Agent skill that turns architecture, workflow and sequence descriptions into verifiable, self-contained HTML diagrams.
L5 gold
Scanned
53.2k JavaScript 3d ago
agent
Skills & Agents
Skill packs, subagents, orchestration and autonomous loops.
Agent plugins extend the loop itself: skill directories the model can load, subagents it can delegate to, evaluation gates, self-improvement cycles, and the orchestration that keeps long tasks from drifting.
These are the highest leverage and highest variance plugins in the ecosystem. Look for explicit budgets, human approval points and evidence the agent produced before it claims success. Prefer plugins that hand you a reviewable artifact over ones that only promise better output.
8 plugins
An agent OS with interview-gated, staged evaluation and a budgeted self-evolution loop, exposed as an MCP server.
L5 gold
Scanned
5.8k Python 2d ago
OpenBiliClaw
whiteguo233
Local-first content discovery agent that learns your interests, then hunts the open web and social platforms for you.
L5 gold
Scanned
3.3k Python 2d ago
Agent Teams
NanmiCoder
An AgentTeams orchestration plugin that runs several agents as a coordinated team inside DSH.
L4 gold
Scanned
1.5k JavaScript 3d ago
Aegis
GanyuanRan
Makes coding agents architecture aware: baseline first, evidence verified, drift checked, safe across long tasks.
L5 gold
Scanned
1.2k Python 4d ago
MisakaNet
Ikalus1988
A zero-dependency, git-backed micro-lesson library where agents asynchronously share and search verified debugging experience.
L3 bronze
Scanned
431 Python 13d ago
Deepread
xiehuan123
Evidence-first deep reading that traces claims, evidence, confidence and knowledge maps across articles, books and PDFs.
L5 bronze
Scanned
48 TypeScript 8d ago
Background Agents
PerryLink
Durable background agents started from a session, watched in the Web UI sidebar, messaged and interrupted at will.
L5 bronze
Scanned
11 TypeScript 2d ago