quangdang46

Diagnose mempalace setup (config, palace path, MCP, FTS/index health)

List or inspect people/project entities tracked in the mempalace graph

Mine a project directory into the mempalace corpus (drawers, rooms, wings)

Hybrid search over the mempalace corpus (BM25 + vectors + optional graph)

Show mempalace palace status (drawers, wings, rooms, health)

Trace a file, function, or line back to the agent session that produced its current commit

List recent git commits linked to agent sessions, optionally filtered by branch or repo

Delete specific observations or sessions from mempalace

Review RTCO Rust code for idiomatic simplification. Detects over-engineering, unnecessary allocations, verbose patterns. Applies Rust idioms without changing behavior.

Rust design patterns for RTCO. Newtype, Builder, RAII, Trait Objects, State Machine. Applied to CLI filter modules. Use when designing new modules or refactoring existing ones.

Issue triage: audit open issues, categorize, detect duplicates, cross-ref PRs, risk assessment, post comments. Args: "all" for deep analysis of all, issue numbers to focus (e.g. "42 57"), "en"/"fr" for language, no arg = audit only in French.

PR triage: audit open PRs, deep review selected ones, draft and post review comments. Args: "all" to review all, PR numbers to focus (e.g. "42 57"), "en"/"fr" for language, no arg = audit only in French.

Enforces TDD (Red-Green-Refactor) for Rust development. Auto-triggers on implementation, testing, refactoring, and bug fixing tasks. Provides Rust-idiomatic testing patterns with anyhow/thiserror, cfg(test), and Arrange-Act-Assert workflow.

Triage complet RTCO : exécute issue-triage + pr-triage en parallèle, puis croise les données pour détecter doubles couvertures, trous sécurité, P0 sans PR, et conflits internes. Sauvegarde dans claudedocs/RTCO-YYYY-MM-DD.md. Args: "en"/"fr" pour la langue (défaut: fr), "save" pour forcer la sauvegarde.

TDD workflow for RTCO filter development. Red-Green-Refactor with Rust idioms. Real fixtures, token savings assertions, snapshot tests with insta. Auto-triggers on new filter implementation.

Add GitHub Actions CI + release workflow + curl-pipe installer to any Rust CLI project. Generates only the minimal drop-in files: .github/workflows/ci.yml, .github/workflows/release.yml, and install.sh. Works for both single-binary repos and multi-crate Cargo workspaces. Use this skill whenever the user wants to add CI/CD, a release pipeline, or a curl install script to a Rust project, asks for "github actions for rust", "release workflow rust", "cross-compile rust ci", "install.sh for rust tool", or wants to wire up a new or existing Rust CLI for distribution.

Launch and manage a coordinated AI agent swarm using the Agentic Coding Flywheel methodology. Use this skill whenever the user wants to: start a multi-agent coding session, orchestrate Claude Code + Codex + Gemini agents in parallel, manage agent coordination via Agent Mail and bv, handle stuck agents or compaction, run review and hardening rounds, or tend an active swarm. Trigger on phrases like "launch agents", "start the swarm", "agent coordination", "agent mail", "multiple agents", "parallel agents", "marching orders", "swarm is stuck", "review round", "cross-agent review", "harden the code", or any mention of running multiple coding agents simultaneously.

Guide the multi-model planning phase of the Agentic Coding Flywheel methodology. Use this skill whenever the user wants to: start planning a new software project, create a comprehensive markdown plan, use multiple AI models to synthesize the best architecture, or iteratively refine a plan before writing any code. Trigger on phrases like "plan this project", "help me design", "create a markdown plan", "multi-model planning", "synthesize plans", "architecture for", or any request to think through a project before implementation. This skill should also trigger when the user describes a project idea and wants to figure out how to build it — even if they don't explicitly say "plan".

Launch and manage a coordinated AI agent swarm using the Agentic Coding Flywheel methodology. Use this skill whenever the user wants to: start a multi-agent coding session, orchestrate Claude Code + Codex + Gemini agents in parallel, manage agent coordination via Agent Mail and bv, handle stuck agents or compaction, run review and hardening rounds, or tend an active swarm. Trigger on phrases like "launch agents", "start the swarm", "agent coordination", "agent mail", "multiple agents", "parallel agents", "ntm spawn", "marching orders", "swarm is stuck", "review round", "cross-agent review", "harden the code", or any mention of running multiple coding agents simultaneously.

Add GitHub Actions CI + release workflow + curl-pipe installer to any Rust CLI project. Generates only the minimal drop-in files: .github/workflows/ci.yml, .github/workflows/release.yml, and install.sh. Works for both single-binary repos and multi-crate Cargo workspaces. Use this skill whenever the user wants to add CI/CD, a release pipeline, or a curl install script to a Rust project, asks for "github actions for rust", "release workflow rust", "cross-compile rust ci", "install.sh for rust tool", or wants to wire up a new or existing Rust CLI for distribution.

