ticket-create

Authoritative protocol for creating Neo.mjs GitHub issues. Enforces duplicate sweep, Fat Ticket body structure, strict label rules, title hygiene, and the six-stage challenge chain at creation time. CRITICAL: Do NOT run default `npx playwright test` to verify issues; Neo uses multiple custom playwright configs (e.g., unit, e2e) which must be explicitly targeted. Use immediately before calling the create_issue MCP tool. Triggers: Use this skill before any invocation of the create_issue MCP tool. This is the creation-side dual of ticket-intake (which consumes existing tickets).

Quality

78%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/ticket-create/SKILL.md

Quality

Content

72%Weight 40%Scale 1-3

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

A minimal, well-disciplined delegation skill: the body is concise and points cleanly to a single real reference file. Its weakness is that almost all actionable detail and the multi-step workflow live entirely in the reference, so the body alone offers little beyond a pointer and a few gating rules.

Suggestions

Surface a compact inline skeleton of the creation workflow (e.g., the ordered stages: duplicate sweep → Fat Ticket body → labels → title hygiene → six-stage challenge chain) so Claude has the sequence without opening the reference, while keeping full detail delegated.

State at least one explicit validation checkpoint in the body — e.g., the duplicate-sweep result must be reviewed before composing the title/body — rather than only forbidding that it be skipped.

Reconcile the referenced path: the body cites the deployed path `.agents/skills/ticket-create/references/ticket-create-workflow.md` while the bundle holds it at `references/ticket-create-workflow.md`; use a bundle-relative reference so navigation is unambiguous in the skill bundle.

Dimension	Reasoning	Score
Conciseness	A lean two-sentence body that assumes Claude's competence and adds no concept re-explanation; the emphatic MUST/MUST NOT language is deliberate enforcement, not padding. Matches the lean-and-efficient score-3 anchor.	3 / 3
Actionability	Gives one concrete executable action ("use the `view_file` tool to read ... `ticket-create-workflow.md`") with a specific path, but all substantive creation guidance is delegated to the reference, so the body standing alone is incomplete with key details missing.	2 / 3
Workflow Clarity	Gating checkpoints are present ("MUST NOT skip the pre-creation duplicate sweep", "read ... before proceeding") but the actual multi-step sequence and validation feedback loops (six-stage challenge chain) live in the reference, leaving the body's sequence implicit and checkpoints delegated rather than shown.	2 / 3
Progressive Disclosure	The body is a concise overview that delegates to a single, clearly-signaled, one-level-deep reference file (`references/ticket-create-workflow.md`, confirmed to exist in the bundle), matching the clear-overview-with-well-signaled-references anchor.	3 / 3
	Total	10 / 12 Passed

Description

85%Weight 40%Scale 1-3

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 strong, specific description that clearly states what the skill does and when to use it, with explicit cross-referencing to avoid conflicts with ticket-intake. Its only weakness is trigger phrasing anchored on the MCP tool name rather than the natural language users would actually say.

Suggestions

Add natural-language trigger terms users are likely to say (e.g., "Use when the user asks to file, open, or report a GitHub issue/bug") alongside the existing MCP-tool trigger so it fires on conversational requests, not only on tool invocation.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: "Enforces duplicate sweep, Fat Ticket body structure, strict label rules, title hygiene, and the six-stage challenge chain at creation time." This is comprehensive and concrete, not the score-2 single-domain naming or the score-1 vague abstraction.	3 / 3
Completeness	Clearly answers both what ("Authoritative protocol for creating Neo.mjs GitHub issues. Enforces duplicate sweep...") and when with an explicit trigger ("Triggers: Use this skill before any invocation of the create_issue MCP tool."), matching the score-3 both-what-and-when anchor.	3 / 3
Trigger Term Quality	Captures the natural phrase "creating Neo.mjs GitHub issues" but the explicit triggers are tool-invocation-oriented ("before any invocation of the create_issue MCP tool") and miss common natural variations a user would say like "file/open an issue" or "report a bug".	2 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (Neo.mjs issue creation via the create_issue MCP tool) and explicitly distinguishes itself from the sibling skill: "This is the creation-side dual of ticket-intake (which consumes existing tickets)." Unlikely to trigger for the wrong skill.	3 / 3
	Total	11 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: neomjs/neo
Path: .agents/skills/ticket-create/SKILL.md
Commit: c1ce853

Reviewed: 8 days 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.