eol-stakeholder-sequence

Plan who to talk to about a sunset, in what order, and what each conversation must cover. Use when an EOL decision is made and you want the landmines found before the announcement.

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

82%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 a strong, single-purpose instructional skill: highly actionable with concrete templates and an explicit ordered workflow. It loses points for rhetorical padding and for referencing example files that are absent from the bundle. Adding lightweight validation checkpoints and shipping the missing example files would lift the two 4s.

Suggestions

Add explicit validation checkpoints between steps (e.g. 'Confirm the chosen level with the user before ordering stops' and 'Verify every stop has a defined output before marking parallel/sequential').

Either include the referenced examples/sample.md and examples/sample-industrial.md in the bundle or remove the Examples section references so progressive disclosure points only at files that exist.

Trim a few of the more rhetorical illustrative passages to tighten token efficiency without losing the operational guidance.

Dimension	Reasoning	Score
Conciseness	Assumes Claude's intelligence (no over-explanation of what EOL is) and stays mostly lean, but several vividly rhetorical passages ('you will have told forty people about a plan that a single contract clause invalidates') add color beyond pure instruction and could be trimmed.	4 / 5
Actionability	Provides fully concrete, executable guidance: a level-selection table, the canonical ordered stop list, a five-field per-stop template, named red flags, and the 4-8 word sticky-note rule — enough to act on without further reference.	5 / 5
Workflow Clarity	A clear sequenced workflow (Set level -> Order stops -> Build each stop -> Mark parallel/sequential -> Assumptions -> Offer next) is present, but it lacks explicit validation checkpoints (e.g. confirm the chosen level before ordering stops, verify each stop has a defined output).	4 / 5
Progressive Disclosure	Well-organized sections with clearly signaled one-level-deep references to examples and related skills, but the referenced example files (examples/sample.md, examples/sample-industrial.md) are not present in this skill bundle, leaving the references partially unfulfilled.	4 / 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 well-crafted: third-person, concise, with explicit what-and-when structure and natural trigger terms. It carves a distinct niche with low conflict risk. Minor gaps in trigger-term synonyms and capability enumeration keep two dimensions at 4 rather than 5.

Suggestions

Add common synonyms to the trigger clause, e.g. 'end of life' or 'retiring a product', so the description fires on a wider range of natural phrasings.

Consider naming one or two more concrete capabilities (e.g. 'right-sizes the sequence to the blast radius') to push specificity toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	Names the EOL/sunset domain and several concrete actions ('who to talk to', 'in what order', 'what each conversation must cover', 'landmines found'), but stops short of a fully enumerated capability list that would warrant a 5.	4 / 5
Completeness	Explicitly answers both what ('Plan who to talk to... in what order, and what each conversation must cover') and when ('Use when an EOL decision is made and you want the landmines found before the announcement') with concrete trigger phrasing.	5 / 5
Trigger Term Quality	Includes natural trigger phrases users would say ('EOL decision', 'sunset', 'before the announcement') with the synonym EOL/sunset, but misses common variations like 'end of life' or 'retiring a product'.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (EOL conversation sequencing) with distinct triggers unlikely to fire for unrelated skills, presenting minimal conflict risk.	5 / 5
	Total	18 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 6 suspicious	Warning

	Total	14 / 16 Passed

Repository: deanpeters/Product-Manager-Skills
Path: skills/eol-stakeholder-sequence/SKILL.md
Commit: 1b5a524

Reviewed: 1 day 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.