Claude-skill-registry contextkit-planning-trigger

Natural language wrapper for ContextKit planning commands - automatically triggers /ctxk:plan commands when users request planning assistance

install

source · Clone the upstream repo

git clone https://github.com/majiayu000/claude-skill-registry

Claude Code · Install into ~/.claude/skills/

T=$(mktemp -d) && git clone --depth=1 https://github.com/majiayu000/claude-skill-registry "$T" && mkdir -p ~/.claude/skills && cp -r "$T/skills/data/contextkit-planning-trigger" ~/.claude/skills/majiayu000-claude-skill-registry-contextkit-planning-trigger && rm -rf "$T"

manifest: skills/data/contextkit-planning-trigger/SKILL.md

contextkit-planning-trigger

Type: ANALYSIS-ONLY DAIC Modes: DISCUSS, ALIGN, IMPLEMENT, CHECK (all modes) Priority: Medium

Trigger Reference

This skill activates on:

Keywords: "plan this", "how should I approach", "create plan", "quick plan", "break down into steps", "research tech", "planning", "approach", "strategy", "implementation plan"

Intent Patterns:

(plan|approach|strategy).*(this|feature|task)

how.*?(approach|implement|structure)

break.*?down.*?steps

research.*(tech|technology|options)

create.*(plan|strategy)

From:

skill-rules.json

- contextkit-planning-trigger configuration

Purpose

Automatically trigger ContextKit planning commands (

/ctxk:plan:quick

/ctxk:plan:1-spec

/ctxk:plan:2-research-tech

/ctxk:plan:3-steps

) when users request planning assistance using natural language.

Core Behavior

In any DAIC mode:

Planning Intent Detection
- Detect planning requests from natural language
- Route to appropriate ContextKit planning command
Command Routing
- Quick planning: "plan this feature" →
```
/ctxk:plan:quick
```
- Detailed spec: "create detailed spec" →
```
/ctxk:plan:1-spec
```
- Tech research: "research technology options" →
```
/ctxk:plan:2-research-tech
```
- Implementation steps: "break down into steps" →
```
/ctxk:plan:3-steps
```

Natural Language Examples

Triggers this skill:

✓ "Plan this feature"
✓ "How should I approach this?"
✓ "Break down into steps"
✓ "Research tech options"
✓ "Create implementation plan"

Safety Guardrails

ANALYSIS-ONLY RULES:

✓ NEVER call write tools
✓ Only invokes ContextKit planning commands (read-only)
✓ Safe to run in any DAIC mode