NeVibeCode · 5,192 items
Skills for Agent setup: memory, context, orchestration
Skills for Agent setup: memory, context, orchestration: what each one does, an install command and example prompts.
autopilot-loop skill A skill that runs one iteration of an autonomous loop: checks progress, picks the next task, schedules the next wake. Use it when you want Claude to keep working without manual breaks between tasks.
CX Codex +1
752installs
research-synthesize skill Turns findings stored in ruflo memory into one report, with evidence grades, contradiction handling and next steps. Useful after a run of deep-research.
CX Codex +1
751installs
vector-search skill Runs vector search over corpora via HNSW embeddings and routes queries across up to 11 hot patterns in WASM.
CX Codex +1
751installs
memory-search skill Searches Ruflo memory using semantic retrieval or hybrid keyword matching. It pulls task context and past solutions directly into the agent.
CX Codex +1
750installs
security-scan skill Scans a repo at three depths: dependency audit, hard-coded secrets, risky code patterns. Useful before a release or while reviewing a PR.
CX Codex +1
748installs
dependency-check skill Scans project dependencies for known vulnerabilities and CVEs. Run before releases, after lockfile changes, or when investigating security advisories.
CX Codex +1
748installs
neural-train skill Trains SONA and MicroLoRA neural patterns from successful task executions, running the distill and consolidate phases in Ruflo.
CX Codex +1
748installs
swarm-init skill Initializes a coordinated agent swarm for complex changes across multiple files. Use it when agents need parallel tasks, named roles and direct messaging.
CX Codex +1
747installs
horizon-track skill Tracks long-term objectives across multiple sessions, stores milestones in persistent memory, and flags project drift.
CX Codex +1
746installs
mantis-critic
official skill Checks whether validated findings remain triggerable in release builds with assertions disabled. Use it after a finding has already been verified.
CX Codex +1
1,600installs
mantis-plan
official skill Generates a targeted security review plan based on your threat model and historical findings. Run at the start of a review campaign to map code boundaries and prioritize what to check.
CX Codex +1
1,600installs
mantis-summarize
official skill Builds a security-focused codebase map with mantis-summary.md files in each directory. Reduces token overhead during planning and research.
CX Codex +1
1,600installs
mantis-architecture
official skill Turns codebase analysis and collected learnings into an interlinked Markdown knowledge base. Use it at the start of an architecture and vulnerability review loop.
CX Codex +1
1,600installs
mantis-review
official skill Reviews findings against the actual source code and drops false positives. Useful once a scan has produced a list of bugs that needs cleaning up.
CX Codex +1
1,600installs
monitor-stream skill Streams ruflo swarm status changes into your session through the Monitor tool, so you see agent counts shift instead of polling the CLI by hand.
CX Codex +1
745installs
trader-backtest skill Runs historical backtests using neural-trader and Ed25519-signs output artifacts to secure paper-to-live promotion gates.
CX Codex +1
745installs
cost-optimize skill Reads token spend for the last 7 days, flags model tiers that don't match the work and weak caching, then ranks fixes by dollar savings.
CX Codex +1
745installs
agentdb-query skill A skill to store and query agent knowledge through AgentDB. Works with hierarchical memory tiers, causal graphs, and semantic routing — use it when your agent needs to retain context across sessions.
CX Codex +1
745installs
memory-bridge skill Bridges Claude Code's auto-memory files into AgentDB with semantic search across all projects. Deduplicates entries and enables unified cross-project memory queries.
CX Codex +1
744installs
trader-signal skill Detects market anomalies with neural-trader Z-score scoring and generates ranked trading signals with entry, stop, and target levels.
CX Codex +1
744installs
loop-worker skill Runs Ruflo background workers on a /loop schedule and checks them through MCP. Use it for recurring code checks and worker tasks.
CX Codex +1
744installs
daa-agent skill Builds Dynamic Agentic Architecture agents that shift behavior from performance metrics, pick up experience as they run and pass it to other agents.
CX Codex +1
744installs
workflow-run skill Runs workflows and manages their lifecycle via MCP tools or native JavaScript orchestrations. Useful for controlling multi-step pipelines and subagent fan-outs.
CX Codex +1
743installs
tdd-workflow skill A skill that walks the agent through London School TDD: a failing test against mocks, the smallest passing implementation, then refactor. Steps are logged through MCP hooks.
CX Codex +1
743installs
git-workflow skill A skill that walks branches, conflicts and the pull request lifecycle, with a diff-risk score before every merge.
CX Codex +1
743installs
doc-gen skill Generates project documentation, detects drift between docs and code, and schedules recurring updates. Helpful when code changes outpace reference files.
CX Codex +1
743installs
autopilot-predict skill Chooses the next task from the current work state and learned patterns. Use it when an agent needs direction during repeated task iterations.
CX Codex +1
743installs
safety-scan skill Scans inputs for prompt injection, jailbreak attempts, and unsafe content before processing. Use it when handling untrusted data from users, APIs, or webhooks.
CX Codex +1
743installs
chat-format skill Formats chat messages into local model templates like llama3 or chatml for Ollama and llama.cpp, and routes queries across intents using a compact WASM HNSW index.
CX Codex +1
742installs
create-plugin skill Skill that generates a complete plugin scaffold with directories, plugin.json, skills, commands, and agents. Saves time on boilerplate and ensures compliance with ruflo standards.
CX Codex +1
742installs
llm-config skill Configures RuVLLM local inference and manages in-memory MicroLoRA and SONA adapters using quality feedback scores.
CX Codex +1
741installs
validate-plugin skill Checks a Claude Code plugin’s structure, frontmatter, and MCP tool references before publishing or after changes.
CX Codex +1
741installs
trader-portfolio skill A skill that walks through portfolio allocation with the neural-trader engine: weights, a risk figure and a rebalancing draft. Useful when you want to map holdings onto a target return.
CX Codex +1
741installs
intelligence-route skill Selects the right agent and model tier across three tiers using learned patterns. Cuts token costs on routine coding tasks.
CX Codex +1
741installs
wasm-gallery skill Skill for browsing, installing, and publishing WASM agents from a community gallery. Useful when you need a ready-made agent or want to share yours.
CX Codex +1
741installs
adr-create skill Writes an Architecture Decision Record into docs/adr with the next number, stores it in AgentDB and links it to related decisions. Useful when a decision has to be recorded and findable later.
CX Codex +1
741installs
huggingface-best skill This skill pulls top models for a task from HuggingFace leaderboards and drops the ones your hardware cannot hold.
CX Codex +1
1,800installs
rvf-manage skill Exports agent memory to an RVF file and imports it again, so context can move between projects or into a backup.
CX Codex +1
740installs
skill-creator skill Skill to create, review and package custom skills with Python scaffolding, frontmatter validation and ZIP helpers. Use it to extend your IDE or automate repetitive tasks.
CX Codex +1
977installs
gmgn-swap skill This skill submits token trades through the GMGN API, including swaps, orders, sales, and multi-wallet operations.
CX Codex +1
17,000installs
881–920 of 5,192
