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, and any question answerable by traversing GitLab's unified entity graph (projects, users, MRs, issues, pipelines, files, definitions, vulnerabilities).
78
100%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
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.
This is an excellent skill description that clearly specifies the tool (glab orbit CLI), enumerates concrete use cases with natural trigger terms, and explicitly states when to use it. The description is comprehensive yet concise, covering both the 'what' and 'when' dimensions thoroughly while maintaining a distinct identity that would not easily conflict with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: querying via CLI subcommands, running a local copy, code-structure questions (who calls a function, where a symbol is defined), cross-project dependency analysis, blast-radius analysis, merge-request queries, contributor queries, and traversing a unified entity graph with specific entity types enumerated. | 3 / 3 |
Completeness | Clearly answers both 'what' (query the GitLab Knowledge Graph via specific CLI commands) and 'when' ('Use for code-structure questions, cross-project dependency and blast-radius analysis, merge-request and contributor queries, and any question answerable by traversing GitLab's unified entity graph'). The 'Use for...' clause serves as an explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes many natural keywords users would say: 'who calls this function', 'where is this symbol defined', 'dependency', 'blast-radius', 'merge-request', 'contributor', 'projects', 'users', 'MRs', 'issues', 'pipelines', 'files', 'definitions', 'vulnerabilities', 'GitLab', 'Knowledge Graph', 'glab orbit'. These cover a wide range of natural query terms. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with specific tool names ('glab orbit remote', 'glab orbit local'), a unique domain (GitLab Knowledge Graph / Orbit), and clearly scoped triggers. Unlikely to conflict with generic code search or git skills due to the specific tooling and graph-traversal focus. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an exceptionally well-crafted skill that provides dense, actionable guidance for querying GitLab's Orbit Knowledge Graph. It excels at conciseness (no wasted tokens explaining concepts Claude knows), actionability (complete executable examples), workflow clarity (explicit iteration budgets with validation checkpoints), and progressive disclosure (clean references table with well-signaled deep links). The common pitfalls section is particularly valuable, providing specific traps with concrete solutions rather than vague warnings.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient throughout. It assumes Claude's competence (no explanation of what a knowledge graph is, what CLI tools are, etc.), and every section provides information Claude wouldn't already know — specific filter syntax, pitfall details, iteration budgets, and query shapes. The caching advice and performance notes earn their tokens. | 3 / 3 |
Actionability | Provides fully executable bash commands and complete JSON query bodies that are copy-paste ready. Filter syntax is specified with concrete operator lists, the query execution pattern (write to file, pass to CLI) is explicit, and even the error-handling/reporting format includes a concrete example of good vs bad output. | 3 / 3 |
Workflow Clarity | The multi-step workflow is clearly sequenced: discover schema → consult recipes → write query to file → execute → validate results → report with caveats. The iteration budget section provides explicit validation checkpoints (5-attempt cap, material change requirement, 3-consecutive-400 rule), and the reporting section includes a feedback loop for coverage gaps. The common pitfalls section serves as a pre-flight checklist. | 3 / 3 |
Progressive Disclosure | Excellent progressive disclosure with a clear overview in SKILL.md and well-signaled one-level-deep references to recipes.md, query_language.md, troubleshooting.md, local_repo_map.md, remote_repo_map.md, and local_cli.md. The references table at the bottom provides clean navigation, and inline links to specific anchors (e.g., recipes.md#pipelines-that-ran-for-one-merge-request) guide to exact content. | 3 / 3 |
Total | 12 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 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 | 9 / 11 Passed | |
- Repository
- gitlabhq/orbit-knowledge-graph
- Commit
f5efc36
- Reviewed
Table of Contents
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.