CtrlK
BlogDocsLog inGet started
Tessl Logo

wagneripjr/requirements-elicitation

Analyse PRDs and feature specs for gaps, generate clarifying questions for PMs and engineers, and assess technical risk before implementation

70

Quality

88%

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

Overview
Quality
Evals
Security
Files

Quality

Content

71%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-structured, actionable skill body with strong progressive disclosure and a clear phased workflow, slightly hampered by redundancy across its philosophy, pitfalls, and best-practices sections. Bundle files are real and one level deep.

Suggestions

Consolidate the repeated 'elicit, don't invent' message: merge Core Philosophy / Key Principles / Common Pitfalls / Best Practices / Success Criteria so the principle is stated once and illustrated once.

Trim the 'Adapting to Document Types' section to a compact table, since the differentiation across PRDs, specs, stories, roadmaps, and one-pagers is largely 'expect more gaps at higher levels'.

Add an explicit validation/check step to the workflow (e.g. re-read gaps against the source document to confirm each gap is real and not already specified) to strengthen feedback-loop clarity.

DimensionReasoningScore

Conciseness

Mostly efficient but the 'ELICIT, DON'T INVENT' philosophy is restated across Core Philosophy, Key Principles, Common Pitfalls, Best Practices, and Success Criteria, adding padding that could be consolidated without losing clarity.

3 / 5

Actionability

Provides a concrete phased workflow with explicit file loads (references/technical_dimensions.md, assets/gap_analysis_template.md) and good/bad example processes, though the executable specifics of the templates themselves are deferred to reference files.

4 / 5

Workflow Clarity

Phases 1–5 are clearly sequenced with explicit gating ('CRITICAL: Do not create these detailed technical artifacts in Phase 1-4') and a referenced checklist, but there is no explicit validate→fix→retry feedback loop since the workflow is read-only analysis.

4 / 5

Progressive Disclosure

Well-signaled one-level-deep references: dedicated 'Reference Files' and 'Asset Files' sections each describe contents and 'When to use', and all referenced paths (references/*, assets/*) resolve to real bundle files with no nesting.

5 / 5

Total

16

/

20

Passed

Description

100%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: third-person voice, concrete actions, comprehensive natural trigger terms, and an explicit 'Use when' clause covering both what and when. It is distinct and unlikely to conflict with sibling skills.

DimensionReasoningScore

Specificity

Names multiple concrete actions — 'analyzing product documents', 'identify gaps', 'generate clarifying questions for PMs and engineers', and 'assess technical risks' — giving comprehensive coverage rather than a minimal or partial list.

5 / 5

Completeness

Explicitly answers both 'what' (analyze docs, identify gaps, generate questions, assess risks) and 'when' with a dedicated 'Use when asked to extract technical requirements, review specs, identify what's missing, or prepare clarifying questions' trigger clause.

5 / 5

Trigger Term Quality

Covers natural document-type synonyms users actually say — 'PRDs, feature specs, user stories, roadmaps, one-pagers' — plus natural trigger verbs like 'extract technical requirements', 'review specs', and 'identify what's missing'.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche — bridging PM documents to implementation via elicitation — with distinct triggers unlikely to fire for unrelated skills; no overlap risk with generic analysis skills.

5 / 5

Total

20

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Reviewed

Table of Contents