ticket-craft

Create Jira/Asana/Linear tickets optimized for Claude Code execution - AI-native ticket writing

Quality

47%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/ticket-craft/SKILL.md

Quality

Discovery

54%

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 has a clear and distinctive niche with good trigger terms covering major project management tools and the Claude Code optimization angle. However, it lacks an explicit 'Use when...' clause and could benefit from listing more specific concrete actions beyond just 'create tickets'. The description reads more like a tagline than a functional skill description.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user asks to write tickets, create issues, or draft task descriptions for Jira, Asana, or Linear that will be executed by Claude Code.'

List specific concrete actions such as 'Structures acceptance criteria, defines subtasks, writes implementation-ready descriptions, and formats tickets with clear scope boundaries for AI agent execution.'

Include common user phrasing variations like 'write a ticket', 'create an issue', 'draft a task', 'story writing', or 'backlog grooming'.

Dimension	Reasoning	Score
Specificity	Names the domain (ticket creation for project management tools) and a general action ('Create... tickets'), but doesn't list multiple concrete actions like formatting fields, setting priorities, writing acceptance criteria, or structuring subtasks.	2 / 3
Completeness	Describes what it does (create tickets optimized for Claude Code) but has no explicit 'Use when...' clause or equivalent trigger guidance. Per the rubric, a missing 'Use when' clause caps completeness at 2, and the 'what' is also somewhat thin, so this scores a 1.	1 / 3
Trigger Term Quality	Includes strong natural trigger terms users would say: 'Jira', 'Asana', 'Linear', 'tickets', 'Claude Code', and 'AI-native'. These cover the major project management tools and the specific use case well.	3 / 3
Distinctiveness Conflict Risk	The combination of specific tools (Jira/Asana/Linear), the specific purpose (optimized for Claude Code execution), and the 'AI-native ticket writing' framing creates a very clear niche that is unlikely to conflict with other skills.	3 / 3
	Total	9 / 12 Passed

Implementation

39%

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

This skill is comprehensive and well-structured in terms of workflow clarity, with clear checklists, validation steps, and a defined ticket creation process. However, it is severely over-long and verbose, explaining many concepts Claude already understands (INVEST, Given-When-Then, what ticket systems are) and inlining all templates and reference material into a single massive file. The token cost is very high relative to the actionable content, and the lack of progressive disclosure means the entire ~500+ line document must be loaded even when only one template type is needed.

Suggestions

Split ticket templates (Feature, Bug, Tech Debt, Epic) into separate referenced files (e.g., templates/feature.md, templates/bug.md) and keep SKILL.md as a concise overview with the checklist and /create-ticket workflow only.

Remove explanations of concepts Claude already knows: INVEST criteria definitions, what Given-When-Then is, what story points represent, descriptions of Jira/Asana/Linear. Keep only the Claude-specific additions (the '+C' criterion, the Claude Code Context sections).

Replace the ASCII box diagrams with compact bullet lists or tables - they consume significant tokens for minimal information density.

Condense the anti-patterns section to a simple table (pattern name | why it fails | fix) rather than full code block examples for each.

Dimension	Reasoning	Score
Conciseness	Extremely verbose at ~500+ lines. Explains concepts Claude already knows (INVEST criteria, what Given-When-Then is, what story points are, what Jira/Asana/Linear are). The ASCII box diagrams, anti-pattern explanations, and extensive template scaffolding with placeholder variables add significant token bloat. Much of this could be condensed to core templates and the checklist.	1 / 3
Actionability	The templates are concrete and structured with specific fields to fill in, and the /create-ticket command provides a clear workflow. However, the templates are filled with placeholder variables rather than realistic executable examples, and the verification commands are generic (npm test, npm run lint) rather than demonstrating real usage. The good vs bad examples section adds actionability but overall the skill is more template-oriented than copy-paste ready.	2 / 3
Workflow Clarity	The /create-ticket command provides a clear 5-step workflow with explicit validation (Step 4: validate with checklist). The Claude Code Ready Checklist serves as an explicit verification checkpoint. The Bug Fix Workflow includes a TDD feedback loop (write failing test → verify it fails → fix → verify passes → regression check). The Definition of Ready and Definition of Done provide clear entry/exit criteria.	3 / 3
Progressive Disclosure	The entire skill is a monolithic wall of text with no references to external files. All four ticket templates, the epic slicing guide, anti-patterns, agent team mapping, story point calibration, and ticket system integration details are inlined. This content would benefit enormously from splitting templates into separate files and keeping SKILL.md as a concise overview with references.	1 / 3
	Total	7 / 12 Passed

Validation

81%

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 — 9 / 11 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (678 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	9 / 11 Passed

Repository: alinaqi/claude-bootstrap
Commit: df6ab96

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.