# Meta

> Strategic decision analysis using CLEAR META framework. Use for architecture decisions, technology selection, strategic trade-offs.

- Skill: `demithras/meta` (Agent Skill, multi-file: 42 files)
- Install (CLI): `npx skillmds@latest add demithras/meta`
- Raw SKILL.md: https://api.skillmd.com/api/skills/demithras/meta/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: demithras (https://skillmd.com/u/demithras)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/demithras/meta

---


# /meta — CLEAR META Decision Framework

> **TL;DR**: Strategic decision analysis. Get structured recommendation with scored options.

---

## Quick Start

```
/meta <question>               # Auto-selects depth
/meta --depth=quick <question> # Force quick (~30s)
/meta --depth=deep <question>  # Force deep analysis
/meta --plan "<criteria>"      # Exit criteria → task plan
```

---

## When to Use

| Use for | Skip for |
|---------|----------|
| Architecture decisions | Trivial choices |
| Technology selection | Information lookup |
| Strategic trade-offs | Already-decided directions |

---

## CLEAR Phases

| Phase | Purpose | Output |
|-------|---------|--------|
| **C** | Gather context | Situation map |
| **L** | Tag claims with confidence | L-labeled claims *(fact/model/hypothesis/heuristic/belief)* |
| **E** | Define "done when" | Exit criteria |
| **A** | Generate tactics, score | Recommendation with MetaScore |
| **R** | Capture learnings | /retro when significant |

**Formula**: C-L-E (reflection) → A (action) → R (review)

---

## Output Format

```markdown
## CLEAR: [Title]

**C** — [Context summary]
**E** — [Exit criterion]

**Key Claims** (L-labeled):
- [claim] *(fact)*
- [claim] *(hypothesis)*

**Options**:
| Option | Score | Pros | Cons |
|--------|-------|------|------|
| A | 78% | ... | ... |
| B | 65% | ... | ... |

**→ Recommendation: [Option A]** (MetaScore: 78%)

⚡ DO THIS NOW: [immediate action]

📋 CLEAR: C✓ L✓ E✓ A✓ R○ | Next: [action]
```

---

## Depth Selection

| Signals | Depth |
|---------|-------|
| Simple, reversible | **Quick** |
| "compare", "vs", options defined | **Comparative** |
| "critical", "important", irreversible | **Deep** |
| Obvious answer | **Skip** |

---

## Flags

| Flag | Description |
|------|-------------|
| `--depth=quick\|deep\|comparative` | Force depth |
| `--plan` | Convert exit criteria to task plan |
| `--persist` | Create Beads issues (with --plan) |

---

## CLEAR Check (Required Exit)

Every invocation ends with:

```
📋 CLEAR: C✓ L✓ E✓ A✓ R○ | Next: [action]
```

**R○ pending** is normal — R✓ requires `/retro` invocation.

**State block** (for agent continuity):
```
<!-- meta:state
depth: quick
recommendation: "Option A"
clear: {C: done, L: done, E: done, A: done, R: pending}
next: "implement recommendation"
/meta:state -->
```

---

## References

- Methodology: `references/methodology.md`
- Agent architecture: `references/agents.md` (for --depth=deep)