skill-prd

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

Quality

76%

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 ./.claude/skills/skill-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.

A clearly sequenced, actionable instruction skill with verbatim prompts and a scoring rubric. Its main weaknesses are mild verbosity in the rationale/host blocks and references to bundle files that are not present.

Suggestions

Tighten or move the Codex host-adapter block and the adversarial-review rationale into a reference file so the main body stays lean.

Either create the referenced `skills/blocks/codex-host-adapter.md` and `prd.md` bundle files, or remove/inline those references so navigation is not dangling.

Add a brief explicit validation step in Phase 4 (e.g. confirm the saved file parses / sections are non-empty) to strengthen the workflow's feedback loop.

Dimension	Reasoning	Score
Conciseness	The phase-based bulleted structure is mostly lean, but the adversarial-review rationale ("A single-model PRD has blind spots...") and the Codex host-adapter block are mild padding Claude does not need.	2 / 3
Actionability	Provides copy-paste-ready guidance: verbatim clarification questions, a verbatim adversarial-dispatch prompt, and a concrete 100-point scoring framework with point allocations.	3 / 3
Workflow Clarity	Phases 0–4 are explicitly sequenced with checkpoints (WAIT for user response in Phase 0, score-then-save, and a revise-after-challenge loop in Phase 2.5).	3 / 3
Progressive Disclosure	The body is well-sectioned but references `skills/blocks/codex-host-adapter.md` and a `prd.md` command that do not exist in any bundle directory, leaving navigation dangling.	2 / 3
	Total	10 / 12 Passed

Description

75%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A concise, well-structured description that clearly states both capability and trigger. It is slightly narrow on action breadth and trigger-term coverage but scores well on completeness and distinctiveness.

Dimension	Reasoning	Score
Specificity	Names one concrete action ("Write an AI-optimized PRD") plus a method ("using multi-AI orchestration"), but does not list multiple distinct actions like the level-3 anchor.	2 / 3
Completeness	Explicitly answers both what ("Write an AI-optimized PRD using multi-AI orchestration") and when ("use when scoping a new feature or product") with an explicit Use-when clause.	3 / 3
Trigger Term Quality	"use when scoping a new feature or product" plus "PRD" gives some natural trigger terms, but misses common variations users would say (e.g. "product requirements", "spec out a feature").	2 / 3
Distinctiveness Conflict Risk	The PRD-writing niche with multi-AI orchestration is distinct and unlikely to trigger for unrelated skills.	3 / 3
	Total	10 / 12 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: .claude/skills/skill-prd/SKILL.md
Commit: 9f39f0c

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.