generate-prd

Generate product requirements documents with optional publishing to Confluence or other wiki platforms

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/generate-prd/SKILL.md

Quality

Content

77%

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 a well-sequenced, gated workflow and concrete commands and templates throughout. Its main weakness is progressive disclosure — everything lives in one large file — and some length that could be trimmed.

Suggestions

Move the full PRD template into references/prd-template.md and reference it one level deep from the body, reducing inline bulk and improving progressive_disclosure.

Trim the 'When to Invoke' trigger list since it overlaps the description, to tighten token efficiency.

Dimension	Reasoning	Score
Conciseness	The body is mostly actionable and avoids explaining concepts Claude already knows, but at ~358 lines it embeds a full ~170-line PRD template inline and repeats trigger phrasing from the description ('When to Invoke'), fitting the score-2 anchor 'Mostly efficient but includes some unnecessary explanation or could be tightened'.	2 / 3
Actionability	It provides concrete globs, exact commands (date '+%Y-%m-%d %H:%M', mkdir -p, gh search issues ... --json number,title,body,labels --limit 15), named tools (WebFetch, mcp__claude_ai_Notion__notion-create-pages), and a copy-paste-ready PRD template, matching the score-3 anchor 'Fully executable code/commands; specific examples; copy-paste ready'.	3 / 3
Workflow Clarity	Six phases are clearly sequenced with explicit validation checkpoints — a Phase 4 Review Gate and 'NEVER auto-publish. Always wait for explicit user approval' — plus an Error Handling section acting as a feedback loop, matching the score-3 anchor for clear sequence with explicit validation and error recovery.	3 / 3
Progressive Disclosure	It is a single monolithic file with no bundle files, and the large inline PRD template is content that should be split into a separate reference; this matches the score-2 anchor 'content that should be separate is inline' rather than score 3 (no one-level-deep references exist) or score 1 (it is internally well-organized with no nested references).	2 / 3
	Total	10 / 12 Passed

Description

50%

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 conveys a clear purpose and niche but stops at a score-2 level across all dimensions because it lacks an explicit 'Use when' trigger clause and the natural trigger term 'PRD'. Adding trigger phrasing and concrete action verbs would lift it toward the top of the scale.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when the user asks to write a PRD, product spec, or requirements document,' to convert completeness and trigger_term_quality from 2 to 3.

Include the natural keyword 'PRD' and common variations ('product spec', 'spec doc') directly in the description so user phrasing matches the skill.

List a few more concrete actions (e.g., 'draft, structure, and optionally publish PRDs') to raise specificity and reinforce distinctiveness against generic writing skills.

Dimension	Reasoning	Score
Specificity	The description names the domain and two actions ("Generate product requirements documents" and "optional publishing to Confluence") but does not list multiple specific concrete actions, matching the anchor 'Names domain and some actions, but not comprehensive' rather than the score-3 multi-action example.	2 / 3
Completeness	It clearly states what the skill does but contains no 'Use when...' clause or equivalent explicit trigger guidance; per the judging guidelines a missing explicit trigger caps completeness at 2 even though the 'what' is well stated.	2 / 3
Trigger Term Quality	It includes relevant terms ("product requirements documents", "Confluence", "wiki platforms") but omits the most natural keyword users say — "PRD" — and common variations like "product spec" or "spec doc", fitting the score-2 anchor 'Some relevant keywords but missing common variations'.	2 / 3
Distinctiveness Conflict Risk	The PRD-generation niche is fairly specific, but with no explicit triggers the description could still overlap with general documentation/writing skills, matching the score-2 anchor 'Somewhat specific but could still overlap with similar skills' rather than a clearly-conflict-free score 3.	2 / 3
	Total	8 / 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: huytieu/COG-second-brain
Path: .claude/skills/generate-prd/SKILL.md
Commit: dfbf9e9

Reviewed: 2 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.