CtrlK
BlogDocsLog inGet started
Tessl Logo

recommendation-canvas

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

62

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/recommendation-canvas/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

63%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 canvas template with per-step quality checks and pitfall recovery, but it is padded with duplicated rationale and references template/examples files that are not bundled. Trimming the explanatory prose and either shipping or removing the referenced files would raise quality.

Suggestions

Remove the "## Purpose" section (it duplicates the frontmatter intent verbatim) and trim "### Why This Works" / "### Anti-Patterns" rationale to one line each so the body leads with actionable templates.

Either add the referenced `template.md` and `examples/sample.md` to the bundle or remove the dangling references; if the inlined 10-step templates already cover the fill-in structure, drop the `template.md` pointer to avoid redundancy.

Promote the per-step quality checks into explicit validation gates (e.g., 'Only proceed to the next box when the outcome is measurable and time-bound') so the workflow has enforced checkpoints rather than advisory criteria.

DimensionReasoningScore

Conciseness

The "## Purpose" section duplicates the frontmatter intent verbatim, and the "### Why This Works" / "### Anti-Patterns" rationale assumes Claude needs convincing, fitting 'mostly efficient but includes some unnecessary explanation'; not a 2 because the bulk is actionable template content rather than padding.

3 / 5

Actionability

Each canvas box has a copy-paste markdown template, an explicit format formula (e.g., "[Direction] [Metric] [Outcome] [Context] [Acceptance Criteria]"), a worked example, and quality checks, giving mostly executable guidance; not a 5 because the full worked example is deferred to examples/sample.md, which is not present in the bundle.

4 / 5

Workflow Clarity

A clear 10-step sequence (Step 1–Step 10) with per-step quality checks and a Common Pitfalls error-recovery section gives a clear sequence with most checkpoints present; not a 5 because the quality checks are advisory criteria rather than enforced validation gates within the workflow.

4 / 5

Progressive Disclosure

Sections are well organized and references are signaled one level deep ("Use `template.md`", "See `examples/sample.md`"), but those referenced files are absent from the bundle and the full templates are inlined in SKILL.md, fitting 'some structure but could be better organized'; not a 4 because the dangling template.md reference is a real organization gap, not a minor one.

3 / 5

Total

14

/

20

Passed

Description

83%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 description that clearly answers both what the skill does and when to use it, with natural trigger terms and a defensible niche. Minor room to add synonymous trigger phrases and sharpen the action verbs.

DimensionReasoningScore

Specificity

Quotes "Evaluate an AI product idea across outcomes, hypotheses, risks, and positioning" name the domain plus several concrete evaluation areas, matching the 'lists several specific actions; minor gaps' anchor; not a 5 because a single verb is applied to category areas rather than multiple distinct concrete verbs.

4 / 5

Completeness

It explicitly states what ("Evaluate an AI product idea across outcomes, hypotheses, risks, and positioning") and when ("Use when deciding whether an AI product idea deserves investment or recommendation") with concrete trigger phrases, matching the top anchor; anchor 4 does not fit because the 'when' is already explicit and specific.

5 / 5

Trigger Term Quality

Phrases like "AI product idea," "investment," and "recommendation" are natural terms a user would say, giving good keyword coverage; not a 5 because common synonyms (e.g., "AI feature," "go/no-go," "build vs. buy") are absent.

4 / 5

Distinctiveness Conflict Risk

The "AI product idea deserves investment or recommendation" niche is mostly distinct with minimal conflict risk; not a 5 because it overlaps with sibling PM skills (problem-statement, positioning-statement) referenced as dependencies.

4 / 5

Total

17

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
deanpeters/Product-Manager-Skills
Reviewed

Table of Contents

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.