Tessl • The package manager for agent skills

orbit

Use the `glab orbit` CLI for questions about code structure, blast radius, cross-project links, and relationships across GitLab entities, and to build a repo map. It works on hosted or local data. Skip it for single-entity lookups or writes that `glab` already handles.

Quality

82%

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

86%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.

A well-structured, actionable skill body with excellent progressive disclosure and copy-paste-ready examples. Minor conciseness trims and a more explicit validation checkpoint in the query workflow would push it to full marks.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — it never explains what GitLab or a knowledge graph is — but a few operational asides (e.g., enumerating the three config keys glab records, or the 17 KB ontology output note) could be trimmed slightly.	4 / 5
Actionability	Copy-paste ready, executable guidance throughout: a full traversal query JSON body, `glab orbit query /tmp/q.json`, the `PROJECT_ID=$(glab api ...)` resolver, and the ontology `jq` pipe cover the common cases concretely.	5 / 5
Workflow Clarity	A clear discovery → query → pitfalls → reporting sequence with real checkpoints (5-attempt iteration budget, coverage-gap reporting, first-run troubleshooting on failure), but it is not a strictly numbered workflow and validation is implicit rather than an explicit validate-then-proceed step.	4 / 5
Progressive Disclosure	The body is an overview pointing to seven real one-level-deep reference files, all clearly listed in a References table with topic labels; content is appropriately split and easy to navigate.	5 / 5
	Total	18 / 20 Passed

Description

78%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.

A strong, specific description with a clear niche and explicit boundary guidance. Its main weakness is the absence of an explicit positive 'Use when...' trigger clause, which keeps completeness and trigger quality at 4 rather than 5.

Suggestions

Add an explicit positive trigger clause such as 'Use when the user asks about code structure, blast radius, or cross-project relationships across GitLab entities' to lift completeness toward 5.

Include common synonyms like 'dependency graph' or 'knowledge graph' alongside 'orbit' to broaden natural trigger coverage.

Replace the abstract 'questions about' framing with discrete verbs (e.g., 'Find', 'Map', 'Trace') to sharpen specificity.

Dimension	Reasoning	Score
Specificity	Lists several concrete use cases — 'questions about code structure, blast radius, cross-project links, and relationships across GitLab entities, and to build a repo map' — but the 'questions about' framing is slightly less concrete than naming discrete operations, leaving minor coverage gaps.	4 / 5
Completeness	Clearly answers 'what' (the listed query use cases plus repo-map building) and provides 'when' guidance via the negative boundary 'Skip it for single-entity lookups or writes that glab already handles', though an explicit positive 'Use when...' clause would make the trigger more direct.	4 / 5
Trigger Term Quality	Natural terms users would say are present ('code structure', 'blast radius', 'cross-project links', 'repo map', 'GitLab'), but common synonyms like 'dependency graph' or 'knowledge graph' are absent, leaving a few natural terms missing.	4 / 5
Distinctiveness Conflict Risk	Clear niche (GitLab Orbit knowledge-graph querying) with distinct triggers and an explicit boundary against glab's own single-entity/writes, giving minimal conflict risk.	5 / 5
	Total	17 / 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
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 1 missing, 1 deeper-than-1-level	Warning

	Total	13 / 16 Passed

Repository: gitlabhq/orbit-knowledge-graph
Path: skills/orbit/SKILL.md
Commit: 1f9ea75

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.