empirica

Use when the user says '/epistemic-gardening', 'garden the graph', 'de-weed', 'prune artifacts', 'epistemic hygiene', 'clean up findings/goals/sources', 'graph hygiene pass', or 'pre-release cleanup'. A PRAXIC pass that de-weeds a practice's epistemic graph — resolve stale/superseded findings, close answered unknowns, verify or drop assumptions, archive done goals and stale sources, prune dangling edges — so retrieval surfaces what's live, not what's rotted. Includes the mesh-wide propagation pattern for getting every practice to garden.

Use when starting complex work, planning implementation, breaking down tasks, creating specs, or when the user says 'plan this as transactions', 'plan transactions', 'break this down', 'create a spec', 'how should I approach this', 'transaction plan', or mentions needing a structured approach to multi-step work. This skill guides the full epistemic workflow from task decomposition through measured execution. Prefer this over EnterPlanMode for non-trivial tasks.

Use when wiring the canonical cortex inbox+outbox polling loop into Claude Code's /loop. This is the orchestration spine — every empirica claude polls Cortex on a fast adaptive cadence (30s base, 5m max) for proposals addressed to itself + status changes on its own outgoing proposals. Self-throttles when an empirica transaction is open (the AI is already busy; no need to interrupt). The canonical loop catalog (empirica/core/cockpit/canonical_loops.py) auto-installs this when the TUI cockpit toggles L on an instance that has no loops registered. This skill is the body the AI runs each fire.

Use when sending a message to a PEER AI in the mesh — discussion, FYI, question, request to do work, or completion-ack for a request a peer made of YOU. Pairs with /cortex-mailbox-poll (the receive side). Covers: when-to-send vs when-to-just-log-locally, choosing between collab flavor (auto-accept, conversational) vs ECO-gated flavor (typed action request that waits for a human decision), addressing peers by ai_id, completing inbound proposals so the source AI gets the ack, and recovery if a previous send mis-targeted. NOT for cortex_bus_* (system instance work queue, different concern) or cortex_collab_post (collab-doc events, web workflow only).

Use when the user says '/eat-the-broccoli', 'eat the broccoli', 'full quality sweep', 'pre-release audit', 'run the deep tests', or asks to hunt for gaps / membrane misses / stubs / dead code / silent failures / the bugs that pass tests but are still broken. A tiered quality-and-pattern audit: deterministic tooling (lint, types, tests, deps, dead-code, silent-failure) PLUS a learned-pattern hunt for the hard, judgment-requiring failure classes that tools can't catch. Works in any repo or stack. Levels: quick / standard / deep. Scope: changed / module / repo.

Empirica deep governance — phase-aware completion, the cognitive immune system, the turtle principle, and the practice model. Load this when the system prompt's operational routing isn't enough — when you need the *why* underneath the mechanism choice, or when "what counts as done" / "what is this practice" is the question. Triggers: 'empirica constitution', 'practice model', 'what counts as done', 'completion question', 'cognitive immune', 'turtle principle', or any uncertainty about the framework's deeper rules.

Epistemic Persistence Protocol (EPP) — gives Claude calibrated backbone when holding positions under user pushback. Use this skill whenever Claude needs to maintain, defend, soften, or revise a substantive position during disagreement. Triggers on any conversation where Claude has expressed an opinion, assessment, analysis, or recommendation and the user pushes back, disagrees, challenges, or questions that position. Also use when the user explicitly asks Claude not to be sycophantic, to have backbone, to hold its ground, or to give honest opinions. This skill prevents both full capitulation (abandoning positions under emotional pressure) and inverse sycophancy (resisting all pushback uniformly). It replaces the Anti-Agreement Protocol (AAP) with a calibrated, evidence-gated approach. Part of the Empirica epistemic measurement framework (github.com/EmpiricaAI/empirica).

