jordanhindo

Use to recall anything from past agent sessions with the server-free `lore` CLI — the "what did we decide", "how did we build X", "why did we drop Y", "find that earlier conversation", "pull context from my last session" task. Trigger whenever you need memory of prior work (yours or another harness's) — searching transcripts by keyword or recency, reading a remembered message back in full, seeing what surrounded it, skimming or jumping around a past session, listing recent sessions, or charting when a project was active. Also covers writing new memory in live (`lore push`). This skill is self-bootstrapping — if the CLI isn't installed or your sessions aren't indexed yet, it covers setup too (detail in references/setup/index.md) — installing lore, indexing or backfilling a harness (Claude Code, Codex, Cursor, Cline, openclaw, Hermes, or any tool that records transcripts), teaching lore a new format by writing and proving an adapter, registering the MCP server, wiring freshness hooks, or feeding a live process

Produces proposal-only Lore continuity briefs for the last 24 hours by default, with cited evidence, open work, learned signals, memory-card candidates, contradiction candidates, and sideEffects:false. Use for daily briefs, recap/continuity summaries, scheduled read-only synthesis, or proposing next actions from Lore without creating anything automatically.

Builds compact Lore continuation handoff packets with verified/open/stale/risky sections, cited evidence, artifacts, shared proposal vocabulary, unresolved questions, and no transcript dumps. Use when handing work to another agent, resuming later, compacting active work, or preparing next-agent context from Lore.

Plans and executes bounded Lore memory recall with status checks, query expansion, context drill-down, freshness labels, cited evidence packets, and retrieval-failure recovery. Use whenever an agent needs to answer from past Lore sessions, recall decisions, inspect last-session context, verify what happened before, or explain gaps without dumping transcripts.

Verifies changes to the Lore repo and Lore workflow skills. Use when working on Lore PRs, issue slices, recall/brief/handoff skills, CLI/MCP retrieval, store migrations, adapters, privacy/destructive-memory behavior, packaging, or any change that needs proof before it is called done.

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

Use when creating new skills, editing existing skills, or verifying skills work before deployment

Use when creating or improving a skill for an AI agent, especially when the skill needs strong trigger wording, project-local context, references, scripts, tests, self-healing rules, or a completion gate another agent could follow without guessing.

Use when an agent needs to generate or update release notes from structured project changes, especially when the repository defines local output paths, release-note conventions, or validation requirements.

Use when creating or improving a skill for an AI agent, especially when the skill needs strong trigger wording, project-local context, references, scripts, tests, self-healing rules, or a completion gate another agent could follow without guessing.

Complete guide for setting up and using MERIDIAN Brain Enhanced - an intelligent agent operating system with RLM-based memory, personality modes, and configuration management. Use when: (1) Setting up MERIDIAN Brain for the first time, (2) Configuring memory systems, (3) Managing personality modes and sliders, (4) Understanding MERIDIAN architecture, (5) Troubleshooting MERIDIAN issues, (6) Integrating MERIDIAN into agent workflows. This skill covers both the enhanced memory system (RLM-based) and the original MERIDIAN Brain framework (personalities, sliders, gauges).

Git-backed issue tracker for multi-session work with dependencies and persistent memory across conversation compaction. Use when work spans sessions, has blockers, or needs context recovery after compaction.

Bootstrap lean multi-agent orchestration with beads task tracking. Use for projects needing agent delegation without heavy MCP overhead.

Build, inspect, modify, test, and improve real Unity game projects as an autonomous AI game-development agent. Use this skill whenever the user asks for Unity work, Unity C# scripting, scene or prefab fixes, gameplay prototypes, creating a Unity game from a rough or empty project, playable vertical slices, Unity build/debugging, Unity MCP workflows, or game projects such as Veyrath - Ashes of the Wild Crown. This skill is especially important when the agent has local filesystem, shell, Unity Editor, MCP, or daemon-style project-agent access and must keep the game playable while making professional improvements.

Verify Unity game-development agent work and the unity-game-development-agent skill package. Use this whenever reviewing Unity agent outputs, checking whether a Unity project was safely inspected or modified, validating playable-slice claims, auditing scene/prefab/reference risk, or deciding whether a Unity skill package has enough files, references, scripts, templates, evals, and proof gates for a novice agent.

Ingest URLs, YouTube videos, and local files (PDF/DOCX/etc) into the Daemion knowledge wiki. Triggers on "ingest", "add this", "remember this article/video". CRITICAL — extraction writes to raw/ only; you are NOT done until you READ COLD, FLAG CONTRADICTIONS with the existing wiki, propose a DECIDED compile plan, and compile with the user via knowledge-wiki skill. Silently overwriting existing claims or reporting "ingested successfully" after extraction alone is a skill violation.

Second-brain wiki. Capture, compile, query, lint. CRITICAL — you are the LIBRARIAN. You decide structure (where pages go); the user decides signal (what's worth keeping). READ COLD before mapping to existing pages. DEFAULT to extending pages over creating new ones. NEVER silently overwrite — preserve contradictions with attribution. Stopping at raw/ and reporting "done" is a skill violation.

Operate the Command Center task tracker at stacean.vercel.app. Use when creating, updating, or managing tasks via Beads CLI, syncing to Vercel KV, or working with the dashboard UI. Covers the 6-status workflow (todo → in_progress → needs-you → review → ready → shipped), beads commands, KV sync, and all tracker APIs.

Meta-skill that catalogs all available skills, explains when and how to use each one, and auto-discovers new skills. ALWAYS read this skill first before starting work to understand what tools are available. Use this as the single source of truth for skill selection.

Use when an agent is executing work in any project repo and needs to coordinate with a human or other agents via BeadBoard. BeadBoard is the human-facing dashboard running separately; this skill is the agent-side operating contract for state, mail, assignment, and evidence flow.

Frontend design skill for creating premium, Awwwards-level UIs with Tailwind CSS. Provides magic prompt formulas, color palettes, and design patterns for stunning landing pages, dashboards, and components.

Use when an agent needs persistent, policy-scoped memory with strict verification gates and a single canonical package path.