CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

orbit

Use Orbit (`glab orbit` or `orbit`) to search code and read it with callers and tests. It reads MRs, issues, and failed jobs with the code they cite. Graph queries answer relationship and aggregation questions across GitLab. Skip it for writes that `glab` handles.

Quality

79%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/orbit/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

82%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 highly actionable, token-efficient body with copy-paste commands, a bounded iteration workflow, and verified one-level-deep references. The only weaknesses are minor: tangled Managed CLI prose that could be tightened or split out, and one dangling example path in the Discovery section.

DimensionReasoningScore

Conciseness

The body is dense with non-obvious operational specifics and assumes CLI competence (e.g. "Endpoints are user-scoped, so do not pass -R owner/repo"), but the Managed CLI flag-behavior prose ("the binary rejects `--yes` after other subcommands, except for `setup` and `uninstall`, which take their own. glab's own `update` command also takes `--yes`") is tangled and could be a table or bullets. Not 5 because minor trimming and relocation to a reference file is possible; not 3 because there is no padding or explanation of concepts Claude already knows.

4 / 5

Actionability

Fully executable, copy-paste ready commands throughout: `glab orbit query 'CALL db.schema()'`, `glab orbit --install --yes`, `glab config set orbit_cli_auto_run true`, and pitfalls given as exact rejected vs. accepted syntax ("MATCH (p:Project) RETURN p LIMIT 5 rejects", "count(DISTINCT pl)"). Matches the top anchor of copy-paste ready commands covering common cases.

5 / 5

Workflow Clarity

Sections sequence a real workflow (prerequisites on failure -> first-run setup, schema discovery "once per session", query construction with pitfalls, "at most 5 query attempts, validation errors included", reporting with coverage caveats) with error-recovery pointers to exit-code troubleshooting. Not 5 because checkpoints live partly in referenced files and there is no explicit ordered procedure; not 3 because validation and feedback loops are present and explicit. Queries are read-only, so the destructive/batch cap does not apply.

4 / 5

Progressive Disclosure

Clear overview with well-signaled one-level-deep references (references/troubleshooting.md, references/gql.md, references/reporting.md, references/maintaining.md) that all exist in the bundle with verifiable anchors, plus a topic-to-location table. Not 5 because the illustrative path `references/local/cli.md` cited in Discovery does not exist in this bundle, and the Managed CLI flag minutiae is arguably reference-file material — minor organization gaps matching the anchor 4 wording.

4 / 5

Total

17

/

20

Passed

Description

70%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 concrete, uses natural developer terminology, and occupies a clearly distinct GitLab-graph niche with an explicit negative boundary. Its main weakness is the absence of a positive "Use when..." trigger clause, which caps completeness, along with a few missing synonyms such as "merge requests" and "knowledge graph".

Suggestions

Add an explicit positive trigger clause, e.g. "Use when asked about GitLab code relationships, MRs, issues, or failed jobs, or when searching code with caller and test context."

Include common synonyms alongside the current terms: "merge requests" (not just MRs), "knowledge graph" (the tool's previous name), and "code search".

Consider mentioning the local-graph capabilities (grep, context, workspace indexing) to round out capability coverage currently detailed only in the body.

DimensionReasoningScore

Specificity

Quotes like "search code and read it with callers and tests", "reads MRs, issues, and failed jobs with the code they cite", and "Graph queries answer relationship and aggregation questions across GitLab" list several concrete actions. Not 5 because local-graph capabilities the body covers (grep, context, workspace indexing) are absent; not 3 because coverage goes well beyond 1-2 actions.

4 / 5

Completeness

The "what" is clear and concrete, but there is no positive "Use when..." clause; the only trigger guidance is the negative "Skip it for writes that `glab` handles", leaving the "when" weakly implied, which caps completeness at 3 per the rubric guidelines. Not 4 because no explicit positive trigger exists; not 2 because the what is clear and an explicit boundary is stated.

3 / 5

Trigger Term Quality

"search code", "MRs", "issues", "failed jobs", and "callers and tests" are phrasings users would naturally say. Not 5 because common synonyms such as "merge requests", "knowledge graph", and "code search" are missing; not 3 because keyword coverage is good rather than partial.

4 / 5

Distinctiveness Conflict Risk

The description is tightly scoped to GitLab Orbit (`glab orbit` or `orbit`) with graph queries, and "Skip it for writes that `glab` handles" explicitly disambiguates it from plain glab usage. Clear niche with distinct triggers and minimal conflict risk, matching the top anchor.

5 / 5

Total

16

/

20

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 — 13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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

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.