epic-create

Authoritative protocol for authoring an Epic body — the creation-side dual of `ticket-create` + entry partner of `epic-review`/`epic-resolution`. Enforces: epic body = problem-scope + intended-solution (NOT pseudo-subs / ACs); ACs live in the SUB tickets; subs are LINKED via `update_issue_relationship` + added incrementally; the body MUST NOT hardcode a sub-list (it stales out → FAIL). Triggers: before creating an Epic (a parent issue labeled `epic`) via `create_issue`, or before decomposing one into sub-tickets.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

85%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.

The body is a lean, well-structured pointer to a single real reference with an unambiguous single-step workflow. Its lone gap is actionability: the body delegates all authoring specifics to the reference rather than carrying any executable guidance inline.

Suggestions

Add a one-line inline essence of the core rule (e.g. 'Epic body = problem-scope + intended-solution only; never ACs or a hardcoded sub-list') so the skill carries a minimum of executable guidance before delegating to the reference.

Fix the reference path mismatch: the body cites `.agents/skills/epic-create/references/epic-create-workflow.md` while the bundle exposes `references/epic-create-workflow.md`, so the signaled path may not resolve as written.

Dimension	Reasoning	Score
Conciseness	Two lines with zero padding and no explanation of concepts Claude already knows — every token earns its place, matching the lean-and-efficient anchor exactly rather than the 'could be tightened' 2.	3 / 3
Actionability	It names a concrete tool (`view_file`) and a specific path, which is executable, but the actual authoring guidance lives one indirection away in the reference rather than as copy-paste-ready inline specifics, so it lands at 'some concrete guidance but incomplete' rather than the anchor-3 fully-executable-inline bar.	2 / 3
Workflow Clarity	Per the simple-skill scoring note, a single unambiguous action can score 3: the body gives one clear sequenced directive — trigger, read the reference, adhere, then proceed — with no ambiguity.	3 / 3
Progressive Disclosure	Scored against the actual bundle: SKILL.md is a concise overview pointing to a single one-level-deep, clearly signaled reference (`references/epic-create-workflow.md`, which exists), matching the clear-overview-with-well-signaled-references anchor.	3 / 3
	Total	11 / 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.

The description is specific, complete, and well-differentiated, with explicit trigger guidance and concrete enforcement actions. Its only weakness is trigger-term quality, which relies on internal ticketing jargon rather than broadly natural user phrasings.

Suggestions

Broaden trigger_term_quality by adding common layperson phrasings a user would actually say (e.g. 'when breaking a large feature into smaller tickets', 'when writing the parent ticket for a multi-part effort') alongside the existing 'create_issue'/'decompose' jargon.

Consider trimming the dense enforcement preamble ('Enforces: ... it stales out → FAIL') so the description leads with the trigger scenarios, keeping it concise per the anti-verbosity guideline.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions tied to the domain — 'authoring an Epic body', 'subs are LINKED via `update_issue_relationship`', 'added incrementally', 'MUST NOT hardcode a sub-list', 'create_issue' — matching the anchor for several specific concrete actions rather than the partial coverage of a 2.	3 / 3
Completeness	Clearly answers what it does (authoring protocol with enforcement rules) and when to use it via an explicit 'Triggers:' clause with two concrete scenarios, satisfying the 'what AND when' anchor and the equivalent-trigger-guidance guideline.	3 / 3
Trigger Term Quality	An explicit 'Triggers:' clause gives relevant phrases ('before creating an Epic', 'decompose one into sub-tickets'), but the terms lean on internal ticketing jargon rather than the broad layperson variations the anchor-3 example shows, so it sits at 'some relevant keywords' above a 1.	2 / 3
Distinctiveness Conflict Risk	It carves a clear niche as the 'creation-side dual of `ticket-create`' and 'entry partner of `epic-review`/`epic-resolution`' with explicit disambiguation, making it 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/epic-create/SKILL.md
Commit: b4a1b58

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.