Ucts Guide

Smart task analysis with optimal tool prescription. Analyze any coding task by complexity, domain, scope, and risk — then prescribe the best combination of U...

Security Scan

Instruction-only helper that classifies coding tasks and prescribes Claude Code session configurations; it requests no credentials, performs no installs, and stays within its stated purpose.

Purpose & Capability

The name/description (task analysis and tool prescription for UCTS/Claude Code) matches the SKILL.md content. No unexpected environment variables, binaries, or config paths are requested; everything in the instructions is about classification and dispatching Claude Code sessions.

Instruction Scope

Runtime instructions only classify tasks and produce spawn/dispatch text for Claude Code (e.g., 'Load UCTS. Run /ucts guide <task>'). They do not instruct reading files, harvesting environment variables, calling external endpoints, or performing unrelated system actions.

Install Mechanism

No install spec and no code files (instruction-only). Nothing will be written to disk or downloaded during install; lowest-risk install posture.

Credentials

The skill declares no required environment variables, credentials, or config paths. The SKILL.md does not reference any hidden env vars or secrets.

Persistence & Privilege

always is false and the skill is user-invocable. It does not request elevated persistent privileges or attempt to modify other skills or system-wide settings. Note: autonomous invocation remains possible (platform default), which is expected for a skill that can dispatch sessions.

Assessment

This skill is an instruction-only helper that suggests how to configure and spawn Claude Code sessions; it asks for nothing sensitive and won't install code. Before enabling, consider whether you trust the agent to autonomously launch the suggested Claude Code sessions and tool combos (those sessions may themselves invoke other tools or perform implementations). If you restrict autonomous actions, keep this skill user-invocable only and review any downstream tools (UCTS/Claude Code integrations) you use alongside it.

UCTS Smart Guide

Analyze the user's task and prescribe the optimal Claude Code session configuration.

When to use

When the user describes any coding task — feature, bug fix, refactor, architecture, etc. — and you need to decide HOW to approach it optimally.

Process

1. Classify the task

Dimension	Options
Complexity	trivial, simple, moderate, complex, massive
Domain	code, debug, refactor, feature, architecture, devops, docs, security, performance, migration
Scope	single-file, multi-file, module, cross-module, full-repo, multi-repo
Risk	none, low, medium, high, critical

Signals to look for:

• "todo list", "script", "hello world" → trivial
• "fix bug", "add test" → simple
• "authentication", "OAuth", "API endpoint" → moderate
• "microservice", "payment", "distributed" → complex
• "redesign", "rewrite", "migration" → massive
• "payment", "stripe", "encryption" → critical risk
• "security", "OWASP", "vulnerability" → high risk

2. Prescribe the combo

Complexity	Caveman	Tools	Model
trivial	ultra	Cache + Monitor	haiku-only
simple	full	+ Pruner, Fast Transform	haiku-default
moderate	full	+ LLMLingua, Semantic Cache, SWE-Pruner, RouteLLM, Repo Map	auto-route
complex	lite	+ AgentDiet, Hierarchical Memory, Swarm, /office-hours	auto-route
massive	off/lite	+ Observability, SPARC, all of the above	sonnet/opus

Risk overrides:

• critical risk → caveman off (no compression on safety-critical work)
• high risk → add /careful (destructive command blocking)
• any security domain → add /cso after implementation

3. Generate the dispatch instruction

Format for spawning a Claude Code session:

Load UCTS. Run /ucts guide <original task description>

For specific known patterns:

• Security audit → Load UCTS. Run /cso
• Code review → Load UCTS. Run /review
• QA test → Load UCTS. Run /qa <url>
• Feature → Load UCTS. Run /ucts guide <desc>, approve, implement, /ship
• Plan only → Load UCTS. Run /ucts guide <desc>, /office-hours, /autoplan. Save plan, don't implement.

4. Show the user

📋 Task: [description]
📊 Classification: [complexity] [domain] | [scope] | risk: [risk]
🎯 Combo: caveman:[level] + [Tool1] + [Tool2] + ...
💰 Estimated savings: [X]%

Spawning Claude Code with: "Load UCTS. Run /ucts guide [task]"