roast

Use when someone asks to roast an idea, pressure-test or stress-test an idea, validate a business idea, "convene the panel", get a brutal second opinion before building something, or says "/roast". Spins up a 5-angle panel (Critic, Champion, Analyst, Investigator, Customer) that attacks the idea from every angle, then a Judge returns one GO / RESHAPE / KILL verdict with the cheapest test to de-risk it.

Quality

93%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

—

The risk profile of this skill

Quality

Content

86%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.

The content is highly actionable with concrete commands, verbatim prompts, and an exact output template, organized into a clear 3-step workflow with validation checkpoints and well-signaled one-level-deep references. It is tight throughout, with only minor motivational prose that could be trimmed.

Suggestions

Trim the motivational framing ('Claude's default is to agree with you', the portability blockquote) to tighten conciseness without losing the load-bearing guidance.

Add a one-line error-recovery note for the script invocations (e.g., what to do if brief_builder reports a missing critical input) to push workflow clarity to 5.

Dimension	Reasoning	Score
Conciseness	The body is dense and purposeful with no padding of concepts Claude already knows, but includes lightly trimmable motivational framing ('Claude's default is to agree with you') and the portability note that aren't strictly load-bearing.	4 / 5
Actionability	Fully executable: copy-paste bash invocations for all three scripts with realistic arguments, verbatim panelist prompts, and an exact verdict output template covering the common cases.	5 / 5
Workflow Clarity	A clear 3-step sequence (Frame → Panel → Verdict) with an explicit pre-panel checkpoint (brief_builder flags missing inputs) and a 'do not average, run the synthesizer' gate; only a minor gap in error-recovery guidance for failed script runs.	4 / 5
Progressive Disclosure	The body is a clear overview that links one-level-deep to real, verified references (3 canon files) and assets (worksheet + example verdict), each clearly signaled with its purpose and easy to navigate.	5 / 5
	Total	18 / 20 Passed

Description

100%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 exemplary: it states concrete capabilities, packs in natural trigger phrases and synonyms, and explicitly covers both what and when, all in third-person voice. It is clearly distinct from neighboring skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Spins up a 5-angle panel', 'attacks the idea from every angle', 'a Judge returns one GO / RESHAPE / KILL verdict', 'the cheapest test to de-risk it' — with comprehensive coverage of what the skill does.	5 / 5
Completeness	Explicitly answers both what (5-angle panel → Judge verdict + cheapest test) and when ('Use when someone asks to roast...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural-term coverage with synonyms: 'roast an idea', 'pressure-test', 'stress-test', 'validate a business idea', 'convene the panel', 'brutal second opinion', and the '/roast' slash trigger.	5 / 5
Distinctiveness Conflict Risk	Clear niche — an adversarial 5-angle panel producing a GO/RESHAPE/KILL verdict — with distinctive triggers and minimal overlap risk, reinforced by the distinct_from metadata.	5 / 5
	Total	20 / 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: productivity/roast/skills/roast/SKILL.md
Commit: 19392f7

Reviewed: ~2 hours 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.