Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

Roast: Devil's Advocate Analysis · notque | DecimalAI

code reviewby notque

Roast: Devil's Advocate Analysis

notque/roast

Source notque/vexjoy-agent ↗License MIT

Constructive critique via 5 HackerNews personas with claim validation.

SkillScore65Maintained

Automatic

Coding pack

Last verified 8/27/2026

What it changes

Passed 12 of 19 test cases with the skill, and 7 of 19 without it.

Without skill35%

With skill65%

Checks it passed that the model alone missed

Identifies README.md as the default initial file target.
Identifies read-only-ops as the guardrail tool to invoke.
Requires claims to include file:line location references.

and 8 more in the full report

8 fixed7 passed either way7 still failing1 broke

Pass-rate lift: +30 pp
Tokens: +123%
Agent turns: 0%
Response time: -28%

Model gemini-3.6-flashMeasured 8/27/2026v2 · latest is v315 of 23 cases passed with skill · 19 comparable

Tokens, turns and time describe resource use, not a dollar price.

This benchmark measured an earlier version of the skill.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/notque-roast/SKILL.md https://app.decimal.ai/s/notque-roast/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add notque-roast, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/notque-roast/ and pins it in .decimal/skills.lock

decimalai skills add notque-roast

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/notque-roast/SKILL.md https://app.decimal.ai/s/notque-roast/SKILL.md

Raw file: /s/notque-roast/SKILL.md ↗ · machine-readable summary at /s/notque-roast.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 8

Prompt

During Phase 4 claim verification, an agent claims line 45 has no error handling, but reading line 45 shows a try-catch block wrapping the entire async call. What verdict must be assigned to this claim?

What was checked, without and with the skill
Checked	Without skill	With skill
Assigns the UNFOUNDED verdict when evidence contradicts a claim.	Missed	Passed

case-14 · gemini-3.6-flash · 8/27/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md274 lines2 files

Roast: Devil's Advocate Analysis

Overview

This skill produces evidence-based constructive critique through 5 specialized HackerNews commenter personas: Skeptical Senior, Well-Actually Pedant, Enthusiastic Newcomer, Contrarian Provocateur, and Pragmatic Builder. The workflow spawns these personas in parallel, validates all claims against actual files and lines, and synthesizes findings into an improvement-focused report.

Key constraints baked into the workflow:

CLAUDE.md must be read and followed before analysis begins
Read-only mode (no Write, Edit, destructive Bash) is mandatory — enforced via read-only-ops skill invocation
Every claim must reference specific file:line locations and be validated against actual evidence before appearing in the final report
All 5 personas must complete before validation begins — no partial analysis
Final report must include both validated strengths and problems, prioritized by impact
Unvalidated claims are dismissed; unfounded critiques are shown with evidence explaining why
Analysis must be direct and focused — no elaborate frameworks beyond the 5-persona + validation pattern
Sarcasm and mockery are stripped during synthesis; technical accuracy and file references are preserved

Deep References

When	Load	Content
Phase 5: writing the synthesized report	`references/report-template.md`	Full report template with tone transformation rules

Instructions

Phase 1: ACTIVATE READ-ONLY MODE

Goal: Establish guardrails before any analysis begins.

Call the Skill tool with read-only-ops.

skill: read-only-ops

This ensures no modifications can occur during the analysis workflow.

Allowed operations:

Read tool for file contents

Track record

Benchmark

12 / 19

test cases passed, vs 7 / 19 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v5 — 9/25/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

notque / vexjoy-agent

skills/research/roast/SKILL.md

View on GitHub ↗

License MITImported 9/25/2026Version v3Bundled 1 file

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Roast: Devil's Advocate Analysis

Overview

Deep References

Instructions

Phase 1: ACTIVATE READ-ONLY MODE

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills