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 A PRAXIC pass that de-weeds a practice's epistemic graph — resolve stale/superseded findings, close answered unknowns, verify or drop assumptions, archive done goals and stale sources, prune dangling edges — so retrieval surfaces what's live,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.