KS
Killer-Skills

full_auth — Categories.community

v1.0.0
GitHub

About this Skill

Perfect for Advanced AI Agents requiring unrestricted file editing and autonomous task execution. AERA: local-first workstation for quantitative research, visualization, and backtesting.

CheekyCodexConjurer CheekyCodexConjurer
[0]
[0]
Updated: 3/5/2026

Quality Score

Top 5%
44
Excellent
Based on code quality & docs
Installation
SYS Universal Install (Auto-Detect)
Cursor IDE Windsurf IDE VS Code IDE
> npx killer-skills add CheekyCodexConjurer/quant-lab/full_auth

Agent Capability Analysis

The full_auth MCP Server by CheekyCodexConjurer is an open-source Categories.community integration for Claude and other AI agents, enabling seamless task automation and capability expansion.

Ideal Agent Persona

Perfect for Advanced AI Agents requiring unrestricted file editing and autonomous task execution.

Core Value

Empowers agents to execute comprehensive content analysis end-to-end using AERA for quantitative research and visualization, with phased implementation plans and immediate execution of all phases, leveraging local-first workstations and backtesting capabilities.

Capabilities Granted for full_auth MCP Server

Automating quantitative research workflows
Executing phased implementation plans for complex tasks
Performing comprehensive content analysis with AERA

! Prerequisites & Limits

  • Requires explicit user permission for file editing
  • Needs sufficient information to avoid blocking
  • Must be able to resolve command failures autonomously
Project
SKILL.md
1.4 KB
.cursorrules
1.2 KB
package.json
240 B
Ready
UTF-8

# Tags

[No tags]
SKILL.md
Readonly

Authorization

Use this skill only when the user explicitly grants permission to edit files and complete the task end-to-end without asking “should I continue?”.

Execution Mode

PHASED PLAN, ALL PHASES IN ONE RUN

  • Produce a phased implementation plan first (Phase 1/2/3…).
  • Immediately execute all phases in sequence in the same run, until Definition of Done is met.
  • Only pause if blocked by missing info or if a command fails and cannot be resolved autonomously.

Blocking Rule

If blocked, ask exactly one concise question that would unblock the work. Otherwise, keep going.

Definition of Done (generic)

  • Safety validation passes (respect .agentignore).
  • Use the best available repo verification:
    • Prefer .agent-docs/memory/COMMANDS.json and MANIFEST.yaml.
    • If missing, run capability/command detection and record confidence.
    • Run tests, lint, and build as applicable.
  • If QUALITY_GATES.md exists, follow it as the source of truth.
  • Provide a final summary and list all modified/created files.

Output Requirements

  1. Investigation notes (what matters in the repo).
  2. Phased plan (Phase 1/2/3… with files and behaviors).
  3. Implementation (commit-style narrative by phase).
  4. Files changed + verification results (commands run and outcomes).

Guardrails

  • Always respect .agentignore forbidden zones.
  • Enforce Trust Layer TDD for behavior changes.
  • Keep an Action Ledger entry for meaningful work.

Related Skills

Looking for an alternative to full_auth or building a Categories.community AI Agent? Explore these related open-source MCP Servers.

View All

widget-generator

Logo of f
f

widget-generator is an open-source AI agent skill for creating widget plugins that are injected into prompt feeds on prompts.chat. It supports two rendering modes: standard prompt widgets using default PromptCard styling and custom render widgets built as full React components.

149.6k
0
Design

chat-sdk

Logo of lobehub
lobehub

chat-sdk is a unified TypeScript SDK for building chat bots across multiple platforms, providing a single interface for deploying bot logic.

73.0k
0
Communication

zustand

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
Communication

data-fetching

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
Communication