amazon-working-backwards

Write a PR/FAQ for a product idea using Amazon's Working Backwards process. Start from the customer press release and work backward to what needs to be built. Use when validating whether an idea is worth building before committing to a spec.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

85%

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 well-sequenced, with a ready-to-use prompt template and an explicit decision checkpoint. The one area with room to improve is conciseness, where a few introductory rhetorical lines could be trimmed.

Suggestions

Tighten the opening two paragraphs by removing editorializing flourishes (e.g., "You have an idea — maybe...") and lead directly with the process, to push conciseness toward a full 3.

If the skill grows, consider moving the FAQ coverage lists and rules into a separate reference file to keep the core template in focus and preserve the lean overview.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and assumes Claude's competence, but a few editorializing lines ("If you can't write a compelling press release, the idea isn't ready" and "You have an idea — maybe...") add rhetorical flourish beyond strict guidance, matching the score-2 anchor rather than a fully lean score-3.	2 / 3
Actionability	It provides a complete, copy-paste-ready prompt template with explicit PR/FAQ structure, external/internal FAQ guidance, a numbered five-test assessment, and concrete rules, matching the score-3 anchor for an instruction-only skill.	3 / 3
Workflow Clarity	The process is clearly sequenced (Press Release -> FAQs -> Working Backwards Assessment) with a numbered checklist and an explicit kill/keep decision checkpoint, matching the score-3 anchor.	3 / 3
Progressive Disclosure	This single-file, well-organized skill has no external references and no bundle files, so it qualifies for the score-3 simple-skill exception via clean section organization (Prompt Template, Tips) rather than file splitting.	3 / 3
	Total	11 / 12 Passed

Description

90%

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 strong: it states a concrete capability, provides explicit natural-language triggers, and is clearly distinct from other skills. The only soft spot is specificity, where a single composite action is named rather than several discrete actions.

Suggestions

Enumerate a couple more concrete sub-actions (e.g., "draft the press release, generate external and internal FAQs, run a kill/keep assessment") to lift specificity to a full 3.

Consider folding one or two of the most natural trigger phrases (e.g., "working backwards", "write the press release first") directly into the description field so the triggers surface without relying on suggest_when.

Dimension	Reasoning	Score
Specificity	The description names the domain and a concrete action ("Write a PR/FAQ... Start from the customer press release and work backward to what needs to be built"), but describes a single composite action rather than listing multiple specific actions, matching the score-2 anchor.	2 / 3
Completeness	It explicitly answers both what ("Write a PR/FAQ for a product idea using Amazon's Working Backwards process") and when ("Use when validating whether an idea is worth building before committing to a spec"), matching the score-3 anchor.	3 / 3
Trigger Term Quality	It offers good coverage of natural terms users would say, including "PR/FAQ", "working backwards", "write the press release first", and "is this worth building" in the suggest_when trigger guidance, matching the score-3 anchor.	3 / 3
Distinctiveness Conflict Risk	It carves a clear niche (Working Backwards PR/FAQ) with distinct triggers unlikely to fire for other skills, matching the score-3 anchor.	3 / 3
	Total	11 / 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: amplitude/builder-skills
Commit: 22b0634

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.