pre-mortem

Identify what could go wrong before launch by imagining failure and working backward. Use after a spec is approved but before you ship — surfaces risks the team isn't talking about.

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.

A lean, highly actionable instruction skill centered on a concrete prompt template with a clear risk taxonomy. The only improvement area is trimming the motivational intro prose that does not earn its tokens.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and the prompt template is tight, but the opening framing ('The spec is done, the team is building, and everyone's optimistic... while there's still time to fix it') adds motivational prose Claude does not need and could be trimmed.	2 / 3
Actionability	Provides a fully copy-paste-ready prompt template with a concrete risk taxonomy (Tigers, Paper Tigers, Elephants), explicit urgency levels, and required per-risk fields (mitigation, owner, deadline) — specific and executable.	3 / 3
Workflow Clarity	A single-purpose skill whose one action — run the structured pre-mortem prompt — is unambiguous; per the simple-skill scoring note, no multi-step validation workflow is required.	3 / 3
Progressive Disclosure	Under 50 lines with no external references needed, organized into clear sections (intro, Prompt Template, Tips), satisfying the simple-skill bar for progressive disclosure.	3 / 3
	Total	11 / 12 Passed

Description

85%

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 specific, well-scoped description that clearly states both capability and timing of use. Its only weakness is that the most natural user trigger phrases sit in suggest_when rather than the description, leaving trigger coverage at a moderate level.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Identify what could go wrong', 'imagining failure and working backward', and 'surfaces risks the team isn't talking about' — rather than vague language.	3 / 3
Completeness	Explicitly answers what ('Identify what could go wrong before launch by imagining failure and working backward') and when ('Use after a spec is approved but before you ship'), with explicit trigger guidance present so it is not capped at 2.	3 / 3
Trigger Term Quality	Contains relevant domain words ('launch', 'ship', 'risks', 'spec') but the natural trigger phrases users would actually say ('what could go wrong', 'pre-mortem', 'risk assessment') live in the separate suggest_when field rather than the description itself, so coverage of natural terms is partial.	2 / 3
Distinctiveness Conflict Risk	Targets a clear niche — pre-launch pre-mortem risk analysis — with distinct framing unlikely to trigger for unrelated skills.	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.