func-req
Use when tech design is reviewed and approved. Generates functional requirements docs (EA then GA) from the approved PRD and tech design. Runs both milestones sequentially in one pass.
64
76%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.claude/skills/func-req/SKILL.mdQuality
Discovery
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 has a clear 'Use when' trigger and a distinct niche in the product development workflow, which are strong points. However, it relies on domain-specific acronyms (EA, GA, PRD) without explanation and could benefit from more concrete action descriptions and natural language trigger terms that users might actually say.
Suggestions
Expand acronyms on first use (e.g., 'Product Requirements Document (PRD)', 'Early Access (EA)', 'General Availability (GA)') and add natural language variations users might say, such as 'write requirements', 'create FRD', or 'requirements document'.
Add more specific actions describing what the generated documents contain, e.g., 'Generates functional requirements docs including feature specs, acceptance criteria, and milestone deliverables'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (functional requirements docs) and some actions (generates EA then GA from PRD and tech design, runs milestones sequentially), but doesn't detail what specific content or structure these docs contain or what 'running milestones' concretely entails. | 2 / 3 |
Completeness | Clearly answers both what ('Generates functional requirements docs (EA then GA) from the approved PRD and tech design, runs both milestones sequentially') and when ('Use when tech design is reviewed and approved') with an explicit trigger clause. | 3 / 3 |
Trigger Term Quality | Includes some relevant terms like 'functional requirements docs', 'PRD', 'tech design', 'EA', 'GA', and 'milestones', but these are somewhat jargon-heavy. Missing natural user phrases like 'write requirements', 'create FRD', or 'requirements document'. | 2 / 3 |
Distinctiveness Conflict Risk | The description carves out a very specific niche: generating functional requirements documents from approved PRDs and tech designs, with the EA/GA milestone structure. This is unlikely to conflict with other skills due to its specificity in the product development workflow. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-crafted skill with strong actionability and workflow clarity. The step-by-step process is clearly sequenced with proper precondition checks, stop conditions with exact error messages, and an approval feedback loop. Minor improvements could be made in conciseness (trimming redundant notes) and progressive disclosure (extracting the story template into a reference file if the skill grows).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient and avoids explaining concepts Claude already knows, but some sections could be tightened — e.g., the story template markdown block is verbose with inline comments, and the Notes section restates things already covered in the steps. | 2 / 3 |
Actionability | Highly actionable: provides exact file paths, specific frontmatter YAML, a concrete story template with all fields, precise stop conditions with exact error messages, and clear citation rules. The guidance is copy-paste ready and leaves little ambiguity. | 3 / 3 |
Workflow Clarity | The 6-step workflow is clearly sequenced with explicit precondition checks (status: approved, ⚡ items resolved), validation gates (stop conditions with specific error messages), and a feedback loop (prompt for approval → set status). The approval step before proceeding is a proper checkpoint. | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear sections and headers, but it's a single monolithic file with no references to supporting documents. The story template and rules could potentially be split into a reference file, though for a skill of this length (~100 lines) it's borderline acceptable. | 2 / 3 |
Total | 10 / 12 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.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- PagerDuty/ai-forward-planning
- Commit
585e8a6
- 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.