lightning-gossip
BOLT 7 gossip: node_announcement, channel_announcement, channel_update. Sync via gossip_queries, channel range queries, gossip rate limiting, pruning stale…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-09 00:13
Agents & models
25,957 results
lightning-htlcs
HTLC (Hash Time-Locked Contract) lifecycle: offered/received, fulfill via preimage, fail/timeout, 2nd-stage txs. Modern variant PTLCs (Point Time-Locked…
lightning-watchtowers
Watchtower architecture: encrypted breach blob storage, justice transactions, monitoring outsourced for offline channels. LN-Symmetry (eltoo, BIP 448)…
markdown-structured
Structured markup ingestion for RAG. Covers markdown (markdown-it, tree-sitter), AsciiDoc, reStructuredText, frontmatter (YAML/TOML), header-hierarchy…
ontology-guided-retrieval
Ontology-aware RAG. Leveraging domain ontologies (SNOMED CT, FIBO, schema.org, Gene Ontology, custom OWL) to expand queries with synonyms, hyponyms, and…
self-querying-retriever
LangChain SelfQueryRetriever pattern. LLM infers structured metadata filters from natural language ("books by Asimov after 2000" -> filter author=Asimov…
gh-issues
Auto-fix GitHub issues by fetching open issues, spawning agents to implement fixes, and opening PRs. Monitors PR review comments. Use when user says "fix…
migrate-openclaw
One-click migration from OpenClaw to Claude-Agent. Reads ~/.openclaw/ and imports memory, skills, agents, conversations, and configuration. Preserves your…
session-logs
Search and analyze past Claude Code session logs using jq and ripgrep (rg). Find conversations by date, keyword, or topic. Extract decisions, code changes, and…
skill-creator
Create or update Claude skills optimized for Skillmark benchmarks. Use for new skills, skill scripts, references, benchmark optimization, extending Claude's…
dispatching-parallel-agents
Use when facing 2+ independent failures or tasks that can be worked on concurrently without shared state. Groups independent failures by component…
artlist-mcp
Use when a task needs AI image or video generation — campaign visuals, hero shots, product or social video, thumbnails, ad creative, localized variants —…
maintenance-manager
Senior Maintenance Manager (15+ years production systems). Evaluates dependency freshness, technical debt severity, upgrade paths, observability coverage, and…
sandcastle-runner
The primitive. Wraps a single Sandcastle invocation (`npx sandcastle run`) so Pi-CEO orchestrator can spawn AFK code-executing agents in isolated Docker /…
agent-orchestrator
Route complex requests to the right specialist agent or chain of agents. Central brain of the agent swarm — analyses what the user needs, determines which…
blueprint-engine
Hybrid DAG execution primitive combining deterministic and agentic nodes with hard iteration caps
ceo-board
Orchestrates 9-persona CEO Board deliberation for strategic business decisions, with persistent agent expertise files
claude-browser
Claude Chrome extension tools for personal browser automation in the user's actual browser. Use for logged-in sessions, form filling, and interactive tasks.
context-partitioning
Manifest-first context isolation — each subagent receives only its scope, never the full codebase
dispatching-parallel-agents
Use when facing 2+ independent failures or tasks that can be worked on concurrently without shared state. Groups independent failures by component…
skill-name
[REQUIRED — This is what Claude reads to decide whether to apply the skill] Apply this skill for ANY [exhaustive list of scenarios where this…
review-validation
Validate review findings from specialist agents by reading the actual repo file content and checking each finding for accuracy, applicability, and false…
pi-trending
Discover popular and emerging Pi Agent packages (extensions/skills/themes/prompt templates) on npm, calculate trend scores, and display a summary.
fabric-best-practices
fabric_exec behavior correction layer: load when fabric_exec runs successfully but behaves incorrectly—results never return to the model, standalone calls don't collapse into parallelism, mechanisms are used at the wrong timescale. Only covers judgment and pitfall avoidance; signature / parameter shape errors see fabric-exec, workflow selection see fabric-guide.