Tessl • The management layer for AI agent skills

Blog Docs Log inGet started

SkillPublic

orbit-cli

New local

Quality

25%

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 ./crates/orbit-cli/tests/fixtures/skills/new-local/SKILL.md

Quality

Content

18%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 pure scaffolding: two placeholder section headings delimited by orbit HTML comments, with no instructions, examples, or workflow content. It appears to be an unfinished template that was never populated, and a reader gains no guidance from it.

Suggestions

Replace the placeholder headings with real instructions for the Orbit CLI — the concrete commands, flags, and workflows the skill is meant to drive (actionability scored 1).

If the skill involves multi-step or state-changing CLI operations, lay out a numbered sequence with explicit validation checkpoints between steps (workflow_clarity scored 1).

Either populate the two orbit sections with meaningful content or remove the empty scaffold comments so every remaining line carries guidance (conciseness and progressive_disclosure both lost points to content-free tokens).

Dimension	Reasoning	Score
Conciseness	The body is 7 lines with zero verbose explanation, padding, or re-teaching of known concepts, so it avoids the 1-2 anchors entirely. But it also cannot score 4-5: the HTML comment markers ("<!-- orbit:section shared -->") and placeholder headings ("## New local shared") are tokens that carry no instruction and thus do not earn their place.	3 / 5
Actionability	The body contains no code, commands, or guidance of any kind — only two scaffold headings ("New local shared", "New local extra") and comment delimiters. This matches the score-1 anchor 'Entirely vague or abstract; no concrete code or commands'; score 2 is ruled out because there are not even high-level hints.	1 / 5
Workflow Clarity	No steps, sequence, or process is present anywhere in the body, matching the score-1 anchor 'Steps missing or incoherent'. The simple-skill exception cannot apply because there is no single unambiguous action described — there is no content at all.	1 / 5
Progressive Disclosure	The body has minimal structure (two headings, an open/close comment pattern) but the sections are meaningless placeholders, no bundle files exist (references/, scripts/, assets/ are absent), and no references are signaled. It sits between the score-1 monolith/nested-reference anchor and the score-3 'some structure' anchor — closer to 2, since the structure present organizes nothing.	2 / 5
	Total	7 / 20 Passed

Description

0%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 a placeholder ("New local") that fails every dimension: it conveys no capability, no trigger terms, no what/when guidance, and no distinctiveness. It reads like an unedited template rather than a shipped skill description.

Suggestions

Replace "New local" with a concrete capability statement in third person, e.g. "Runs Orbit CLI commands to manage deployments and inspect cluster state" — naming the domain plus 2-3 specific actions.

Add an explicit trigger clause, e.g. "Use when the user mentions Orbit, deployments, or cluster operations" — without a 'Use when...' clause completeness is capped at 3.

Include natural synonyms and artifact names users would actually say (e.g. the CLI command, file types, or workflows the skill handles) to make the skill discoverable and distinct from generic dev-ops skills.

Dimension	Reasoning	Score
Specificity	The description is the placeholder text "New local" — it names no domain and no concrete or abstract action of any kind, matching the anchor 'Entirely vague; no concrete actions; pure abstract language' (cf. "Helps with documents", which at least names a domain). Score 2 is ruled out because even a minimal domain mention is absent.	1 / 5
Completeness	Neither 'what does this do' nor 'when to use it' is present in any form; the text is an empty placeholder. This is the exact score-1 anchor ('Missing both what and when') and clearly below the score-2 anchor, which requires at least a vague 'what' or a 'when'.	1 / 5
Trigger Term Quality	"New local" contains no keywords users would naturally say and no technical terms either — there is no trigger vocabulary whatsoever, matching the score-1 anchor. It cannot be 2 because even 'one or two generic keywords' (e.g. "Works with files") are missing.	1 / 5
Distinctiveness Conflict Risk	The description is entirely generic and indistinguishable — it neither carves out a niche nor provides any distinguishing trigger, so it cannot be reliably matched to any intent, matching the score-1 anchor 'Entirely generic'. The additional hint 'Requires Orbit CLI' sits in a non-description frontmatter field and does not rescue distinctiveness.	1 / 5
	Total	4 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
description_field	'description' is very short (9 chars), consider making it more detailed	Warning
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: gitlabhq/orbit-knowledge-graph
Path: crates/orbit-cli/tests/fixtures/skills/new-local/SKILL.md
Revision: ed321d9

Reviewed: 27 days 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.

orbit-cli

Table of Contents

Is this your skill?