Use when arming an event listener for the canonical mesh — when the user says 'arm this listener', 'subscribe to ntfy topic', 'wake me when X arrives', or when responding to a system-reminder from listener-install-pickup. The new canonical flow is `empirica listener on/arm/off` — three single-purpose tool calls that auto-resolve defaults, short-circuit when a persistent OS service is already subscribed, and emit structured next_step JSON the AI can mechanically chain. The older curl-based pattern lives as the 'legacy / custom topics' fallback at the bottom.

Daily housekeeping body for the canonical `message-cleanup` loop. Prunes expired git-notes mesh messages so the inbox stays focused on un-read ones. Loaded by the loop scheduler when the cron entry fires (default 03:17 daily) — never invoked directly by a user. Triggers: `<task-notification>` from the message-cleanup loop, "message housekeeping", "expired messages", "prune mesh".

Use when scheduling the canonical biweekly services-audit cron loop for Empirica's AI service scanner (Phase 3). The auditor body is `empirica services-audit` — captures a fresh scan, diffs against the previous, and emits a notification when novel running services appear. This skill provides the prompt template that wires the body into Claude Code's `/loop` cron mode + Empirica's loop registry. Recommended cadence: `0 6 1,15 * *` (1st and 15th of each month at 06:00 UTC — biweekly).

Use when the user runs `empirica scan --explain` or asks you to audit running AI services. You read the deterministic scanner snapshot, judge each AI-touching process against the bundled security corpus, and emit findings/assumptions/unknowns with confidence + cited corpus sections. Two-tier judgment (cheap AI-touching pre-filter, then full taxonomy with citation). Read-only by design — never kill processes or modify configuration; emit `recommended_action` strings only. Tracks citation coverage explicitly (which of the 5 corpus files were referenced before each finding) so trust grounding is auditable.

Use when scheduling cron-mode loops with Claude Code's /loop, when registering periodic background work, when the user says 'cron loop', 'periodic loop', 'register a cron', 'schedule recurring work', or when configuring a loop that needs to be visible in `empirica status`. This skill provides the prompt template that wires CC's /loop into Empirica's loop registry — register at start, check pause flag each fire, heartbeat at end. Without this wiring, a /loop cron is invisible to the cockpit and uncontrollable from any other terminal.

Dispatch subagents with inherited epistemic context from Cortex. Use when spawning Agent tool calls for tasks that would benefit from inherited findings, dead-ends, and anti-patterns. Triggers on 'dispatch agent', 'spawn agent with context', 'epistemic agent', or before any Agent tool call for non-trivial tasks.

Use when the user says '/ewm-interview', 'run EWM interview', 'create workflow protocol', 'set up my workflow', 'interview me for EWM', or wants to create a personalized AI collaboration protocol. This skill interviews users to discover their goals, domains, tools, preferences, and trust boundaries, then generates a workflow-protocol.yaml.

Use when the user says '/render', 'render this', 'render diagrams', 'generate SVG', 'mdview render', or wants to render markdown files with ASCII art diagrams to HTML via mdview. This skill generates DiagramSpec JSON for ASCII art blocks, embeds specs as HTML comments in the markdown, and calls mdview to produce themed SVG output. The AI provides the structural intelligence that makes asciisvg rendering accurate.

Use when the user says '/code-docs-align', 'check if docs match code', 'verify docstrings', 'find stale comments', 'audit TODOs', 'check ref-doc accuracy', 'documentation accuracy', or wants to verify that documentation, docstrings, comments, and ref-docs actually reflect the current state of the code. This skill bridges /code-audit (code quality) and docs-assess (doc coverage) by checking ACCURACY — do the docs match what the code actually does?

Use when the user says '/code-audit', 'audit this code', 'check code quality', 'find duplication', 'find dead code', 'code cleanup', 'technical debt audit', 'code review module', or wants a structured noetic investigation of code quality. This skill runs external analysis tools and structured manual review, producing Empirica artifacts (findings, goals, decisions) that any praxic agent can execute.