Dogfood GJC on next-code — implement issue → PR with CI watch

Discipline for replacing next-code UI with Grok Face (xai-grok-pager) via copy, delete old UI, and wire into next-code — never invent Face behavior. Use when migrating TUI/Face, PR8 cutover, wiring xai-grok-pager, removing next-code-tui, adapting ratatui 0.28 shims, quit/resume/auth wire bugs, or comparing grok-build vs next-code embed. Triggers on: grok migration, Face cutover, wire Face, copy grok UI, replace next-code TUI, grok-build research, SharedTermWriter, pager_launch, NextCodeFaceAgent.

Use when improving performance, latency, throughput, memory usage, or general efficiency. Start by defining target metrics, measuring comprehensively, attributing bottlenecks, validating with static analysis, and prioritizing macro-optimizations before micro-optimizations.

Deep feature research and implementation planning for AI coding agent projects. Use this skill whenever a user asks about a feature they want to implement, improve, add, or design — especially in the context of AI coding agents, CLI tools, terminal agents, or LLM-powered developer tools. Triggers on: "I want to add X feature", "how do I implement X", "can we improve X", "I want to build X into my agent", "feature request for X", "how does X work in these tools", or any phrasing that implies implementing/improving a capability. This skill clones 13 reference repos, spawns sub-agents for deep per-repo research, runs an ultra-QA interview with the user, then produces a comprehensive implementation plan with code, pseudocode, test cases, benchmarks, and direct repo links — so the user can go from idea to working implementation with total confidence.

Analyze the current repository, detect language/tooling, verify real test and coverage commands, and generate a proposed factory.manifest.json plus seeded .factory memory files. Use when initializing Factory in a repo or refreshing stale manifest data.

Run Factory's autonomous cycle loop: select a target, spawn constrained agents, verify changes, ship a PR, update memory, and continue until a stop condition is met. Use when a repository already has a factory.manifest.json and you want unattended improvement cycles.

Display the current Factory dashboard for the repository by reading the manifest, memory files, active stop signal, worktrees, and open Factory PRs. Use when checking progress, streaks, coverage movement, or current stop state.

Gracefully stop a running Factory session by writing the stop signal, checking active worktrees, and explaining how to resume. Use when you want the current loop to finish cleanly and then halt.

Phase 2 extraction skill for library porting. Use when user wants to extract the API surface from an original library, create conformance packet fixtures, or write oracle scripts. This is the most critical phase - it establishes the behavioral contract that the port must match.

Phase 4 implementation skill for library porting. Use when user wants to implement features for a library port, run conformance tests, or verify parity. This skill guides the implementation phase where features are built one-by-one with conformance verification after each.

Master skill for the 5-phase library porting workflow. Use when user wants to port a library from one language to another (pandas → Rust, NumPy → Rust, Redis → Rust, etc.) with full feature parity. This skill provides the overall workflow pattern while porting-extract and porting-implement provide phase-specific guidance.

Official skill for beads_rust (`br`), a local-first, dependency-aware issue tracker for AI agents. Use when creating issues, triaging backlogs, managing dependencies, finding ready work, updating status, or syncing to git via JSONL.

Migrate docs from bd (beads) to br (beads_rust). Use when updating AGENTS.md, converting bd commands, "bd sync" → "br sync --flush-only", or beads migration.

Install, initialize, and operate OpenProxy from the CLI — either guiding a human through setup or driving it fully autonomously as an agent. Use whenever the user asks to install the openproxy binary, start the local AI router on 127.0.0.1:4623, configure providers / combos / keys, or wire an AI coding CLI (Claude Code, Codex, Cursor, Cline, OpenClaw, Copilot, …) into OpenProxy.

Use when a Looper-managed GitHub repo needs scheduled pre-merge QA — a PR carries the `looper:qa` label, the spec stage reaches `looper:spec-ready`, or the Looper reviewer loop requests an independent second pass. Runs the full QA cycle (Looper state probe → PR checkout → ffs code review → language-specific test suite → optional computer_use UI smoke → GitHub review post with structured verdict and label update). Triggers on Hermes cron ticks, on demand from `looper-qa.sh`, or whenever a Looper loop asks for an independent review.

Convert a markdown plan into polished beads (br) for the Agentic Coding Flywheel. Use this skill whenever the user wants to: turn a plan into br tasks, create beads from a design document, polish or review existing beads, deduplicate a bead set, cross-reference beads against a plan, or validate bead quality before implementation. Trigger on phrases like "create beads", "convert plan to beads", "polish beads", "check beads", "bead polishing", "plan to tasks", "br create", or any mention of bead quality, bead dependencies, or bead graph. Also trigger when the user has a finished or near-finished plan and asks "what next?" — the next step is always beads.

Run NTM for multi-agent tmux orchestration, work triage, robot mode, safety, coordination, and local APIs. Use when spawning swarms, dispatching work, or operating `herdctl` as an agent or human operator.

Drive multi-OS install/smoke/feature checks with rth (Remote Test Helper) on Mac + Windows + Ubuntu WSL over SSH. Use when the user wants to run the same command across lab hosts, set up OpenSSH/keys for the lab, retest an install link on Windows/WSL, matrix-smoke a CLI after a fix, parse rth --json output, or avoid clipboard-hopping logs between machines. Triggers on: rth, remote test helper, multi-OS smoke, matrix test, run on Windows/WSL/Mac, lab doctor, hosts.conf, install-link retest.