prd

Gated PRD generation — interrogates problem, user, and metric before drafting; refuses to draft on unknowns. Usage: /prd <feature-or-problem>

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.gemini/skills/prd/SKILL.md

Quality

Content

81%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 a well-sequenced, actionable workflow with a strong validation gate and feedback loop, and it appropriately keeps detailed templates in separate files. Structure and conciseness are solid, with only minor organization gaps around the externally referenced, non-bundled asset paths.

Dimension	Reasoning	Score
Conciseness	The body assumes Claude knows what a PRD/RICE is and stays tight, but a few rhetorical flourishes ("a feature wish, not a requirements document", "the CEO wants it" is not evidence) could be trimmed without losing the gating intent.	4 / 5
Actionability	Guidance is concrete and specific — one-by-one questions with anti-pattern callouts, an explicit refusal condition, a required-sections checklist, and a copy-paste RICE command — but the actual draft format is delegated to an external template not shown inline, leaving a minor gap.	4 / 5
Workflow Clarity	Phase 1 → Drafting Gate → Phase 2 → optional Phase 3 is a clear sequence with an explicit validation gate (hard refusal on unknowns), a feedback loop (refuse and output the cheapest way to resolve each open question), and a verification checklist.	5 / 5
Progressive Disclosure	Sections are well-organized with a clearly signaled "Repo Assets" list and a "Related" section at one level of depth, but the references point to external repo-absolute paths rather than local bundle files (none exist under references/scripts/assets), and the asset list self-references the skill's own SKILL.md path.	4 / 5
	Total	17 / 20 Passed

Description

70%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 is specific and distinctive, clearly communicating a gated PRD-generation niche with concrete refusal behavior. Its main weakness is the missing explicit "Use when..." trigger guidance, which leaves the "when to use it" only weakly implied.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user needs to turn a feature idea or problem into a product requirements document (PRD)."

Include common synonyms such as "product requirements", "spec", or "requirements document" so the description matches more of the phrases users naturally say.

Optionally surface the optional RICE-prioritization hook in the description so the capability set reads as more comprehensive.

Dimension	Reasoning	Score
Specificity	"interrogates problem, user, and metric before drafting; refuses to draft on unknowns" names several concrete behaviors (interrogate, gate, refuse, draft), with only minor coverage gaps (e.g. RICE prioritization lives in the body, not the description).	4 / 5
Completeness	The "what" is clear (gated PRD generation with interrogation/refusal), but the only trigger guidance is the invocation line "Usage: /prd <feature-or-problem>" — there is no explicit "Use when..." clause, so per the judging guideline "when" is only weakly implied and completeness is capped at 3.	3 / 5
Trigger Term Quality	"PRD", "PRD generation", "feature", and "problem" are natural terms a product person would say, but common synonyms like "product requirements", "spec", or "requirements document" are absent.	4 / 5
Distinctiveness Conflict Risk	"Gated PRD generation" with "refuses to draft on unknowns" and the /prd command is a clear niche with distinct triggers and minimal overlap risk with adjacent skills.	5 / 5
	Total	16 / 20 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: alirezarezvani/claude-skills
Path: .gemini/skills/prd/SKILL.md
Commit: 19392f7

Reviewed: ~12 hours 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.