skill-z3-implementation

Implement Z3 constraints. Invoke for Z3-language implementation tasks.

438 stars

Best use case

skill-z3-implementation is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Implement Z3 constraints. Invoke for Z3-language implementation tasks.

Teams using skill-z3-implementation should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

You only need a quick one-off answer and do not need a reusable workflow.
You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/skill-z3-implementation/SKILL.md --create-dirs "https://raw.githubusercontent.com/benbrastmckie/nvim/main/.claude/extensions/z3/skills/skill-z3-implementation/SKILL.md"

Manual Installation

Download SKILL.md from GitHub
Place it in .claude/skills/skill-z3-implementation/SKILL.md inside your project
Restart your AI agent — it will auto-discover the skill

How skill-z3-implementation Compares

Feature / Agent	skill-z3-implementation	Standard Approach
Platform Support	Not specified	Limited / Varies
Context Awareness	High	Baseline
Installation Complexity	Unknown	N/A

Frequently Asked Questions

What does this skill do?

Implement Z3 constraints. Invoke for Z3-language implementation tasks.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

SKILL.md Source

# Z3 Implementation Skill

Thin wrapper that delegates Z3 implementation to `z3-implementation-agent` subagent.

## Trigger Conditions

This skill activates when:
- Task language is "z3"
- /implement command targets a Z3 task
- Plan exists and task is ready for implementation

## Execution Flow

### Stage 1: Input Validation
Validate task_number exists and language is "z3".

### Stage 2: Preflight Status Update
Update status to "implementing" BEFORE invoking subagent.

### Stage 3: Prepare Delegation Context
Include task_context, plan_path, metadata_file_path.

### Stage 4: Invoke Subagent
Use Task tool with subagent_type: "z3-implementation-agent".

### Stage 5: Parse Subagent Return
Read metadata from `specs/{N}_{SLUG}/.return-meta.json`.

### Stage 6: Update Task Status (Postflight)
Update state.json and TODO.md based on result.

### Stage 7: Link Artifacts
Add artifact to state.json with summary.

### Stage 8: Git Commit
Commit changes with session ID.

### Stage 9: Return Brief Summary

## MUST NOT (Postflight Boundary)

After the agent returns, this skill MUST NOT:

1. **Edit Z3 files** - All constraint work is done by agent
2. **Run z3 solver** - Verification is done by agent
3. **Analyze or grep source** - Analysis is agent work
4. **Write summary/reports** - Artifact creation is agent work

The postflight phase is LIMITED TO:
- Reading agent metadata file
- Updating state.json via jq
- Updating TODO.md status marker via Edit
- Linking artifacts in state.json
- Git commit
- Cleanup of temp/marker files

Reference: @.claude/context/standards/postflight-tool-restrictions.md

---

## Return Format

Brief text summary (NOT JSON).