crucible

Solid

Pressure-test important decisions, plans, proposals, strategies, architectures, and recommendations before acting. Use when trade-offs, uncertainty, meaningful downside, or an important second opinion could change the outcome. Stay lightweight for routine or trivial work.

AI & Automation 9 stars 0 forks Updated 5 days ago MIT

Install

View on GitHub

Quality Score: 85/100

Stars 20%
33
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
80
License 10%
100
Description 5%
100

Skill Content

# Crucible — Adaptive Decision-Pressure-Testing for Claude Code ## Mission Help Claude make **better decisions with the least sufficient compute**. Think of this as a built-in second brain: it should quietly improve important choices without turning every question into a long debate or exposing the machinery. The user should experience a clearer, more trustworthy answer—not an "agent show." **Default UX:** concise, direct, plain language. Go deeper only when the stakes, uncertainty, or user request justify it. ### Use it for - important choices and trade-offs; - plans, strategies, proposals, roadmaps; - architecture/design decisions; - consequential research conclusions; - recommendations with meaningful uncertainty; - pressure-testing an answer before the user acts on it. ### Do not use it heavily for - simple factual lookups; - routine transformations; - trivial reversible choices; - tasks where extra review cannot change the outcome. ## Default operating loop **Frame → Route → Verify → Review only what matters → Challenge → Quality-check → Stop → Act** ### 1. Frame Identify only what matters: - desired outcome; - actual decision; - realistic options; - constraints; - stakes and reversibility; - time sensitivity; - known evidence; - unknowns; - dominant assumption. If one missing fact truly blocks the answer, ask **one high-value question**. Otherwise state an assumption and continue. ### 2. Route Choose the cheapest sufficient mode: **QUICK** — one-pass reason...

Details

Author
smshahbaj
Repository
smshahbaj/crucible
Created
6 days ago
Last Updated
5 days ago
Language
Python
License
MIT

Similar Skills

Semantically similar based on skill content — not just same category

AI & Automation Listed

crucible

Assumption-driven venture validation that compounds founder judgment across sessions. Use whenever someone wants to pressure-test, stress-test, red-team, or validate a business or product idea, asks if an idea is worth building, wants a brutal or honest second opinion, says "convene the council", types "/crucible", or returns with the results of a previous Crucible experiment. Each session interrogates the idea into an assumption stack (KNOW/BELIEVE/HOPE), judges only what is checkable now, designs one falsifiable real-world experiment, and records everything in a per-venture ledger. The idea may be provided inline (e.g. "/crucible [the idea]").

2 Updated 2 weeks ago
AdityaVasireddy
AI & Automation Listed

crucible

The epistemic forge. Sits upstream of every other BrainStormer skill. Before you build, before you scaffold, before you ideate — CRUCIBLE forces you to enumerate what you actually know, what you're assuming, and what you can verify. Four phases: Pre-Flight (assumption enumeration), Architecture (falsifiable structure), Quality Gate (verification contracts), Evolution (compounding knowledge). This is the assumption-audit muscle promoted from debugging to default mode. Every skill, agent, feature, and design decision passes through CRUCIBLE's epistemic filter before resources are committed. Trigger on: "crucible", "epistemic check", "what do we actually know", "assumption audit", "prove it first", "verify before building", "falsifiability check", "pre-flight", "epistemic clarity", "what are we assuming", "challenge assumptions".

1 Updated 3 days ago
pnmcguire480
AI & Automation Listed

crucible

CRUCIBLE is an 8-agent code production pipeline built on Loop Engineering principles. It takes any coding task through Architect → Coder → Reviewer → Tester → Optimizer → Security Auditor → Documenter → Deployer before delivering production-ready, tested, optimized, secured, documented, and shippable code. A Loop Sentinel governs all feedback cycles with stagnation detection, progress thresholds, and a global step budget — the pipeline always converges or halts with a clear reason. Use CRUCIBLE for any task where quality, correctness, and production-readiness matter. Trigger whenever the user says: "build", "write", "code", "implement", "create a function / class / module / app / script / API / service", "refactor this", "I need code that does X", or invokes /crucible. Always prefer CRUCIBLE over a single-pass response when the task is non-trivial — more than ~30 lines, any business logic, any external integration. Also trigger on: "do this properly", "production-ready", "I want this reviewed", "build this ri

0 Updated 2 days ago
Eastern-comptrollership272