Skip to content

mikeng-io/agent-skills / skills/context

context

Verified

Analyze conversation context to classify what is being discussed, detect relevant domains from domain-registry, and determine optimal routing (parallel-workflow vs debate-protocol vs deep-council). Can be invoked directly or called by other skills as a pre-flight step.

FileKindSize
README.mdmarkdown1.4 KB
SKILL.mdskill md10.2 KB
schemas/context-report-schema.jsonconfig1.7 KB
# Deep Context

Artifact classifier and smart router for the Deep Skills Suite. Analyzes conversation context to detect domains and determine optimal review routing.

## What it does

1. Analyzes conversation for signals (file types, topics, concerns, explicit mentions)
2. Classifies artifact type (code, financial, marketing, creative, research, mixed)
3. Selects matching domains from domain-registry
4. Recommends routing: `parallel-workflow`, `debate-protocol`, or `deep-council`
5. Produces a context report for use by the calling skill or user

## Usage

Standalone:
```
Invoke: context
```

As pre-flight step (called by other skills inline):
```
Other skill reads context/SKILL.md and applies context analysis
steps before spawning domain experts.
```

## Routing Logic

| Condition | Routing |
|-----------|---------|
| < 3 domains, no high-stakes signals | parallel-workflow |
| >= 3 domains OR high-stakes signals | debate-protocol (standard) |
| "thorough" / "critical" in request | debate-protocol (thorough) |
| Explicit multi-model request | deep-council |

## Confidence Levels

| Level | Meaning |
|-------|---------|
| high | Explicit domain mentions, clear file types |
| medium | Inferred from technical terms, mixed signals |
| low | Minimal context, ambiguous signals |

## Schema

Output validated against `schemas/context-report-schema.json`.

## Outputs

Artifacts saved to `.outputs/context/` with YAML frontmatter and JSON companion.
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall