linear-issue
Plan, create, and improve Linear issues with business-level clarity. Use this skill whenever the user wants to create a Linear issue, improve an existing one, file a bug, plan a feature, create a chore/enabler, or mentions "linear issue", "file an issue", "create a ticket", "log a bug", "new issue", "plan this work", "improve this issue", or "clean up this ticket". Also trigger when the user says "I found a bug", "we need a ticket for...", "can you create an issue for...", "break this down into issues", or pastes a Linear issue URL/ID. This is the required way to create and maintain issues — it ensures every issue follows the team's format and is scoped for small PRs.
91
88%
Does it follow best practices?
Impact
97%
2.48xAverage score across 3 eval scenarios
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 a strong skill description that excels across all dimensions. It provides specific concrete actions, extensive natural trigger terms covering many user phrasings, explicit 'Use this skill whenever...' guidance, and a clear niche focused on Linear issue management. The only minor concern is that the description is somewhat verbose with its long list of trigger phrases, but this verbosity serves a functional purpose for skill selection.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions: 'Plan, create, and improve Linear issues with business-level clarity.' Also mentions specific issue types like bug, feature, chore/enabler, and scoping for small PRs. | 3 / 3 |
Completeness | Clearly answers both 'what' (plan, create, improve Linear issues with business-level clarity, ensuring team format and small PR scoping) and 'when' (explicit 'Use this skill whenever...' clause with extensive trigger phrases and scenarios). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'create a Linear issue', 'file a bug', 'create a ticket', 'log a bug', 'I found a bug', 'we need a ticket for...', 'break this down into issues', plus Linear issue URLs/IDs. These are highly natural phrases. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly scoped to Linear issues specifically, with distinct triggers like 'Linear issue', 'Linear issue URL/ID', and specific issue management terminology. Unlikely to conflict with general coding or document skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, highly actionable skill with clear workflows, executable CLI commands, and good examples. Its main weakness is length — it packs a lot of team-specific detail into a single file that could benefit from splitting templates and reference tables into separate files. Some sections are mildly redundant (labeling info appears twice), but the content is overwhelmingly useful and well-organized.
Suggestions
Extract the issue templates (Bug/Feature/Enabler) and the labeling/relationship reference tables into a separate TEMPLATES.md or REFERENCE.md file to reduce the main skill's token footprint.
Remove the duplicate labeling information — the 'Labeling Convention' section near the end repeats what's already covered in 'Issue Types' and 'Source Labels' sections earlier.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is quite long (~300+ lines) with some redundancy — the labeling convention section repeats information already covered in Source Labels and Issue Types sections. The Golden Rule section over-explains what business-level means with both 'never include' and 'always include' lists that Claude could infer. However, much of the content is genuinely necessary team-specific configuration (PR size labels, CLI syntax, relationship types). | 2 / 3 |
Actionability | Highly actionable with complete, executable CLI commands for creating and updating issues, concrete templates for each issue type, specific examples (the GitHub #2859 example), exact flag names, and real tool invocations (linear CLI, save_issue MCP tool). The workflow is copy-paste ready. | 3 / 3 |
Workflow Clarity | The workflow is clearly sequenced across 5 phases with explicit confirmation checkpoints (Phase 5: 'Let them adjust before you create anything'). Both Create and Improve modes have clear step-by-step sequences. The Improve mode includes a validation step (analyze gaps against templates) and confirmation before updating. Feedback loops are present — user confirms before any creation/mutation. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear sections and headers, but it's a monolithic document that could benefit from splitting — the templates, labeling conventions, and relationship management details could be in separate referenced files. At ~300+ lines, the inline detail is heavy for a single SKILL.md. No external file references are used. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- akash-network/console
- Commit
609b56d
- 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.