recommendation-canvas

Evaluate an AI product idea across outcomes, hypotheses, risks, and positioning. Use when deciding whether an AI solution deserves investment or recommendation.

Quality

70%

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/recommendation-canvas/SKILL.md

Quality

Content

65%

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

The body is highly actionable with concrete fill-in templates and examples per step, but it is verbose (duplicated intent, explained-known-concepts), lacks inter-step validation checkpoints, and references bundle files (template.md, examples/sample.md) that are not actually provided. Adding the missing bundle files and a validation loop between steps would resolve the two weakest dimensions.

Suggestions

Provide the referenced bundle files (template.md, examples/sample.md) in the skill directory or remove the dangling references, since references/, scripts/, and assets/ are empty.

Add an explicit validation checkpoint between steps (e.g., 'After Step 4, confirm every outcome has a measurable metric before proceeding') rather than only per-section quality checks.

Delete the duplicated Purpose intent paragraph (it repeats the frontmatter intent field) and remove definitional asides like the SMART acronym expansion.

Dimension	Reasoning	Score
Conciseness	The ~380-line body provides valuable canvas scaffolding but duplicates the intent paragraph verbatim (Purpose repeats the frontmatter intent) and explains concepts Claude already knows (e.g., unpacking the SMART acronym), so it is mostly efficient yet could be tightened.	2 / 3
Actionability	Each step gives an explicit fill-in formula (e.g., '[Direction] [Metric] [Outcome] [Context] [Acceptance Criteria]'), a worked example, and concrete quality checks, making the guidance copy-paste ready for an instruction skill.	3 / 3
Workflow Clarity	The 10 steps are clearly sequenced, but there are no explicit validation checkpoints between steps—only per-section 'Quality checks' bullets with no validate-then-proceed loop—so checkpoints are implicit rather than enforced.	2 / 3
Progressive Disclosure	The body references template.md and examples/sample.md but no bundle files exist in references/, scripts/, or assets/, so those references are non-functional and the full canvas template is inlined rather than split out.	2 / 3
	Total	9 / 12 Passed

Description

75%

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 cleanly states both what the skill does and when to use it with a clear, distinct niche, but its action verbs are generic and its trigger terms miss several common user phrasings. Tightening specificity and adding natural keywords like 'go/no-go' or 'pitch' would lift the weaker dimensions.

Suggestions

Replace the single verb 'Evaluate' with multiple concrete actions (e.g., 'Score, pressure-test, and structure an AI product idea across outcomes, hypotheses, risks, and positioning').

Broaden trigger terms with phrasings users actually say: 'go/no-go decision', 'pitch an AI feature to execs', 'business case for an AI product', 'should we invest in this AI idea'.

Dimension	Reasoning	Score
Specificity	It names four concrete assessment domains (outcomes, hypotheses, risks, positioning) but uses a single generic verb ('evaluate across') rather than multiple distinct concrete actions, matching the 'names domain and some actions' anchor rather than level 3.	2 / 3
Completeness	It explicitly answers both what it does ('evaluate across outcomes, hypotheses, risks, and positioning') and when to use it ('Use when deciding whether an AI solution deserves investment or recommendation').	3 / 3
Trigger Term Quality	Phrases like 'AI solution deserves investment or recommendation' are relevant but miss common user variations such as 'should we build', 'pitch', 'go/no-go', or 'business case', so coverage is partial.	2 / 3
Distinctiveness Conflict Risk	The strategic AI-investment-recommendation niche is distinctive and the triggers are unlikely to fire for unrelated skills; voice is third person.	3 / 3
	Total	10 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: deanpeters/Product-Manager-Skills
Path: skills/recommendation-canvas/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.