Tessl • The package manager for agent skills

orbit

Query the GitLab Knowledge Graph (Orbit) via `glab orbit remote` CLI subcommands or run a local copy with `glab orbit local`. Use for code-structure questions (who calls this function, where is this symbol defined), cross-project dependency and blast-radius analysis, merge-request and contributor queries that require relationship traversal or aggregation, repository map / repo-map generation, and any question spanning relationships, cross-entity joins, or multi-entity aggregation across GitLab entities (projects, users, MRs, issues, pipelines, files, definitions, vulnerabilities). Do not use for single-entity GitLab lookups or write operations that `glab` handles directly (e.g. `glab mr view`, `glab mr create`); prefer Orbit when the question spans relationships, cross-entity joins, or multi-entity aggregation.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

100%

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 well-structured, executable guide that defers detail to one-level-deep reference files (all verified present) while keeping the overview lean. It pairs concrete code with explicit validation and feedback loops, including a defined iteration budget and loud-give-up rule.

Dimension	Reasoning	Score
Conciseness	Lean body with no padding of concepts Claude already knows; sections like 'Running a query' and 'Common pitfalls' each earn their place with executable content. A few Discovery sentences could be tightened, but it stays at the 'lean and efficient' anchor rather than dropping to 2.	3 / 3
Actionability	Provides a complete copy-paste-ready query body fenced as 'json orbit-query' plus the exact shell command 'glab orbit remote query /tmp/q.json', a concrete operators list, and a working --jq example; fully executable, not pseudocode.	3 / 3
Workflow Clarity	Clear sequence (prerequisites -> discovery -> run -> pitfalls -> iteration budget -> reporting) with explicit validation checkpoints: HTTP 400 errors count toward the budget and 'give up loudly' is a defined feedback loop; above 2 which has implicit checkpoints.	3 / 3
Progressive Disclosure	SKILL.md is a clear overview with a well-signaled one-level-deep References table; all nine referenced files exist in references/ and the three scripts exist in scripts/, with content appropriately split across files. Not 2 because references are clearly signaled and navigation is easy.	3 / 3
	Total	12 / 12 Passed

Description

100%

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, third-person description that clearly states capabilities, natural trigger terms, both what-and-when guidance, and a negative trigger that disambiguates it from the base glab CLI. It is concise yet comprehensive without fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'cross-project dependency and blast-radius analysis, merge-request and contributor queries... repository map / repo-map generation' — matching the 'lists multiple specific concrete actions' anchor; it is above 2 because coverage is comprehensive rather than partial.	3 / 3
Completeness	Explicitly answers both what ('Query the GitLab Knowledge Graph... via glab orbit remote') and when ('Use for code-structure questions... any question spanning relationships, cross-entity joins'), plus a 'Do not use for...' negative trigger; clearly above 2 which lacks an explicit when-clause.	3 / 3
Trigger Term Quality	Includes natural phrasings a developer would actually say — 'who calls this function, where is this symbol defined', 'blast-radius analysis', 'repository map / repo-map generation' — giving good coverage; not 2 because common variations are well represented.	3 / 3
Distinctiveness Conflict Risk	Clear niche (GitLab Knowledge Graph relationship traversal) with an explicit disambiguator ('Do not use for single-entity GitLab lookups or write operations that glab handles directly'), making conflict with plain glab unlikely; above 2 which only reduces some overlap.	3 / 3
	Total	12 / 12 Passed

Validation

87%

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 — 14 / 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

	Total	14 / 16 Passed

Repository: gitlabhq/orbit-knowledge-graph
Commit: 00ca361

Reviewed: 4 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.