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`).

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No known issues

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable with a clear, checkpointed workflow and clean progressive disclosure into verified references. Its only weakness is conciseness: inline version pins and a few asides carry time-sensitive weight that could be trimmed or moved to a versioned/deprecated section.

Suggestions

Move or isolate version-specific facts (e.g. `glab v1.94.0+`) so they don't burden the core instructions, or note them in a dedicated compatibility note.

Trim peripheral asides like the '~17 KB+' output-size aside unless it changes an action Claude must take.

Consider folding the four 'Common pitfalls' items into recipes.md (already referenced) to keep the overview shorter, since each pitfall already deep-links there.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and assumes competence, but inline version pins (`glab v1.94.0+`, `source = "merge_request_event"`) and a few asides (e.g. '~17 KB+ of output') add time-sensitive/extraneous weight the guidelines say to trim or relocate.	2 / 3
Actionability	Provides fully executable, copy-paste-ready guidance: a paste-ready query JSON written to /tmp/q.json, the exact `glab orbit remote query /tmp/q.json` command, a concrete operator list, and real `--jq` examples.	3 / 3
Workflow Clarity	A clear sequence (prerequisites → discovery → running → pitfalls → iteration budget → reporting) with an explicit feedback loop: HTTP 400 errors count toward the budget and exceeding 5 attempts means 'give up loudly' rather than continuing.	3 / 3
Progressive Disclosure	SKILL.md is a concise overview pointing one level deep to a well-organized References table; every referenced path and deep-link anchor resolves to a real bundle file, with no multi-level nesting.	3 / 3
	Total	11 / 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.

The description is specific, trigger-rich, and complete, naming concrete capabilities and explicit use/avoid conditions tied to natural user phrasing. It cleanly distinguishes Orbit from ordinary glab single-entity commands.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — querying via `glab orbit remote`/`local` subcommands, blast-radius analysis, MR/contributor queries, and repo-map generation — matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Explicitly answers both what (query the GitLab Knowledge Graph for relationship/aggregation questions) and when ('Use for code-structure questions…'), with an explicit negative trigger ('Do not use for single-entity GitLab lookups…').	3 / 3
Trigger Term Quality	Natural user phrasing like 'who calls this function', 'blast-radius analysis', and 'repo-map' plus keywords (orbit, knowledge-graph, glab) give good coverage of terms a user would actually say.	3 / 3
Distinctiveness Conflict Risk	A clear niche (GitLab Knowledge Graph relationship traversal) with distinct triggers and explicit disambiguation against plain `glab mr view`/`glab mr create` makes conflict with other skills unlikely.	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: 78fa8a1

Reviewed: about 10 hours 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.