onboard

What this skill does

# Onboard Skill

Start with a quick recommendation based on recent sessions, then optionally continue to guided learning — so users experience value first, learn second.

Invoke directly with `/onboard` when the user wants onboarding or protocol discovery.

## When to Use

Invoke this skill when:
- A new user wants to discover which epistemic protocols fit their workflow
- A user wants to experience protocols through guided practice
- Re-onboarding after new protocols are added or workflow changes

Skip when:
- User wants analytical report with evidence and HTML artifact (use `/report`)
- User already knows which protocol to use (direct invocation)
- Quick single-protocol question (answer directly)

## Workflow Overview

```
Quick Proof:    ENTRY → QUICKSCAN → PICK-1 → EVIDENCE → TRIAL → INSIGHT → NEXT
Targeted:       ENTRY → QUICKSCAN → MAP → SCENARIO → TRIAL → QUIZ → GUIDE
Targeted + std: ENTRY → SCENARIO → TRIAL → QUIZ → GUIDE
```

| Phase | Owner | Tool | Purpose |
|-------|-------|------|---------|
| 0. Entry | Main | Gate | Path selection: quick/targeted |
| 1. Quick Scan | Main | Glob, Read | User Context Profile extraction |
| 2a. Pick-1 | Main | — | Quick path: select 1 recommendation |
| 2b. Evidence | Main | — | Quick path: show 1 evidence card |
| 2. Map | Main | — | Targeted path: Profile → Protocol matching |
| 3. Scenario | Main | Gate | Targeted path: context-personalized intervention point |
| 4. Trial | Main | Gate | Real protocol execution (quick: mini trial, targeted: full trial) |
| 4→Q. Insight | Main | — | Quick path: post-trial insight card |
| 4→Q. Next | Main | Gate | Quick path: simplified navigation |
| 4→5 LOOP | Main | Gate | Targeted path: post-trial navigation |
| 5. Quiz | Main | Gate | Targeted path: Socratic protocol recognition quiz |
| 6. Guide | Main | Gate | Targeted path: summary + /report CTA |

## Data Sources

Compact mapping for inline use. For full Primary/Secondary/Tertiary tables with detection methods and rationale, refer to `/report` SKILL.md.

| Protocol | Cluster | When to Use | Key Patterns |
|----------|---------|-------------|-------------|
| Aitesis `/inquire` | Planning | AI is about to answer without enough observable context | External fact queries, verifiable grounding (for prior-session recall → use `/recollect`) |
| Euporia `/elicit` | Planning | Intent articulated but axis-undetermined; decision coordinates implicit in codebase / rules / past sessions | Multi-axis intent without single axis-specific protocol fit; substrate-implicit coordinates surface through cycle-emergent dimensions |
| Prothesis `/frame` | Analysis | Unsure which analytical perspective to use | Exploration ratio 3:1+ (Read+Grep+Glob vs Edit+Write) |
| Analogia `/ground` | Analysis | Checking if abstract advice fits your situation | Abstract pattern application without domain validation |
| Periagoge `/induce` | Analysis | Concrete cases accumulating into an unnamed essence — crystallize the emerging abstraction | 3+ instances with essence intuition but no located abstraction; `/ground` misfit where colimit is forced into substitution |
| Syneidesis `/gap` | Decision | Right before committing, checking for blind spots | Same file 3+ edits (different concerns), `excessive_changes` friction |
| Prosoche `/attend` | Execution | Risk-classified execution — safe actions flow, risky ones gate | Mixed-risk plans (bulk safe work + judgment moments), upstream deficit signals, `wrong_file_edited` friction |
| Epharmoge `/contextualize` | Verification | Output is correct but doesn't fit the accumulated conversation context | Mismatch against session-built constraints (user-aware context accumulation) |
| Elenchus `/sublate` | Verification | About to externalize a working context whose apparent sufficiency has decayed | Dialectical antithesis per source (provenance / counterfactual / cross-source consistency) before pre-execution sync |
| Horismos `/bound` | Cross-cutting | Deciding what to delegate to AI | Boundary probe, domain classification, BoundaryMap |
| Anamnesis `/recollect` | Cross-cutting | Resolving vague recall of prior sessions or discussions | Cross-session state recovery via narrative recognition (Recognition over Retrieval) |
| Katalepsis `/grasp` | Cross-cutting | Rapid comprehension verification via intent-scented entry points | User-intent grasp for AI-completed work, reviews, plans, docs, or code changes |
| Diylisis `/distill` | Cross-cutting | Distilling a session-tethered working context into a self-contained portable handoff for a fresh zero-memory recipient | Handoff brief / fresh-context subagent dispatch / resumable plan with undefined jargon, deictic anchors, or dangling task ids |
| Hyphegesis `/conduct` | Cross-cutting | Conducting the method of a multi-move work prospect before object-level cognition — order, independence, reconciliation, termination, routing | Multi-move work with non-trivial conduct (migrations, staged investigations, entangled adversarial/parallel/synthesis); "how should I approach this whole thing?" meta-questions |

