SpillwaveSolutions

Installation and configuration skill for Agent Brain document search system. Use when asked to "install agent brain", "setup agent brain", "configure agent brain", "setting up document search", "installing agent-brain packages", "configuring API keys",…

Add an idea to the backlog parking lot (999.x numbering)

Add phase to end of current milestone in roadmap

Generate tests for a completed phase based on UAT criteria and implementation

Capture idea or task as todo from current conversation context

Audit milestone completion against original intent before archiving

Cross-phase audit of all outstanding UAT and verification items

Run all remaining phases autonomously — discuss→plan→execute per phase

Ingest a PRD journey section as Persona, UserJourney, JourneyStage, Scenario, and UserStory concepts, and link them to Features, Epics, and work Stories. Use when a PRD must drive story mapping.

Check PKC toolchain (python, ripgrep, SQLite FTS5) and optionally install ripgrep after the user consents. Use when search/pack is slow, rg is missing, or the user asks to set up PKC.

Bind a Grok Bot agent to Project Knowledge Capture. Isolation, identity, deterministic capture.

Build a progressive-disclosure context pack for a Feature (or any concept). Supports --tiny (1 hop / 8 nodes) for chat focus and mermaid graphs. Auto-run when starting work on a Feature.

Spawn the knowledge-retriever sub-agent to search and pack project memory without contaminating parent context. Use before answering from the OKF tree, or when starting work that needs Feature/Decision context.

Full-text search over the knowledge bundle (AND terms, type filters). Use when finding decisions, meetings, or features by keyword.

Run a one-screen health check on a PKC knowledge bundle — broken links, orphans, thin Features, decision conflicts, open Questions, stale Discoveries/Assumptions, toolchain (ripgrep). Use when auditing knowledge quality or before a release.

Refresh, inspect, or drop the disposable SQLite/FTS5 knowledge index. Use when search/pack/validate is slow, after a large git checkout, or when the user asks about the PKC index.

Bind data-engineering-knowledge-capture for LangChain Deep Agents / Deep Agents Code.

Bind a Grok Bot agent to Data Engineering Knowledge Capture. Isolation, identity, deterministic writes.

Breadth-first reverse-engineering plan — map scan roots and optional exports, rank focus areas, emit deep-dive checklists. Pause here before spawning specialists. Not query-time retrieve.

Walk a data lake/warehouse filesystem or ingest Fabric/Power BI inventory JSON into DEKC.

Build progressive-disclosure context packs for a data concept.

Query-time DEKC retrieval. Spawn data-retriever; parent gets a summary card only. Use for Table, Metric, LineagePath, IngestionJob, Transformation, Dashboard, DataProduct, GlossaryTerm, BusinessObject questions.

Full-text search over the DEKC knowledge bundle (AND terms, type filters). Use when finding tables, lineage, or metrics by keyword.

Query the DEKC OKF second brain with design intents (reports, land data, metrics, impact). Uses standard concept schemas under schemas/okf-concepts/.

End-to-end reverse-engineer one or more git repositories into a SAC architecture knowledge graph (packages, services, IaC, CI/CD, IAM, identity, topology). Plan breadth-first, then fan out area walkers. Primary entry skill for SAC.

Breadth-first reverse-engineering plan — map monorepo/multi-repo roots, rank focus areas, emit deep-dive checklists. Pause here before spawning area walkers. Not query-time retrieve.

Bind a Grok Bot agent to System Architecture Capture. Isolation, identity, deterministic reverse-engineering.

Run deterministic architecture scanners (packages, containers, IaC, K8s, CI/CD, identity) against a code root without writing knowledge.

Bind a Cursor agent (including Grok Bot cloud sessions) to the system-architecture-capture ContentPack.

Bind System Architecture Capture for LangChain Deep Agents / Deep Agents Code.

Use the SAC architecture second brain when designing new features, services, APIs, mobile apps, web apps, or infra. Loads progressive-disclosure packs (blast radius, contracts, deps, environments) so design work reuses existing topology instead of inventing…

Build progressive disclosure context packs (default 2-hop) for precise LLM queries over architecture knowledge.

BM25 keyword search for agent-memory. Use when asked to "find exact terms", "keyword search", "search for specific function names", "locate exact phrase", or when semantic search returns too many results. Provides fast BM25 full-text search via Tantivy index.

