epic-breakdown-advisor

Break down epics into user stories with Humanizing Work split patterns. Use when a backlog item is too large to estimate, sequence, or deliver safely.

Quality

72%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/epic-breakdown-advisor/SKILL.md

Quality

Content

77%

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

The content is highly actionable and the workflow is clearly sequenced with strong validation checkpoints, but it is padded by triple-repeated pattern lists and basic-concept explanations, and it does not split its detailed reference material into bundle files.

Suggestions

Remove the triple repetition of the 9 patterns: keep the per-pattern walkthrough in Application and reduce Key Concepts and Examples to brief pointers rather than re-listing all nine.

Trim explanations of concepts Claude already knows (the INVEST acronym walkthrough, the definition of a user story, vertical vs. horizontal slicing) down to the non-obvious domain specifics.

Move the full output template and the detailed pattern reference into `references/` files and link to them one level deep, so SKILL.md reads as an overview rather than a monolith.

Dimension	Reasoning	Score
Conciseness	The skill carries genuine methodology value, but the 9 patterns are repeated three times (Key Concepts, Application, Examples) and basic PM concepts like INVEST and vertical-vs-horizontal slicing are explained at length that Claude already knows.	2 / 3
Actionability	Concrete agent prompts, numbered response options, a worked example per pattern, and a complete copy-paste markdown output template with Given/When/Then give fully executable guidance.	3 / 3
Workflow Clarity	Steps 0 through 3 are clearly sequenced with explicit validation checkpoints: the INVEST pass/fail gates, a critical "STOP" when Valuable fails, and re-split / restart-at-Pattern-1 feedback loops for oversized stories.	3 / 3
Progressive Disclosure	The body is well-sectioned but a ~660-line monolith with the full pattern reference and output template inline; no references/scripts/assets bundle exists, and content that should be split out stays in SKILL.md.	2 / 3
	Total	10 / 12 Passed

Description

67%

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 well-formed with an explicit "Use when" clause covering both what and when, but it names only one core action and its trigger phrasing is somewhat abstract. It also overlaps conceptually with the documented sibling user-story-splitting skill.

Suggestions

Add concrete secondary actions to the description (e.g., validate with INVEST, evaluate splits to reveal low-value work) to lift specificity from one action to several.

Use more natural trigger phrasings a PM would actually say ("split this epic," "too big for a sprint," "before sprint planning") instead of the abstract "too large to estimate, sequence, or deliver safely."

Sharpen the distinction from the sibling `user-story-splitting.md` skill by noting this one drives the full flowchart sequence rather than just explaining the 9 patterns.

Dimension	Reasoning	Score
Specificity	"Break down epics into user stories with Humanizing Work split patterns" names the domain and method, but it describes essentially one action rather than listing multiple concrete actions, so it does not reach the comprehensive level.	2 / 3
Completeness	It clearly answers what ("Break down epics into user stories with Humanizing Work split patterns") and when via an explicit "Use when a backlog item is too large to estimate, sequence, or deliver safely" clause.	3 / 3
Trigger Term Quality	"Use when a backlog item is too large to estimate, sequence, or deliver safely" supplies natural terms a PM would say, but the trigger is somewhat abstract and omits common phrasings like "split this epic" or "too big for a sprint."	2 / 3
Distinctiveness Conflict Risk	The Humanizing Work epic-breakdown niche is fairly distinct, but the body lists a sibling skill `user-story-splitting.md` as "the 9 patterns in detail," creating real overlap risk with that related skill.	2 / 3
	Total	9 / 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 — 13 / 16 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
relative_links	Relative link issues: 1 suspicious	Warning

	Total	13 / 16 Passed

Repository: deanpeters/Product-Manager-Skills
Path: skills/epic-breakdown-advisor/SKILL.md
Commit: 9971018

Reviewed: 3 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.