eol-readiness-advisor

Run a go/no-go assessment for retiring a product or feature, then right-size the effort. Use when someone says "we should probably kill this" and nobody has made the call.

Quality

83%

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.

A well-engineered interactive advisory skill: concrete prompts, an explicit sequenced workflow with validation and feedback loops, and clear cross-skill navigation. The main lever is length — the two full worked dialogues and inline reference material could be trimmed or split to tighten token efficiency.

Suggestions

Condense Examples A and B to the trigger, the dial decision, and the verdict line each — the surrounding dialogue restates guidance already in the Application section.

Consider moving the Common Pitfalls catalog and/or the full Examples into a separate reference file referenced one level deep, keeping SKILL.md as the overview-plus-workflow.

Dimension	Reasoning	Score
Conciseness	The body is information-dense and assumes Claude's competence — it defines EOL-specific vocabulary (lifecycle gates, retire/hold signals) rather than padding with concepts Claude already knows — though the two full multi-turn dialogue examples (A and B) could be trimmed without losing the modeling value.	4 / 5
Actionability	It gives literal agent prompts to ask, a fill-in verdict template, a numbered next-steps menu, and concrete tables (intensity dial, trigger watch-fors); for an instruction-only skill the guidance is copy-paste ready and covers the common cases.	5 / 5
Workflow Clarity	A clear four-question-plus-final-step sequence carries explicit validation checkpoints (trigger-type watch-for table, obligation check asked early, path-readiness as a go/no-go input) and feedback loops for dial-up/dial-down and unready landing paths.	5 / 5
Progressive Disclosure	Structure is strong with clear sections and one-level-deep, clearly signaled related-skill references; however the bulk (full dialogue examples, pitfall catalog) lives inline in a single ~440-line file with no split detail files, leaving minor organization gaps.	4 / 5
	Total	18 / 20 Passed

Description

78%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.

A strong, third-person description with an explicit, natural trigger clause and a clear what/when pairing. Its only real gap is keyword coverage — it leans on one trigger phrasing and misses common synonyms (sunset, deprecate, EOL) that would broaden discoverability.

Suggestions

Add common synonyms to the trigger clause, e.g. "Use when someone says 'we should probably kill this' or mentions sunsetting, deprecating, or end-of-lifing a product or feature."

Surface one more concrete capability in the what clause (e.g. naming obligations/intensity) to lift specificity beyond two actions.

Dimension	Reasoning	Score
Specificity	"Run a go/no-go assessment" and "right-size the effort" name the domain (retiring a product or feature) plus two concrete actions, but coverage is not comprehensive — the intensity dial, stakeholder naming, and obligation checks that the body emphasizes are absent from the description.	3 / 5
Completeness	It explicitly answers both what ("go/no-go assessment ... right-size the effort") and when ("Use when someone says 'we should probably kill this' and nobody has made the call") with a concrete quoted trigger phrase, matching the top anchor.	5 / 5
Trigger Term Quality	It includes a highly natural trigger phrase ("Use when someone says 'we should probably kill this'") plus "retiring a product or feature", but omits common synonyms users also say — sunset, deprecate, end of life, EOL — so a few natural terms are missing.	4 / 5
Distinctiveness Conflict Risk	The EOL/retirement niche plus the specific "nobody has made the call" trigger is mostly distinct with minor overlap risk against generic go/no-go or portfolio-decision skills.	4 / 5
	Total	16 / 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: 9 suspicious	Warning

	Total	14 / 16 Passed

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