Query past conversations from the agent-memory system. Use when asked to "recall what we discussed", "search conversation history", "find previous session", "what did we talk about last week", or "get context from earlier". Provides tier-aware retrieval with…

Agent retrieval policy for intelligent memory search. Use when implementing memory queries to detect capabilities, classify intent, route through optimal layers, and handle fallbacks. Provides tier detection, intent classification, fallback chains, and full…

Topic graph exploration for agent-memory. Use when asked to "explore topics", "show related concepts", "what themes have I discussed", "find topic connections", or "discover patterns in conversations". Provides semantic topic extraction with time-decayed…

Semantic vector search for agent-memory. Use when asked to "find similar discussions", "semantic search", "find related topics", "what's conceptually related to X", or when keyword search returns poor results. Provides vector similarity search and hybrid…

Wizard-style configuration guidance for a single-agent agent-memory setup. Shows defaults inline, provides a full sample config, and includes a dry-run config check step. Always confirm before creating or editing files.

Wizard-style installation guide for agent-memory (macOS/Linux). Helps users choose an install path, check prerequisites, and set PATH. Always confirm before any file edits or copying binaries. Provide verification commands only.

Diagnostic and troubleshooting workflow for agent-memory. Guides users through common install/config/daemon/ingest issues. Requires confirmation before any edits or restarts. Provides verification commands only.

End-to-end reverse engineer of agent codebases (Claude/ChatGPT APIs, LangChain/LangGraph, CrewAI, LlamaIndex, Claude Agent SDK, Deep Agents, MCP, AgentCore, microVMs) into a draft AGER OKF knowledge graph. Primary reverse entry skill for okf-agent-graph…

Scan a codebase for agent frameworks (LangGraph, CrewAI, LlamaIndex, Claude/OpenAI APIs, MCP, Deep Agents, hyperscalers, microVMs) and for Claude/Grok/Codex/universal plugin agents and skills. Extracts prompts, tools, schemas, orchestration, loops, harness…

A helper skill that formats commit messages.

You are the orchestrator. You are the only role in this loop that writes the real patch.

Helper skill for patch drafting conventions.

Supporting grok skill for review checklists.

Grok plan-loop skill that coordinates the planner worker.

You are the orchestrator. You are the only role in this loop that writes the real ticket file or talks to GitHub.

Master RuleZ, the high-performance AI policy engine for development workflows. Use when asked to "install rulez", "create hooks", "debug hooks", "hook not firing", "configure context injection", "validate hooks.yaml", "PreToolUse", "PostToolUse", "block…

RuleZ release workflow automation. Use when asked to "release RuleZ", "create a release", "prepare release", "tag version", "hotfix release", or "publish RuleZ". Covers version management from Cargo.toml, changelog generation from conventional commits, PR…

RuleZ release workflow automation. Use when asked to "release RuleZ", "create a release", "prepare release", "tag version", "hotfix release", or "publish RuleZ". Covers version management from Cargo.toml, changelog generation from conventional commits, PR…

Coordinates planning, delegation, and evaluation across architect and code agent workspaces. Use when asked to "write instructions for code agent", "initialize architect workspace", "grade code agent work", "send instructions", or "verify code agent setup".

Create Mermaid diagrams (activity, deployment, sequence, architecture) from text descriptions or source code. Use when asked to "create a diagram", "generate mermaid", "document architecture", "code to diagram", "create design doc", or "convert code to…

This skill should be used when creating professional software documentation (SRS, PRD, OpenAPI, user manuals, tutorials, runbooks) from templates (greenfield) or reverse-engineering documentation from existing code like Spring Boot or FastAPI (brownfield).…

Git CLI operations, workflows, and automation for modern development (2025). Use when working with repositories, commits, branches, merging, rebasing, worktrees, submodules, or multi-repo architectures. Includes parallel agent workflow patterns, merge…

GitHub CLI (gh) command reference for repository search, code discovery, CI/CD monitoring, workflow authoring, and automation. Triggers on "gh" commands, "github cli", searching repos for files/directories (.skilz, .cursor, .codex, Dockerfile), monitoring…

Propose work items from recent conversation (flag-gated classifier). Use when the Stop hook requests classification or when asked to sweep a conversation for untracked work. Propose-only: writes .work/suggestions.jsonl, never the event log.

Generate or sync the design document or code walkthrough. Live current pair regenerated from the actual code; a release freeze is a short tag+hash+delta note, not a full dated copy. Uses document-specialist v3.2.2, design-doc-mermaid v1.1.1, plantuml v1.2.2.…

Look up how wiki_ticket_sdd integrates with a specific SDD tool or ticket/wiki system — Superpowers, GSD, SpecKit, OpenSpec, Jira, Confluence, GitHub, GitLab, Azure DevOps (ADO), AWS CodeCatalyst, or Google Cloud DevOps (GCP). Use when asked how to set up,…

Write rich, durable issue/ticket descriptions. Use when creating or updating tickets by hand, when composing bodies for ticket-sync, or when a work item needs a description a future reader (human or agent) can act on without archaeology.

Merge PRs only when all quality gates pass. Use whenever asked to merge a PR, complete a merge, or land a branch — arms GitHub auto-merge and falls back to polling instead of merging blind or bypassing.

