orbit-planning

Label Orbit work items, epics, and MRs with the canonical taxonomy (orbit:: area, type::, priority::). Manage roadmap membership (orbit-roadmap::), due dates, health, and epic hygiene. Use when you label or triage issues or MRs, add or mark roadmap deliverables, or draft or repurpose epics.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

78%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 concrete commands and sensible validation gates for batch/destructive work. Its main weakness is structure: most reference material (label IDs, mechanics) lives inline with no local bundle files to defer to.

Suggestions

Move the label-id table and detailed GraphQL mechanics into a references/ file (e.g. LABELS.md) and link to it from SKILL.md to improve progressive disclosure.

Add an explicit error-handling loop for mutations: after each `workItemUpdate`/`mergeRequestSetLabels`, check the returned `errors` field and retry or report before proceeding.

Consider splitting the bulk-sweep and roadmap sections into separate reference files so the main skill stays a concise overview with one-level-deep pointers.

Dimension	Reasoning	Score
Conciseness	Dense, action-oriented prose with no padding or explanation of concepts Claude already knows; the large inline label-id table is useful reference data but is bulk that slightly resists trimming.	4 / 5
Actionability	Fully executable glab/GraphQL commands with real GIDs, label IDs, and concrete mutation examples that are copy-paste ready across the common cases.	5 / 5
Workflow Clarity	Clear sequences with real checkpoints ('State the plan and counts before you change more than 20 items', approval gate before create, 'Check what fell off'), though error-retry loops on API mutation responses are implicit rather than spelled out.	4 / 5
Progressive Disclosure	Well-sectioned single file with external repo links signaled up top, but no bundle files exist and a large lookup table plus detailed mechanics are inlined in SKILL.md rather than split into a reference file.	3 / 5
	Total	16 / 20 Passed

Description

92%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 high-quality description that crisply states capabilities and provides concrete 'Use when...' triggers in third person. It is specific, distinct, and complete with only minor synonym coverage gaps.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('Label Orbit work items, epics, and MRs with the canonical taxonomy', 'Manage roadmap membership... due dates, health, and epic hygiene') with comprehensive coverage of the skill's scope.	5 / 5
Completeness	Explicitly answers both what (label/roadmap/epic hygiene) and when ('Use when you label or triage issues or MRs, add or mark roadmap deliverables, or draft or repurpose epics') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Strong natural trigger phrases ('label or triage issues or MRs', 'add or mark roadmap deliverables', 'draft or repurpose epics') that users would plausibly say, though a few synonyms (e.g. 'tag', 'roadmap status') are absent.	4 / 5
Distinctiveness Conflict Risk	A clear niche (Orbit GitLab taxonomy and roadmap planning) with distinct, domain-specific triggers that minimize overlap with other skills.	5 / 5
	Total	19 / 20 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
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	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
Path: .claude/skills/orbit-planning/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.