ticket-intake

Authoritative protocol defining the "Pre-Execution Reflection Gate". Mandates architectural validation, negative ROI calculation, and duplicate sweeps before an agent is permitted to begin working on a GitHub Issue. Triggers: Use this skill immediately when assigned a ticket whose authoring you did NOT see, before checking out a branch or writing any codebase modifications. A ticket YOU authored this session is exempt; one you authored in an earlier session runs a cheap drift probe instead — never an exemption you judge for yourself.

Quality

83%

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

80%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.

The body is an exceptionally lean overview that delegates detail to well-structured references, scoring high on conciseness and progressive disclosure. Its main weakness is that validation/workflow checkpoints live only in the referenced file, not in the body itself, which caps workflow clarity.

Suggestions

Add a one-line inline validation checkpoint in the body (e.g., 'Do not proceed to branch/code changes until the workflow's reflection gate has passed') so the gating sequence is self-contained.

Surface the key sub-steps of the reflection gate as a brief inline checklist so the most critical workflow is visible without requiring a reference read.

Confirm the absolute reference path '.agents/skills/ticket-intake/references/...' matches the installed bundle layout so the view_file directive resolves reliably.

Dimension	Reasoning	Score
Conciseness	Three lean lines with no padding and no over-explanation of concepts Claude already knows; every token earns its place, matching the lean-and-efficient anchor.	5 / 5
Actionability	Gives concrete directives — invoke the `view_file` tool on a specific path and named reference files — with minor gaps since the actual procedure is delegated to the referenced workflow.	4 / 5
Workflow Clarity	A rough sequence is present (don't start, read the workflow, self-authored tickets read the carve file first) but the body itself contains no validation checkpoints for this destructive-gating skill, capping the score at 3 per the destructive-operation rule.	3 / 5
Progressive Disclosure	SKILL.md is a brief overview with clearly signaled, verified one-level-deep references (ticket-intake-workflow.md, self-authored-carve.md), and the workflow in turn links to audit sub-files, giving easy navigation.	5 / 5
	Total	17 / 20 Passed

Description

87%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 is specific, trigger-rich, and clearly answers both what the skill does and when to invoke it, with a distinct niche. It is slightly long and could use a few more natural synonyms, but verbosity is moderate.

Dimension	Reasoning	Score
Specificity	Names the ticket/Issue domain and several concrete actions — 'architectural validation, negative ROI calculation, and duplicate sweeps' plus a gating mechanism; falls just short of the fully comprehensive coverage anchor at 5.	4 / 5
Completeness	Explicitly answers both what (defines the Pre-Execution Reflection Gate, mandates the three checks) and when ('Triggers: Use this skill immediately when assigned a ticket whose authoring you did NOT see').	5 / 5
Trigger Term Quality	Includes natural phrases users/agents would say such as 'assigned a ticket', 'GitHub Issue', and 'before checking out a branch or writing any codebase modifications', but misses a few common synonyms like 'bug report'.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear, narrow niche — a pre-execution gate for externally-authored tickets — with distinct triggers and minimal overlap with other skills.	5 / 5
	Total	18 / 20 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-intake/SKILL.md
Commit: 210c03c

Reviewed: 4 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.