Capture an approved plan as tracked work items. Use when exiting plan mode, when the user approves a plan, or says "capture this plan". Writes docs/plans/<date>-<slug>.md and appends the plan's tasks to .work/todo.jsonl via bin/worklog.

Decide what to work on next — use when asked "what should we do next", "what's most important", or when planning a new work session.

Write a high-context PR description for any substantial PR. Use whenever creating or editing a pull request body — the description must let a reader with zero prior context understand what is being built, why, where it sits in the larger system, and exactly…

After tick-hour, read .source.jsonl, apply the host-switch filter, write summary and saliency. Edition A (host CLI) or B (API key). Does not touch the snapshot.

Copy a host JSONL transcript into an immutable sessions/<slug>.source.jsonl snapshot. No LLM.

Scheduled hourly tick. Writes an Hour node only when the window has closed segments and no open ones. Sparse.

Commit a temporal node. The model proposes body text; this script writes frontmatter.

Drop telemetry files older than 90 days. Pruning is a git commit of the working tree.

Walk Year → Month → Week → Day → Hour → Session using only the filesystem.

Close sessions open longer than the global watchdog (default one hour). Per-role is phase two.

Load okf-time-series via LangChain Deep Agents SkillsMiddleware / skills=.

Bind a Cursor agent (including Grok Bot cloud sessions) to the second-brain-core ContentPack.

Bind LangChain Deep Agents to second-brain-core. Isolation, identity, deterministic writes.

Bind a Grok Bot agent to the second-brain-core ContentPack. Isolation, identity, deterministic writes.

Build a bounded ContextPack from a Second Brain Core root concept (default 2 hops, 20 nodes, 1/4 window token budget).

Spawn a retrieval sub-agent for second-brain Q&A so search and pack stay off the parent context.

Capture a Second Brain Core noun into the shared second brain via the deterministic write helper.

Open or close an isolated second-brain write session (worktree + PR). Use before writing when multiple agents share one knowledge remote.

Health-check the Second Brain Core catalogs and report empty indexes or missing schemas.

Curate OKF bundles — indexes, log.md, drift detection, broken links, orphan cleanup, staleness, and v0.1 to v0.2 migration. Use when the graph feels messy, catalogs are out of date, links break, content is stale, or the user asks to maintain, curate, or…

Create or update OKF concepts using the core envelope (type + title). This plugin owns Catalog and ContextPack only. For domain nouns, hand off to PKC, SAC, DEKC, or AGER.

Scaffold an OKF bundle for the graph engine — catalogs, knowledge, packs, index.md, log.md. Does not seed AgentNode, Workflow, TicketLink, or other domain nouns; those belong to PKC, SAC, DEKC, and AGER.

Compute the transitive impact (blast radius / ripple) of changing a concept in an OKF bundle. Use when the user asks what depends on a concept, what breaks if something changes, needs a ranked update list, or wants blast-radius / ripple analysis before…

Multi-hop query and subgraph extraction over OKF bundles for progressive disclosure. Use when packing minimal context for long-running agents, exploring the neighborhood of a concept, or answering what relates to X within N hops.

Validate OKF v0.2 conformance and graph quality — orphans, connectivity, staleness, unverified high-impact nodes, broken links, missing frontmatter. Use when checking bundle health, before commits/PRs, after bulk edits, or when the user asks if the OKF graph…

Visualize OKF bundles as Mermaid, HTML summaries, or JSON graphs. Use when the user wants a diagram of knowledge, an HTML map, or export for docs.

Bind a Cursor agent (including Grok Bot cloud sessions) to the okf-graph-eng ContentPack.

Bind a Cursor agent to RKC. Capture research into OKF. Do not project the graph.

Bind a Grok Bot agent to RKC. Isolation, identity, fail-closed writes.

Build an RKC ContextPack. Structural max_hops=2 plus Finding→Claim→Evidence spine. Question roots allow one inbound hop on answers.

Spawn research-retriever for RKC Q&A. Parent gets a summary card only. Do not pack inline.

Thin git-native RKC search (rg → scan). AND terms, type filter, limit, json. No Chroma or Kuzu.

Archive AI deep-research dumps and articles into RKC source-assets. Hash, copy, write SourceDocument + ResearchTask shells. Optionally run the Phase 2 extractor. Idempotent on bytes plus prompt hash plus extractor version.

Create missing Subject and ResearchArea nodes and write has_task / has_subject on an existing RKC tree. Idempotent repair for 0.2.0 archive-only ingest.

Segment an archived research dump, extract claims/evidence/findings, merge on claim_key, write a required PR summary. Fail-closed. Never auto-supersede accepted or verified nodes.