CtrlK
BlogDocsLog inGet started
Tessl Logo

product-lens-reviewer

Reviews planning documents as a senior product leader -- challenges problem framing, evaluates scope decisions, and surfaces misalignment between stated goals and proposed work. Spawned by the document-review skill.

60

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/product-lens-reviewer/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

86%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 an exemplary instruction-only skill: a tightly sequenced review protocol with concrete heuristics, numeric confidence calibration, explicit exclusions to avoid duplicating sibling lenses, and zero padding. The only meaningful gap is the absence of a worked example showing the expected finding format.

DimensionReasoningScore

Conciseness

The body is lean and dense — 'The most common failure mode is building the wrong thing well' sets the role in one line, and every section (premise challenge, trajectory, alternatives, alignment, prioritization, calibration, exclusions) delivers non-obvious heuristics with no padding or explanation of concepts Claude already knows. Nothing can be trimmed, matching the 'every token earns its place' anchor.

5 / 5

Actionability

The guidance is directly executable: 'For every plan, ask these three questions' with the exact questions, concrete alignment checks ('Orphan requirements', 'Unserved goals', 'Weak links'), and numeric calibration rules ('HIGH (0.80+)', 'Below 0.50: Suppress'). It sits at 'mostly executable... minor gaps' rather than 5 because no worked example of a finding or its expected output format is given.

4 / 5

Workflow Clarity

The sequence is explicit and ordered — premise challenge is marked '(always first)', followed by trajectory, alternatives, alignment, and prioritization — with the confidence-calibration section acting as an explicit gating checkpoint ('Below 0.50: Suppress'). Missing an output-format or verify-then-refine step keeps it at 4 rather than 5; it is well above 3 because checkpoints are explicit, not implicit.

4 / 5

Progressive Disclosure

At ~43 lines with no need for external reference files, the skill uses clear section headers and a well-organized single-file layout, which scores 5 under the simple-skill guideline for short skills requiring no bundle. All content is appropriately inline; there are no nested or buried references.

5 / 5

Total

18

/

20

Passed

Description

58%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 states a clear, third-person 'what' with several concrete capabilities and a well-defined niche, but it omits any explicit 'when to use' trigger guidance, relying instead on delegation to the parent document-review skill. Trigger term coverage is relevant but thin on natural synonyms and user-facing phrasing.

Suggestions

Add an explicit 'Use when...' clause (e.g., 'Use when reviewing planning documents, PRDs, or project proposals for product alignment') to lift completeness and trigger-term quality together.

Include natural user-facing synonyms and artifacts — 'plan review', 'PRD review', 'product requirements', 'roadmap critique' — so the skill surfaces when users describe the task in their own words.

State one or two of the body's distinctive checks (e.g., premise challenge, goal-requirement alignment) as distinguishing triggers to reduce overlap with generic document-review skills.

DimensionReasoningScore

Specificity

Quotes 'Reviews planning documents', 'challenges problem framing', 'evaluates scope decisions', and 'surfaces misalignment' — the domain plus several distinct concrete actions, matching the 'several specific actions; minor gaps in coverage' anchor. It falls short of 5 because coverage is incomplete relative to the body's full protocol (prioritization coherence, trajectory checks), but well above 3's 1-2 actions.

4 / 5

Completeness

The 'what' is clear (reviews planning documents through a product-leadership lens), but there is no 'Use when...' clause — 'Spawned by the document-review skill' only weakly implies when to use it, so completeness is capped at 3 per the judging guidelines. Not 4 because the 'when' is never explicitly stated.

3 / 5

Trigger Term Quality

Relevant keywords like 'planning documents', 'problem framing', 'scope decisions', and 'misalignment' are present, but common user-facing variations and synonyms ('plan review', 'PRD', 'proposal critique') are missing, matching the 'some relevant keywords but missing common variations' anchor. Not 4 because a few natural terms are clearly absent; not 2 because the keywords are domain-specific rather than generic.

3 / 5

Distinctiveness Conflict Risk

It carves a clear niche (product-leadership review, scoped by its parent 'document-review skill') and would rarely be confused with unrelated skills, matching 'mostly distinct; minor overlap risk'. Not 5 because the trigger surface alone overlaps generic 'review my plan/PRD' requests; not 3 because the framing is considerably more specific than 'works with document files'.

4 / 5

Total

14

/

20

Passed

Validation

81%

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

Validation — 13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

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

Warning

Total

13

/

16

Passed

Repository
udecode/plate
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.