skill-prd

Write an AI-optimized PRD using multi-AI orchestration — use when scoping a new feature or product

Quality

68%

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 ./skills/skill-prd/SKILL.md

Quality

Content

75%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 well-structured, mostly lean instruction skill with a clear phased workflow, concrete prompts, and an adversarial-review feedback loop; its main weakness is referencing bundle paths that do not exist in the provided skill folder.

Suggestions

Either include skills/blocks/codex-host-adapter.md and the prd.md command file in the bundle or remove/soften those references so navigation is not broken.

Make the adversarial-review feedback loop a mandatory checkpoint (not just "recommended") and specify the revise→re-validate cycle explicitly.

Add a concrete output-format spec for the saved PRD (filename convention, markdown structure) to close the actionability gap.

Dimension	Reasoning	Score
Conciseness	The body is lean and avoids explaining concepts Claude already knows (no definition of a PRD); the host-adapter and STOP blocks are operational and earn their tokens, with only minor trimmable redundancy.	4 / 5
Actionability	Provides concrete guidance: a full clarification prompt, an 8-section PRD structure with FR-001 format, point allocations for self-scoring, and a ready-to-use adversarial-review dispatch prompt; minor gaps remain in specifying output format.	4 / 5
Workflow Clarity	Phases 0–4 are clearly sequenced with explicit gating checkpoints ("WAIT for user response", "AFTER drafting but BEFORE self-scoring, dispatch") and a revise-after-challenge feedback loop; the loop is skippable rather than mandatory, keeping it just below 5.	4 / 5
Progressive Disclosure	Content is well-organized into clearly headed phases with no monolithic wall of text; however two referenced paths (skills/blocks/codex-host-adapter.md and the prd.md command) are not present in the bundle, a minor navigation gap.	4 / 5
	Total	16 / 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 cleanly states what the skill does and when to use it with a concrete trigger, but the action list is thin and it lacks common synonyms (e.g. "product requirements document", "spec") that users naturally say.

Suggestions

Expand the action coverage beyond a single verb, e.g. "Draft, structure, and self-score an AI-optimized PRD".

Add natural trigger synonyms: "use when writing a PRD, product requirements document, or spec for a new feature or product".

Clarify the multi-AI orchestration angle concretely (e.g. "dispatches a second provider for adversarial review") to sharpen distinctiveness.

Dimension	Reasoning	Score
Specificity	Names the domain and a concrete action ("Write an AI-optimized PRD") plus a method ("multi-AI orchestration"), but coverage of actions is not comprehensive — it stops at one verb.	3 / 5
Completeness	Explicitly answers both what ("Write an AI-optimized PRD using multi-AI orchestration") and when ("use when scoping a new feature or product"); the when clause is concrete but a single trigger phrase rather than multiple.	4 / 5
Trigger Term Quality	Includes natural terms like "PRD", "scoping a new feature", and "product", but omits common synonyms a user might say such as "product requirements document", "spec", or "requirements doc".	3 / 5
Distinctiveness Conflict Risk	The PRD-writing niche with "multi-AI orchestration" framing is mostly distinct with clear triggers; minor overlap risk with generic orchestration or writing skills keeps it just below 5.	4 / 5
	Total	14 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: nyldn/claude-octopus
Path: skills/skill-prd/SKILL.md
Commit: 242e51d

Reviewed: 3 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.