Super Skill

Super Skill - Agent Entry Point

Before Any Action

Read these files in this order:

1. CONTEXT.md - who owns this, what domain, what goals
2. CURRENT_STATE.md - what the domain looks like right now
3. PENDING.md - what is waiting for user approval

Never skip this sequence. Context before action, always.

Operating Principle

Iron Principle: propose → PENDING.md → user decides → system executes.

Domain Files

After reading the three required files above, load the remaining layer files as needed for the current task: DOMAIN_MAP.md - structure and sub-domain relationships EVALUATION.md - criteria for evaluating new entrants DECISIONS.md - decisions made and reasoning MONITORING.md - sources to watch for drift LEARNING.md - NotebookLM integration structure LOG.md - change log and audit trail experts/COUNCIL.md - active expert council and debates traces/ - execution traces for causal reasoning wiki/graph.json - domain structure map (optional; run /ss-graph to generate)

Individual expert profiles (experts/[name].md) load on demand only, not by default. Load them when a specific expert's perspective is needed.

Evidence Routing

Before proposing any change, load the files most likely to contain relevant evidence for your task type. This prevents blind proposals.

| Task type | Evidence files (load in order) | |------------------------------|---------------------------------------------------| | Evaluate a new tool/method | EVALUATION.md, CURRENTSTATE.md, DECISIONS.md | | Propose architecture change | DECISIONS.md, DOMAINMAP.md, CURRENTSTATE.md | | Investigate drift or breakage | MONITORING.md, CURRENTSTATE.md, traces/ | | Resolve a PENDING item | PENDING.md, DECISIONS.md, EVALUATION.md | | Generate learning content | LEARNING.md, CONTEXT.md, CURRENTSTATE.md | | Root-cause analysis | traces/, DECISIONS.md, LOG.md | | Cross-domain impact check | DOMAINMAP.md, CURRENT_STATE.md, DECISIONS.md | | Expert disagreement | experts/COUNCIL.md, DECISIONS.md, experts/[name].md |

Load the minimum set. Do not load files not listed for your task type.

How Prompts Work

All prompts live in ONBOARDING.md. Claude Code reads and runs them automatically. Users do not copy prompts after the initial Bootstrap setup.

Slash commands: see CLAUDE.md

Capabilities

Operating rules and capabilities: see CLAUDE.md

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: Asaf-Dahan
• Source: Asaf-Dahan/super-skill
• License: MIT

Install and usage instructions live in the source repository linked above.