self-grill
Runs Bayesian Self-Grill prior locking (C0..C3) and multi-loop headless Chromium DOM/SVG geometry verification (audit_web_ui_geometry.py).
Skill by gmilen-sketch
Chalk Labs
Need help deploying self-grill?
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/gmilen-sketch-self-grill
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 and code. Checked Oct 26, 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/self-grill
What's inside
- Skill name
self-grill- Description
- Runs Bayesian Self-Grill prior locking (C0..C3) and multi-loop headless Chromium DOM/SVG geometry verification (audit_web_ui_geometry.py).
- License
- MIT
- Metadata
- icon: 🔥 · version: 3.4.0
- Instructions
- 9 lines in SKILL.md · view on GitHub
Files (3)
- EVAL.txtpb
- SKILL.md
- pdq-extended-guide.md · references/
SKILL.md (first lines)
# self-grill (v3.4.0 Clean-Room Enterprise Edition) ## Epistemic Reasoning & Grounding Protocol (PD-Q) 1. **Step-1 Complete Causal Reasoning Mandate**: Formulate the complete multi-hypothesis causal plan and failure checks (`F1` Hallucination, `F2` Missed Constraint, `F3` Flag Guessing, `F4` Cross-Workflow Bleeding, `F5` Stale State) before executing mutating tool calls (`TCA = 100%`). 2. **Primary-Source Grounding Contract (`GCS >= 0.85`)**: Anchor every technical claim and metric in verified primary sources: Knowledge Graph SSOT (`/dev/shm/kg_warm_cache.json`), Open Knowledge Format (`kb/`) dossiers, and live tool outputs (`exit_code == 0`). 3. **Progressive Disclosure**: Load extended reference patterns from [`references/pdq-extended-guide.md`](references/pdq-extended-guide.md) on demand.
From gmilen-sketch/antigravity-web-hub, MIT.
More from gmilen-sketch/antigravity-web-hub
- 0.601score
workspace-docs-publisher
gmilen-sketch
Publishes 3-Tab Inverted-Pyramid (Arm E / AGENT-SSOT-v1) technical reports with 516.0 pt centered tables via public Google Docs REST API v1.
SkillAFreshness: A★ 3Claude Code +9 - 0.601score
diagram-renderer
gmilen-sketch
Compiles BENTO architecture DSL and Mermaid v12 definitions into high-DPI orthogonal SVG/PNG diagrams with rounded r=5.5px Manhattan connectors.
SkillAFreshness: A★ 3Claude Code +9 - 0.601score
golden-ab-testing
gmilen-sketch
Executes paired A/B evaluations with Hake's Normalized Gain, unbiased hypergeometric pass@k/pass^k, and Wilcoxon/McNemar significance gates.
SkillAFreshness: A★ 3Claude Code +9 - 0.601score
open-deep-researcher
gmilen-sketch
Executes multi-source deep research across Git repositories, BigQuery datasets, enterprise wikis, and public documentation with citation hash verification.
SkillAFreshness: A★ 3Claude Code +9 - 0.601score
workspace-slides-generator
gmilen-sketch
Generates executive 720x405 pt presentations with 4-card layouts and 3-shape vector chevron connectors via public Google Slides REST API v1.
SkillAFreshness: A★ 3Claude Code +9 - 0.601score
antigravity-web-builder
gmilen-sketch
Provisions, configures, and verifies cloud-hosted Antigravity Web Hub instances with Cloud IAP, HTTPS reverse proxying, and pre-warmed sessions.
SkillAFreshness: A★ 3Claude Code +9 - 0.601score
p0-quality-first-engine
gmilen-sketch
Enforces P0 deterministic circuit-breakers (CB-1..CB-7), Bernstein disjoint write-set locks, temporal window resolution, and chained-shell subshell guards.
SkillAFreshness: A★ 3Claude Code +9 - 0.601score
p1-quality-first-engine
gmilen-sketch
Enforces P1 grounded retrieval circuit-breakers (P1-CB-1..P1-CB-8), Pre-Ingestion Prompt-Injection (PICC) quarantine, and 3-Stage issue triage.
SkillAFreshness: A★ 3Claude Code +9 - 0.601score
parallel-task-orchestrator
gmilen-sketch
Coordinates parallel leaf subagents (MAX_DEPTH=1) with <hydrated_context> XML bundles and disjoint write-set enforcement.
SkillAFreshness: A★ 3Claude Code +9 - 0.601score
playwright-agent-browser
gmilen-sketch
Automates headless Chromium via Playwright and RFC 6455 WebSocket CDP (:9222) with Shadow-DOM piercing and React Fiber file uploads.
SkillAFreshness: A★ 3Claude Code +9 - 0.601score
six-hats-evaluator
gmilen-sketch
Evaluates architectural decisions across Edward de Bono's Six Thinking Hats with iterative Delphi convergence and weighted trade-off matrices.
SkillAFreshness: A★ 3Claude Code +9 - 0.601score
universal-solution-architect
gmilen-sketch
Designs production cloud architectures across all 6 pillars (AI/ML, Data Analytics, App Mod, Security, Multicloud, Sovereign Cloud).
SkillAFreshness: A★ 3Claude Code +9
Signals
- Stars
- 3
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 14, 2026 (16 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- Version
- 3.4.0
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from gmilen-sketch
- 0.601score
parallel-task-orchestrator
gmilen-sketch
Coordinates parallel leaf subagents (MAX_DEPTH=1) with <hydrated_context> XML bundles and disjoint write-set enforcement.
SkillAFreshness: A★ 3Claude Code +9 - 0.601score
antigravity-web-builder
gmilen-sketch
Provisions, configures, and verifies cloud-hosted Antigravity Web Hub instances with Cloud IAP, HTTPS reverse proxying, and pre-warmed sessions.
SkillAFreshness: A★ 3Claude Code +9 - 0.601score
diagram-renderer
gmilen-sketch
Compiles BENTO architecture DSL and Mermaid v12 definitions into high-DPI orthogonal SVG/PNG diagrams with rounded r=5.5px Manhattan connectors.
SkillAFreshness: A★ 3Claude Code +9 - 0.601score
p0-quality-first-engine
gmilen-sketch
Enforces P0 deterministic circuit-breakers (CB-1..CB-7), Bernstein disjoint write-set locks, temporal window resolution, and chained-shell subshell guards.
SkillAFreshness: A★ 3Claude Code +9 - 0.601score
p1-quality-first-engine
gmilen-sketch
Enforces P1 grounded retrieval circuit-breakers (P1-CB-1..P1-CB-8), Pre-Ingestion Prompt-Injection (PICC) quarantine, and 3-Stage issue triage.
SkillAFreshness: A★ 3Claude Code +9 - 0.601score
playwright-agent-browser
gmilen-sketch
Automates headless Chromium via Playwright and RFC 6455 WebSocket CDP (:9222) with Shadow-DOM piercing and React Fiber file uploads.
SkillAFreshness: A★ 3Claude 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 self-grill 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
self-grill skill. Agent Mart. https://agentmart.dev/skills/gmilen-sketch-self-grill (last updated 2026-10-24)