## Phase Execution

### Phase 0: Entry (Path Selection)

Do NOT present the full protocol catalog upfront. Start with a concise welcome and path selection.

**Gate #1**:
- Text: Path selection prompt
- Options:
  - Quick recommendation (Recommended)
  - Learn a specific protocol
  - Browse all protocols

**If Quick recommendation**: set `path = quick`, proceed to Phase 1.

**If Browse all**: Present the protocol catalog (check installation status via Glob `~/.claude/plugins/cache/epistemic-protocols/*/`, then render the 14 protocols from Data Sources as a numbered list grouped by Cluster with name + "When to Use" + installation badge). After catalog, present:
- Text: Post-catalog path selection
- Options:
  - Quick recommendation
  - Learn a specific protocol (type name in Other)

Then proceed based on selection.

**If Targeted + Other contains protocol name**: proceed directly to session source question.

**If Targeted + no protocol specified**:

Present a condensed catalog as text output: render the Data Sources table grouped by Cluster, each protocol as `/command — When to Use description`.

Then **Gate #2**:
- Text: Protocol selection (type name or number in Other)
- Options:
  - Pre-execution (Planning) — /bound, /inquire, /elicit
  - Analysis/Decision — /frame, /ground, /induce, /gap
  - Execution/Verification/Understanding — /attend, /contextualize, /sublate, /recollect, /distill, /conduct, /grasp

**Gate #3** (Targeted only, session source):
- Text: Session source selection
- Options:
  - Personalize with my recent sessions
  - Use standard examples (no session needed)

State after Phase 0:
- `path`: quick | targeted
- `target_protocol`: (targeted only) selected protocol name
- `session_source`: (targeted only) scan | standard — Quick path always runs Quick Scan

**Skip rule**: If targeted + standard → skip Phases 1-2, jump to Phase 3 with preset scenarios from `references/scenarios.md`.

### Phase 1: Quick Scan (User Context Profile) — Inline

Build a User Context Profile from recent session metadata. Runs inline with Glob + Read (no subagent delegation). Both Quick and Targeted paths share this phase.

**Step 1: Collect session metadata**

Glob `~/.claude/projects/*/sessions-index.json` (exclude directories containing `-worktrees-`). Read the 2-3 most recently modified indexes. For each, parse `entries` and extract the 5 most recent entries' `firstPrompt` and `summary` fields.

**Step 2: Infer User Context Profile**

From collected metadata, infer:
- **Work domains**: What areas the user works in (e.g., API development, infrastructure, data pipeline)
- **Conversation patterns**: Request clarity level, incremental vs. batch requests, question types (how/why/what)
- **Task types**: Ratio of feature development, debugging, refactoring, documentation

If no `sessions-index.json` files found: Quick path proceeds to Pick-1 with fallback (`/elicit`); Targeted pa