roast
Roast me — adversarial critique of a plan, design, or diff to find where it breaks, via pre-mortem, red-team, and steelman-then-destroy.
Skill by PlatformRelay
Chalk Labs
Need help deploying roast?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/platformrelay-roast
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: design
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/roast
What's inside
- Skill name
roast- Description
- Roast me — adversarial critique of a plan, design, or diff to find where it breaks, via pre-mortem, red-team, and steelman-then-destroy. Use when the operator says "roast this / roast me", "tear this apart", "where does this break", "red-team it", or wants a brutal-honesty review before committing.
- License
- MIT
- Instructions
- 33 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# roast — adversarial critique Dispatches the `roaster` role to attack the work from a fresh, unsentimental perspective. Use it *before* committing to a plan, *before* opening a big PR, or whenever you want the failure modes surfaced rather than discovered in production. Complements `/tech-review` (which gates a diff) and `/grill-me` (which interviews you) — this one attacks the artifact. ## Step 1 — set the target and mode Point at the artifact: a plan/design (paste or file), an ADR, or a diff/branch. Choose mode(s): pre-mortem, red-team, steelman-then-destroy, or all three (default). State the goal it's supposed to achieve so the roaster judges gaps against intent, not taste. ## Step 2 — dispatch the roaster Spawn the `roaster` subagent with the artifact, its stated goal, the relevant repo context (`GUIDELINES.md`, code paths), and the chosen mode(s). ## Step 3 — triage the findings Present the critique. Separate **would-sink-this** (P0/P1) from optional taste items. For each real finding, decide: fix now, turn into a backlog story (`/write-story`), record as accepted risk (in the ADR / handoff), or refute with evidence. End with the single cheapest risk-reducer. ## Step 4 — log it for review Save the critique to `agent-context/inbox/reports/<YYYY-MM-DD>-roast-<slug>.md` and append a **REPORT** line to the INBOX (repo or workspace) so it's on the operator's review queue, not just in scrollback. ## Do not - Treat the roast as a verdict to act on blindly — weigh each finding; refute with evidence where the roaster is wrong. - Let it pad the list with style nits dressed as risks — those go in a clearly-optional bucket. - Use it to gate a PR — that's `/tech-review`.
From PlatformRelay/Kaddy, MIT.
More from PlatformRelay/Kaddy
- 0.497score
agent-loop
PlatformRelay
Start or resume implementation in one PlatformRelay repo.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
agent-loop-auto
PlatformRelay
Autonomous variant of /agent-loop for ONE repo: thin coordinator + parallel implementer subagents + a coordinator-dispatched INDEPENDENT reviewer, plus an…
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
agent-loop-local
PlatformRelay
Maximum-autonomy variant of /agent-loop-auto for ONE repo: no PRs — each lane is gated by a coordinator-dispatched INDEPENDENT reviewer, then a serialized…
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
brainstorm
PlatformRelay
Structured diverge → cluster → converge ideation that prevents premature fixation on the first idea.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
changelog
PlatformRelay
Turn gitmoji-conventional commit history into categorized, user-facing release notes for a PlatformRelay repo.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
design-architecture
PlatformRelay
Design a change and record the decision: ADR/AgDR, C4 sketch, weighted trade-off matrix, or a spec-first contract.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
retrospective
PlatformRelay
End-of-session learnings loop.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
security-review
PlatformRelay
Dedicated data-flow security pass over a diff or a repo — deeper than the security dimension of /tech-review.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
tech-review
PlatformRelay
Review a lane/branch before opening (or while awaiting) a PR in any PlatformRelay repo.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
write-story
PlatformRelay
Turn an epic, feature idea, or vague ask into INVEST-compliant vertical-slice stories with Given-When-Then acceptance criteria, mapped onto the target repo's…
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
handover
PlatformRelay
Wrap up a session cleanly and produce a copy-pasteable prompt to start the NEXT one.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
merge-open-prs
PlatformRelay
Review and merge all open PRs/MRs in ONE repo after checking CI.
SkillCFreshness: C★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jul 20, 2026 (3 months ago)
- Last release
- Jul 21, 2026 (3 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/PlatformRelay/Kaddy
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from PlatformRelay
- 0.497score
agent-loop
PlatformRelay
Start or resume implementation in one PlatformRelay repo.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
agent-loop-auto
PlatformRelay
Autonomous variant of /agent-loop for ONE repo: thin coordinator + parallel implementer subagents + a coordinator-dispatched INDEPENDENT reviewer, plus an…
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
agent-loop-local
PlatformRelay
Maximum-autonomy variant of /agent-loop-auto for ONE repo: no PRs — each lane is gated by a coordinator-dispatched INDEPENDENT reviewer, then a serialized…
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
brainstorm
PlatformRelay
Structured diverge → cluster → converge ideation that prevents premature fixation on the first idea.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
changelog
PlatformRelay
Turn gitmoji-conventional commit history into categorized, user-facing release notes for a PlatformRelay repo.
SkillCFreshness: C★ 1Claude Code +9 - 0.497score
design-architecture
PlatformRelay
Design a change and record the decision: ADR/AgDR, C4 sketch, weighted trade-off matrix, or a spec-first contract.
SkillCFreshness: C★ 1Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get roast running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
roast skill. Agent Mart. https://agentmart.dev/skills/platformrelay-roast (last updated 2026-10-24)