catalog
$
npx mdskill add jongwony/epistemic-protocols/catalogReference protocols instantly to match situations with the right epistemic command.
- Helps agents select correct protocols when context is insufficient or intent is implicit.
- Depends on scenarios.md and cluster groupings to organize protocol definitions.
- Decides recommendations by matching user queries to specific command patterns.
- Delivers results via overview cards, cluster details, or single protocol expansions.
SKILL.md
.github/skills/catalogView on GitHub ↗
---
name: catalog
description: "Protocol handbook — instant reference for when to use each epistemic protocol."
---
# Catalog Skill
Instant reference handbook for 11 epistemic protocols. Browse by cluster, look up by command, or find the right protocol for a situation.
## When to Use
Invoke this skill when:
- Quick reference: "which protocol handles X?"
- Browsing: exploring available protocols without commitment
- Situation lookup: matching a current situation to the right protocol
Skip when:
- Guided learning with practice and quizzes (use `/onboard`)
- Session analytics and growth analysis (use `/report`)
- Full coverage dashboard (use `/dashboard`)
## Argument Handling
| Invocation | Behavior |
|------------|----------|
| `/catalog` | Overview: 11 protocols grouped by cluster, 1-line each + usage hints |
| `/catalog {cluster}` | Cluster detail: expanded protocol cards with scenarios |
| `/catalog {command}` | Single protocol detail: full card from scenarios.md |
Argument normalization: case-insensitive, accepts `/command` or bare name (e.g., `/catalog inquire` = `/catalog /inquire` = `/catalog Aitesis`).
## Protocol Catalog
### Planning
| Protocol | Command | When to Use |
|----------|---------|-------------|
| Aitesis | `/inquire` | Context is insufficient for confident execution |
| Euporia | `/elicit` | Intent articulated but decision coordinates implicit in externalized substrate — reverse-trace to surface |
### Analysis
| Protocol | Command | When to Use |
|----------|---------|-------------|
| Prothesis | `/frame` | No framework — need analytical lenses or multi-perspective team |
| Analogia | `/ground` | Abstract idea needs concrete domain validation |
| Periagoge | `/induce` | Concrete instances accumulating — abstraction has not located itself |
### Decision
| Protocol | Command | When to Use |
|----------|---------|-------------|
| Syneidesis | `/gap` | About to act — potential gaps unexamined |
### Execution
| Protocol | Command | When to Use |
|----------|---------|-------------|
| Prosoche | `/attend` | Execution risks not yet classified or delegated |
### Verification
| Protocol | Command | When to Use |
|----------|---------|-------------|
| Epharmoge | `/contextualize` | Output is correct but may not fit the actual context |
### Cross-cutting
| Protocol | Command | When to Use |
|----------|---------|-------------|
| Horismos | `/bound` | Unclear who decides what — ownership boundaries undefined |
| Anamnesis | `/recollect` | Resolve vague recall into recognized context — /recollect (ἀνάμνησις: recollection) |
| Katalepsis | `/grasp` | AI did work but you don't fully understand what or why |
## Detail Mode
When a cluster name or protocol command/name is provided as argument:
1. Normalize the argument:
- Strip leading `/` if present
- Match case-insensitively against protocol names (Aitesis, Euporia, etc.) and commands (inquire, elicit, etc.)
- Match cluster names: planning, analysis, decision, execution, verification, cross-cutting
2. For **cluster** arguments: display all protocol cards in that cluster with expanded "When to Use" descriptions from the tables above.
3. For **protocol** arguments: call Read on `epistemic-cooperative/skills/onboard/references/scenarios.md`, extract the matching `## ProtocolName /command` block, and present:
- **Situation**: the scenario description
- **Intervention**: how the protocol helps
- **Philosophy**: the Greek etymology and core principle
- **Try it**: `/{command}` — direct invocation prompt
4. If no match found: list the closest matches and suggest `/catalog` for the full overview.
## Rules
1. **No gate interaction** — pure text output only. This skill is a passive reference, not an interactive dialogue.
2. **No delegation** — main agent handles all output directly. Read tool for scenarios.md detail mode only.
3. **Static overview, dynamic detail** — the Protocol Catalog tables above are embedded and authoritative. Detail mode reads scenarios.md at runtime for richer content.
