to 5.	4 / 5
Distinctiveness Conflict Risk	The .trellis/spec/ niche and pre-implementation timing make it mostly distinct with only minor overlap risk against a generic 'read conventions before coding' skill; not yet the unambiguous, zero-conflict niche of a 5.	4 / 5
	Total	17 / 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-before-dev/SKILL.md
Commit: 64e6636

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.