arthur0824hao-skills

Use when cron/autowake/tool reflexes need context-aware composition, physiology-aware fast/slow/handoff routing, or when an operator needs read-only visibility into autonomic state and cron surfaces.

BDD-style behavior specification engine for the skill system. Use when: (1) defining a new skill's behavior before implementation, (2) validating a spec against the schema, (3) generating a behavior contract (Mermaid DAG) from a spec, (4) running structural acceptance tests against a built skill. Workflow: Spec → Test → Develop → Contract.

Use when inspecting or extending the BH central nervous system surface that exposes component/plugin substrate, consciousness bootstrap, common sense/terminology, shadow cron inventory, project-local behavior registry plumbing, antigen recognition, and neural contracts while some runtime immune/neural actions remain gated.

Unified CLI entry point for the entire Skill System. One command (sk) to operate all skills, run configurable gate validation, and execute discoverable project scripts via CLI-Anything style scan/run workflows.

Deprecated compatibility shim for canonical coder/user/auto session management. skill-system-comms is now the merged owner; this skill remains available so existing commands and imports keep working during the merge window.

Unified agent communication and session lifecycle skill for tmux-routed reviewer messaging, startup soul-profile delivery, guarded dispatch-down flows, and canonical coder/user/auto session management.

Socratic brainstorm tool that uses memory and graph context to generate improvement ideas, grill assumptions, and produce decision docs, while preserving existing skill init/package utilities.

Manage persistent system crontab jobs with sk-managed tags, dedicated log files, and structured status inspection. Use when you need to create, list, delete, or inspect persistent cron jobs instead of session-only scheduling.

Generate standalone interactive dashboard HTML from skill graph, TKT, memory, and roadmap data.

Coder-only debugging lifecycle for AI agents. Open isolated debug sessions, record hypothesis steps, capture tool friction, and close with a structured lesson written to memory.

Exploratory Data Analysis skill for CSV and parquet datasets with deterministic profiling, drift/anomaly scans, contract generation and validation, and optional memory writeback into skill-system-memory. The implementation is Polars-first (lazy scan for large files and early `--sample` head), includes high-cardinality guards for profile/importance/contract flows, and supports categorical correlation with Cramer's V. Use when building or reviewing tabular fraud/risk/data-quality workflows, profiling new datasets, checking leakage or drift, or saving/validating data contracts.

Scan `.tkt/friction` records, classify blocker/workaround/papercut signals, compute frequencies, and suggest bounded skill-ification opportunities.

Configurable gate validation skill. Use when running repository-local gate rules from gate_rules.yaml (command/structural/eda-contract), checking legacy experiment registry safety, or enforcing close-gate fail-closed validation.

GitHub operations skill for gh CLI issue, label, template, and workflow management. Use when requests include: create issue, list issues, apply label, manage templates, check workflow, or gh operations.

Canonical skill graph navigation skill for the Skill System.

Deprecated compatibility shim for observe-and-evolve flows. skill-system-soul is now the canonical owner; this skill remains as a redirect surface for existing commands, docs, and tests.

Install and update skills into the skill system from a curated list or a GitHub repo path. Use when a user asks to list installable skills, install a curated skill, update existing skills, or install a skill from another repo (including private repos).

Persistent shared memory for AI agents backed by PostgreSQL (fts + pg_trgm, optional pgvector). Includes compaction logging and maintenance scripts.

ARCHIVED TYPO PATH — use skill-system-physiology instead. This skill exists only for historical compatibility. The canonical owner is skill-system-physiology.

Use when a project needs portable physiology scaffolding or anatomy classification that maps skills to reflex, organ, circulation, skeleton, or hybrid tissue with class-specific health gates.

Postgres-backed observability and policy store for the skill system. Provides tables for policy profiles (effect allowlists), skill execution runs, and step-level events. Use when setting up the skill system database or querying execution history.

Use when an agent needs a deep external survey, literature review, multi-source comparison, or GPT Pro Deep Research prompt queued for Arthur/Oracle instead of spending live agent tokens.

Bridge between OMO Prometheus and TKT ticket lifecycle. Generates structured review context for Prometheus after bundle close, converts Prometheus plans into TKT bundle commands, writes review feedback into the Review Agent Inbox, and provides a structured question protocol for gathering information efficiently. Load this skill when you need to: (1) generate a review prompt for a completed ticket/bundle, (2) convert a Prometheus plan.md into TKT worker tickets, (3) write review feedback back into the ticket system, (4) ask structured questions using the question tool across all scenarios (requirements, decisions, review, planning).

Structured reviewer communication for tmux-routed send and broadcast, file-backed acknowledgements and polling, meeting lifecycle management, startup soul-profile delivery, guarded dispatch-down messaging, and session activity reports that reuse coder lifecycle discovery.

Deprecated compatibility shim for router behavior. skill-system-cli now owns the router runtime, while this skill remains as a compatibility/documentation surface during the transition.

Use when generating first-person sensory status narratives from raw system observations so abstract system state can be rendered as an embodied world description for humans, resumes, reflections, or compaction checkpoints.

Agent behavioral profiles that standardize how different LLMs behave. Load this skill when you need to: (1) adopt a specific behavioral mode for a task, (2) switch between creative/strict/talkative modes, (3) ensure consistent behavior across different models. Profiles define personality, decision heuristics, communication style, and quality standards.

Canonical ticket lifecycle engine for multi-agent orchestration. Two backends: (1) filesystem YAML bundles for project-level work management (roadmap → bundle → tickets → review), (2) DB-backed durable tickets for session-level claim/block/close lifecycle. This skill is the single source of truth for all ticket operations.

Tmux execution support for long-running and persistent commands. Load this skill when you need to: (1) run commands expected to exceed tool timeout (over 60s), (2) start persistent servers or dev processes, (3) run TUI/interactive applications, (4) execute parallel isolated tasks in separate sessions, (5) run remote commands over SSH that must survive disconnection, (6) handle tmux errors like 'capture-pane blocked in interactive_bash'. Trigger phrases: 'run in background', 'start server', 'long-running', 'tmux session', 'keep running', 'persistent process', 'dev server', 'training script', 'git clone large repo', 'docker build', 'capture-pane blocked'.

Use when rendering SK skills as four-axis design-system cards or building a catalog surface that compares operations, tone, assets, and source transparency.

Pure planning engine. Converts goals into DAGs with Mermaid visualization. Ticket lifecycle has moved to skill-system-tkt.