4. **Argument normalization** — accept case-insensitive input; strip `/` prefix; match against both protocol names and commands.
5. **Graceful fallback** — unrecognized arguments get closest-match suggestions plus the full overview.
6. **Distinction from /onboard** — catalog is passive reference (read and go); onboard is active learning (scenario, trial, quiz). Never redirect to onboard unless the user explicitly asks for guided learning.
More from jongwony/epistemic-protocols
- attendRoute upstream epistemic deficits and evaluate execution-time risks during AI operations. Scans for unresolved upstream protocol needs, materializes intent into tasks, classifies each for risk signals, delegates low-risk tasks to executor, and surfaces elevated-risk findings for user judgment. Type: (ExecutionBlind, User, EVALUATE, ExecutionContext) → SituatedExecution. Alias: Prosoche(προσοχή).
- audit-deltaPeriodic progress-tracking re-run of the c059212d epistemic-protocols audit. Surveys state of audit-derived GitHub issues (#237-#241) and Deterministic Queue items (DQ1-DQ8) via gh CLI, traces commit activity in audit scope files (Track Alpha + Track Beta), scans for emergent audit targets in newly opened issues, and produces a progress report at docs/audit-delta-YYYY-MM-DD.md. Invoke this skill whenever you want to check 'how much of the previous epistemic audit is resolved', 'track audit issue status', 'see what changed in the audit scope since the last run', 'find new audit items', or run /audit-delta. Invoke on demand for weekly-to-monthly audit progress checks. This is a lightweight delta tracker, not a fresh ensemble re-audit.
- boundDefine epistemic boundaries per decision. Produces BoundaryMap classifying domains as user-supplies, AI-proposes, or AI-autonomous when boundary ownership is undefined. Type: (BoundaryUndefined, AI, DEFINE, TaskScope) → DefinedBoundary. Alias: Horismos(ὁρισμός).
- clarify[Deprecated — use /elicit (Euporia) for axis-emergent reverse induction] Clarify intent-expression gaps. Extracts clarified intent when what you mean differs from what you said. Type: (IntentMisarticulated, Hybrid, EXTRACT, Expression) → ClarifiedIntent. Alias: Hermeneia(ἑρμηνεία).
- comment-reviewReview markdown artifacts before fixation (publish/commit/deposit/merge) via /inquire × /gap × /contextualize through a channel-first browser preview loop. User-invoked via /comment-review.
- composeProtocol composition authoring assistant — build composition SKILL.md files from protocol Lego blocks. Validates chains against graph.json, analyzes gate dispositions via the Constitution/Extension classification model, and generates pipeline templates. Use when the user asks to 'compose protocols', 'create composition skill', 'build protocol chain', 'combine protocols', or wants to author a composition workflow like /review.
- contextualizeDetect application-context mismatch after execution. Verifies applicability when correct output may not fit the actual context, producing contextualized execution. Type: (ApplicationDecontextualized, AI, CONTEXTUALIZE, Result) → ContextualizedExecution. Alias: Epharmoge(ἐφαρμογή).
- cursesDiscover the structural costs hidden in your strengths through behavioral dimension analysis, strength-shadow extraction, and attitude recommendations.
- dispatchDelegated parallel issue resolution via /dispatch. User sets a minimal delegation contract (or accepts profile-derived defaults); AI categorizes open issues by project mission/direction (read from the project guide) and evidence-accumulation status (whether substrate-cited locks are satisfied), fans out per-category sub-branches with per-category PRs, then loads review feedback and inscribes rejection traces to the linked issues so a fresh-context next session can re-enter without re-deriving the rejection. Reads the project's profile rule and editing conventions for personalization. Use when the user asks to 'resolve as many open issues as possible', 'process the open backlog', 'work through pending issues', or invokes /dispatch.
- elicitResolve via Extended-Mind reverse induction. Reverse-traces decision coordinates from externalized substrate (codebase, rules, past sessions, user environment) and surfaces them through cycle-emergent dimension projections; user answers explicate the coordinates until intent crystallizes. Type: (AbstractAporia, Hybrid, REVERSE-INDUCE-CYCLE, IntentSeed × ExternalizedSubstrate) → ResolvedEndpoint. Directional dual to Periagoge. Alias: Euporia(εὐπορία).