CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

ticket-craft

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

56

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/ticket-craft/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

71%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.

This is a highly actionable, well-structured instructional skill — templates, commands, checklists, and worked examples are all copy-paste ready, and the ticket-creation workflow has real validation checkpoints. Its weaknesses are economy and modularity: ASCII-art boxes and explanatory padding cost tokens, and the whole library of templates and integrations lives inline in SKILL.md instead of being split into reference files.

Suggestions

Split the four ticket-type templates, the ticket-system integration guides, and the agent-team mapping into references/ files (e.g., templates/feature.md, integrations.md), keeping SKILL.md as an overview with clearly signaled links — the skill's biggest structural gap.

Replace the two ASCII-art boxes with plain bullet lists; they duplicate content (the checklist box restates the Definition of Ready items) at a large token cost.

Close the workflow's validation loop: after Step 4 flags unchecked items, instruct the agent to revise the ticket and re-run the checklist until every box passes, instead of deferring to the user.

DimensionReasoningScore

Conciseness

Mostly efficient reference material (templates, tables, commands), but the two ASCII-art boxes ("A TICKET IS A PROMPT" and the checklist) restate content that flat lists would carry in far fewer tokens, and passages like the Core Principle box explain things Claude already knows (that agents cannot ask clarifying questions). Anchor 3: could be tightened, but not anchor 2 since padding is localized rather than pervasive.

3 / 5

Actionability

Fully executable throughout: copy-paste-ready ticket templates for four ticket types, exact verification commands (e.g., "npm test -- --grep \"rate-limit\""), a complete worked good-vs-bad example, and a concrete 5-step /create-ticket workflow. Matches anchor 5: specific examples cover the common cases.

5 / 5

Workflow Clarity

The /create-ticket flow is a clear 5-step sequence with an explicit validation checkpoint (Step 4 runs the Claude Code Ready Checklist), and the bug-fix workflow embeds a TDD verify-loop (write failing test → fix → verify passes → full regression). Not 5 because Step 4's failure path ("Flag any unchecked items for the user to address") defers recovery to the user rather than looping back to regenerate and re-validate.

4 / 5

Progressive Disclosure

Sections are well-organized with clear headers, but the ~600-line body is a monolith: the four full ticket templates, per-tool integration guides (Jira/Asana/Linear/GitHub), and agent-team mapping clearly belong in separate reference files, and no bundle files or references exist at all. Anchor 3 (structure present, content that should be separate is inline), not 2 because navigation via headers is genuinely easy.

3 / 5

Total

15

/

20

Passed

Description

61%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 clearly communicates the domain (ticket writing for Jira/Asana/Linear, optimized for AI execution) with strong tool-name triggers, but it reads more as a tagline than a complete description: it lacks an explicit use-when clause and states only one concrete action. Moving the trigger guidance into the description itself would lift it substantially.

Suggestions

Append an explicit trigger clause to the description, e.g. "Use when creating tickets, breaking down epics, or writing specs for AI agent execution in Jira, Asana, Linear, or GitHub Issues" — this directly addresses the completeness cap.

List 2-3 more concrete capabilities in the description (e.g., "apply INVEST+C criteria, generate acceptance criteria, validate tickets against a Claude-Ready checklist") to raise specificity.

Replace the vague "AI-native ticket writing" tail with a distinguishing phrase like "self-contained tickets an agent can execute without clarifying questions" to sharpen distinctiveness.

DimensionReasoningScore

Specificity

"Create Jira/Asana/Linear tickets" names the domain and one concrete action, but "optimized for Claude Code execution - AI-native ticket writing" leans on buzzphrases and no other actions (break down epics, validate readiness) appear in the description field. Matches anchor 3 (domain plus 1-2 concrete actions), not 4, which requires several specific listed actions.

3 / 5

Completeness

The "what" is clear, but the description field contains no "Use when..." clause or equivalent trigger guidance (that lives in a separate when-to-use frontmatter field, not the description), so completeness is capped at 3 per the rubric guidelines. Not 4 because the "when" is absent entirely from the evaluated text rather than merely imprecise.

3 / 5

Trigger Term Quality

"Jira/Asana/Linear tickets" and "Claude Code" are natural terms users would actually say when needing this skill. A few common variations ("issues", "user stories", "backlog", "spec") are missing, keeping it at anchor 4 rather than 5.

4 / 5

Distinctiveness Conflict Risk

Naming the three specific tools carves a distinct niche with clear triggers; only minor overlap risk with general technical-writing or spec-drafting skills. Not 5 because "AI-native ticket writing" is generic enough to brush against adjacent writing-skills.

4 / 5

Total

14

/

20

Passed

Validation

87%

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

CriteriaDescriptionResult

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

14

/

16

Passed

Repository

alinaqi/maggy

Path

skills/ticket-craft/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.