Tessl • The management layer for AI agent skills

The body is a concise, fully executable single-purpose workflow with explicit validation and well-organized sections. It assumes Claude's competence and provides copy-paste-ready commands with useful troubleshooting notes.

Dimension	Reasoning	Score
Conciseness	Lean and efficient with a short intro, three one-line command steps, and brief troubleshooting notes; no over-explanation of direnv or basic concepts, and every line earns its place.	5 / 5
Actionability	Every step is a copy-paste-ready executable command (direnv allow, the eval export, the validation one-liner) and the Notes give specific system-tool checks and a macOS PATH export covering common cases.	5 / 5
Workflow Clarity	Clear numbered sequence (allow -> load into shell -> validate) with an explicit validation checkpoint and success/error branch; the simple-skill exception applies since this is non-destructive setup.	5 / 5
Progressive Disclosure	Under 50 lines, single-purpose, with no need for external references; organized into clear Instructions / Steps / Notes sections, qualifying for the simple-skill exception.	5 / 5
	Total	20 / 20 Passed

Description

70%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 states what the skill does and gives an explicit precondition for when to run it, with concrete, natural trigger terms. It is slightly limited by listing only one action and framing the 'when' as a precondition rather than a 'Use when...' trigger.

Suggestions

Add 1-2 more concrete actions (e.g., 'sets AKASH_ROOT, GOTOOLCHAIN, and PATH, and downloads build tools') to broaden capability coverage.

Reframe the 'when' as an explicit 'Use when...' trigger phrase (e.g., 'Use when running any make target such as tests, builds, or linting').

Include common synonyms or aliases a user might say (e.g., 'make', 'build', 'lint') to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain (development environment setup) and one concrete action (loading direnv), but does not enumerate multiple specific actions, matching the '1-2 concrete actions' anchor.	3 / 5
Completeness	Has both a clear 'what' ('Set up development environment by loading direnv') and an explicit 'when' ('Must be run before any make targets'), though the 'when' is a precondition rather than a 'Use when...' trigger phrase.	4 / 5
Trigger Term Quality	Includes specific natural terms a user would say ('direnv', 'make targets', 'tests, builds, linting') with good coverage, though it lacks synonyms or file extensions.	4 / 5
Distinctiveness Conflict Risk	Tied to a clear niche (direnv loading before make targets) with low conflict risk, with only minor possible overlap against a generic build/test skill.	4 / 5
	Total	15 / 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: akash-network/node
Path: .agents/skills/setup-env/SKILL.md
Revision: 4373aa9

Reviewed: 2 months ago

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.

setup-env

Table of Contents

Is this your skill?