generate-prd

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

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

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 content is highly actionable and clearly sequenced with strong validation checkpoints, but it leans long due to the large inline template and does not offload detail to separate reference files.

Suggestions

Move the full PRD template into a references file (e.g. references/prd-template.md) and link to it from the body to improve progressive disclosure and reduce token load.

Tighten or remove the "When to Invoke" section, which largely duplicates the frontmatter description and trigger phrasing.

Condense the publishing sub-sections (Confluence/Notion/HackMD) into a single parameterized block since they share the same approve-then-publish pattern.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with a clear phased structure, but the ~170-line inline PRD template and duplicated "When to Invoke" triggers add bulk that could be tightened, matching anchor 2's "mostly efficient but could be tightened."	2 / 3
Actionability	Concrete commands (date, mkdir -p, gh search issues), named tools (ToolSearch, WebFetch, specific MCP tool names), real API endpoints, and a full copy-paste PRD template make the guidance fully executable, matching anchor 3.	3 / 3
Workflow Clarity	The six-phase sequence is explicit with a review-gate checkpoint ("NEVER auto-publish. Always wait for explicit user approval"), plus fallback and error-handling tables, matching anchor 3's clear sequence with validation steps and feedback loops.	3 / 3
Progressive Disclosure	No bundle files exist and the 365-line body keeps the large PRD template inline rather than splitting it into a referenced template file, matching anchor 2's "content that should be separate is inline" despite good section organization.	2 / 3
	Total	10 / 12 Passed

Description

57%

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 clearly conveys the skill's purpose and niche but stops short of the strongest examples: it lists limited actions, omits common trigger phrasings, and lacks an explicit when-to-use clause.

Suggestions

Add an explicit "Use when..." clause naming trigger phrases users would say (e.g. "Use when the user asks for a PRD, product spec, or requirements document").

Expand the action list to mention concrete capabilities (e.g. draft, structure, and publish PRDs) rather than only "generate" and "publish".

Include common shorthand triggers like "PRD", "spec doc", and "feature spec" to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Quotes "Generate product requirements documents" and "optional publishing to Confluence or other wiki platforms" name the domain and a couple of concrete actions, but the action set is not comprehensive — closer to anchor 2 than the multi-action anchor 3.	2 / 3
Completeness	It states what the skill does (generate + publish PRDs) but provides no explicit "Use when..." trigger clause; per the judging guidelines a missing trigger clause caps completeness at 2.	2 / 3
Trigger Term Quality	Terms like "product requirements documents", "Confluence", and "wiki" are relevant but omit common user phrasings ("PRD", "spec", "requirements doc"), matching anchor 2's "some relevant keywords but missing common variations."	2 / 3
Distinctiveness Conflict Risk	The PRD-generation-plus-wiki-publishing niche is specific and unlikely to fire for unrelated skills, matching anchor 3's "clear niche with distinct triggers."	3 / 3
	Total	9 / 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
Commit: 5e9851c

Reviewed: 14 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.