Tessl • The package manager for agent skills

SkillPublic

prd

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

Quality

82%

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

Quality

Content

96%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 lean, highly actionable workflow: exact questions, a hard drafting gate with a defined failure output, a required-sections checklist, and a concrete optional command. The only weakness is reference signaling — repo asset paths are listed in a trailing section rather than linked at point of use.

Dimension	Reasoning	Score
Conciseness	The body never explains what a PRD is or other known concepts; every line instructs ("Walk these one at a time. Do not batch them.", "Keep it to ~2 pages"). Asides like '"the CEO wants it" is not evidence' are compact calibration, not padding — every token earns its place.	5 / 5
Actionability	Fully concrete: five exact forcing questions with expected evidence types, a hard refusal rule with a defined fallback output, a required-sections checklist, and a copy-paste command ("python3 product-team/skills/product-manager-toolkit/scripts/rice_prioritizer.py features.csv --capacity 20"). As an instruction-only skill, the guidance is fully executable.	5 / 5
Workflow Clarity	Clear three-phase sequence with an explicit validation checkpoint (the drafting gate: "Refuse to draft the PRD if the answer to question 1 (problem), 2 (user), or 3 (metric) is unknown"), a feedback loop on failure (output open questions and the cheapest way to answer each), and a checklist to verify the draft ("emit the checklist at the end and mark each"). This matches the anchor-5 profile of sequence + validation + recovery + checklist.	5 / 5
Progressive Disclosure	The body stays lean and points to one-level-deep external assets listed with full paths under "Repo Assets (verified paths)" (PRD template, patterns reference, RICE tool). Not 5: the references are collected in a bottom-of-file section rather than signaled at their point of use ("Use the repo template as the skeleton" does not link the template path), and the referenced files live outside this bundle (no references/ or scripts/ directories present), so navigation depends on repo paths that cannot be verified here.	4 / 5
	Total	19 / 20 Passed

Description

62%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 concise, third-person, and names concrete gated actions, with a distinctive niche. Its weakness is trigger guidance: no "Use when..." clause and no expansion of "PRD" into the natural phrases a user would say, which caps completeness and trigger-term quality.

Suggestions

Add a trigger clause, e.g. "Use when the user asks for a PRD, product requirements document, or product spec for a new feature or initiative."

Spell out "PRD" at least once ("product requirements document") so the description matches users who say the full phrase rather than the acronym.

Mention the deliverable's shape briefly (e.g. "...drafts a ~2-page PRD with required sections") to round out capability coverage.

Dimension	Reasoning	Score
Specificity	"interrogates problem, user, and metric before drafting; refuses to draft on unknowns" lists several concrete actions (interrogate, gate/refuse, draft) with a specific gating behavior. It is not 3 (more than 1-2 actions named) nor 5 (coverage of the drafting output — sections, user stories, success metric checklist — is absent from the description).	4 / 5
Completeness	The "what" is clear ("Gated PRD generation — interrogates problem, user, and metric before drafting; refuses to draft on unknowns"), but the "when" is missing: "Usage: /prd <feature-or-problem>" is invocation syntax, not a trigger clause like "Use when the user asks for a PRD or feature spec". Per the rubric guideline, a missing 'Use when...' clause caps completeness at 3.	3 / 5
Trigger Term Quality	Relevant keywords are present ("PRD generation", "problem", "user", "metric", "feature-or-problem") but common variations are missing: the expansion "product requirements document", and natural phrases like "product spec" or "write a PRD". It sits between anchor 3 (some keywords, missing synonyms) and anchor 4, but the gaps are more than "a few".	3 / 5
Distinctiveness Conflict Risk	"Gated PRD generation" with an evidence-gating refusal behavior is a clear niche with distinct triggers; minimal overlap risk with generic writing or doc skills. It clearly matches the anchor-5 example's profile of a distinct, well-bounded skill.	5 / 5
	Total	15 / 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
Revision: 27cfcd0

Reviewed: 18 hours ago

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.

prd

Table of Contents

Is this your skill?