eol-process

Run a product sunset end to end — decide, align, plan, prepare, announce, close. Use when you need the whole EOL process, not just one artifact.

Quality

90%

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

88%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 well-sequenced, highly actionable orchestration guide with explicit decision-point validation and feedback loops. Its weaknesses are mild redundancy across the Key Concepts, Application, and End-to-End summary sections, and references to bundle files (template.md, examples) that are signaled but not actually shipped.

Suggestions

Either ship the referenced bundle files (template.md, examples/sample.md, examples/sample-industrial.md) or remove the references, since progressive_disclosure currently points at files that don't exist.

Tighten the redundancy between the Key Concepts level/intensity tables, the Application section, and the End-to-End ASCII summary so each section adds distinct information rather than re-sequencing the same phases.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and directive, assuming Claude's competence without explaining what an EOL or a stakeholder is, but the level table, Application section, and the End-to-End ASCII summary re-state sequencing already covered in the per-phase sections, so minor redundancy could be trimmed. Not a 5 because of that repetition; not a 3 because nothing explains basic concepts Claude already knows.	4 / 5
Actionability	As an instruction-only orchestration skill it gives concrete, specific guidance: numbered phase activities, explicit decision-point routing (Go/Hold/Harvest, return to Phase 1), and usable tests like the 'sticky-note test' and 'ask a rep who they'd call about a churn threat'. Per the rubric's instruction-skill note, absence of code is not penalized when guidance is this actionable.	5 / 5
Workflow Clarity	Six phases are explicitly sequenced with a decision point after each acting as a validation checkpoint, with real feedback loops (DP2 returning to Phase 1, DP4 gating DP5) and an end-to-end ASCII summary confirming the route — clear validation steps and error-recovery loops throughout.	5 / 5
Progressive Disclosure	Sections are well-organized with clear navigation and one-level-deep references to sibling skills, and template.md / examples are signaled. Not a 5 because no bundle files actually exist (references/, scripts/, assets/ are empty) and the referenced template.md and examples/*.md are not present, so the disclosure is signaled but not realized; not a 3 because structure and signaling are otherwise good.	4 / 5
	Total	18 / 20 Passed

Description

92%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, complete, and distinctive, naming six concrete phases and providing an explicit 'Use when' trigger. Its only weakness is modest trigger-term variety, relying on 'EOL process' and 'product sunset' without synonyms like retire, deprecate, or end-of-life.

Suggestions

Broaden trigger-term coverage by adding natural synonyms users might say, e.g. 'Use when retiring, deprecating, or sunsetting a product end to end, or running the full end-of-life process.'

Consider adding a cue for the mid-stream rescue scenario in the description, since 'rescuing a sunset already in motion' is a distinctive use case captured in the body but not the description.

Dimension	Reasoning	Score
Specificity	Lists six concrete, named actions — 'decide, align, plan, prepare, announce, close' — giving comprehensive coverage of the orchestration steps rather than vague language.	5 / 5
Completeness	Clearly answers 'what' (run a product sunset end to end across six named phases) and explicitly answers 'when' with a concrete 'Use when you need the whole EOL process, not just one artifact' trigger.	5 / 5
Trigger Term Quality	Includes a natural 'Use when you need the whole EOL process' trigger and the terms 'product sunset' and 'EOL process', but misses common synonyms users might say (retire, deprecate, end-of-life, sunset) and file-like concrete cues. Not a 5 because keyword variety is limited; not a 3 because a genuine natural trigger phrase is present.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche — full end-to-end product sunset orchestration — with distinct triggers ('the whole EOL process, not just one artifact') that minimize overlap with single-artifact sibling skills.	5 / 5
	Total	19 / 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: 14 suspicious	Warning

	Total	14 / 16 Passed

Repository: deanpeters/Product-Manager-Skills
Path: skills/eol-process/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.