Intelligent prompt optimization: injects the right context at the right moment so Claude lands a better first output. Clarifies vague prompts with research-based questions, plus targeted nudges for approach selection, plan readability, workflow routing, background execution, subagent routing, output readability…
Troubleshooter + machine-readable corpus for reinforcement-learning training, evaluation, and experiment design on LLM agents (single/multi-agent, multi-turn, tool-augmented). Distilled from the AgentsMeetRL awesome list (378 projects).
★not rated 1.9k▲
+3
changed 7d agoA
tokens not measured
Collection of commands that force LLM to reflect on previous response and output. Based on papers like Self-Refine and Reflexion. These techniques improve the output of large language models by introducing feedback and refinement loops.
★not rated 1.8k▲
+27 1mo agoA
tokens not measured
GPL-3.0
Humanize - An iterative development plugin that uses Codex to review Claude's work. Creates a feedback loop where Claude implements plans and Codex independently reviews progress, ensuring quality through continuous refinement.
Claude Code operations suite that bundles cross-project prior-work retrieval across code, docs, Skills, meetings, WeChat archives, and conversation history; provider-separated Claude Code and Codex history readers; identity- and lineage-gated continuation workflows; plugin/skill troubleshooting; CLAUDE.md progressive…
★not rated 1.5k▲
+21
changed todayA
tokens not measured
originalMIT
Drive CLI Agent Orchestrator multi-agent sessions from any Agent-Plugins-compatible client. Prerequisites: the uv toolchain must be on PATH (the MCP server is launched via uvx), and a CAO API server must be running locally at http://127.0.0.1:9889 (cao-server). All communication is localhost-only.
Universal Claude Code workflow with specialized agents, skills, hooks, and mode commands for any software project. Includes orchestrator, code-reviewer, debugger, docs-writer, security-auditor, refactorer, and test-architect agents.
The anti-PUA. Drives AI with wisdom, trust, and inner motivation instead of fear and threats. Based on Dao De Jing philosophy. 7 languages, 7 platforms.
★not rated 1.4k▲
+2 19d agoA
tokens not measured
originalMIT
Translate raw health data into LOINC/UCUM/ICPC-3 coded rows and read lab reports against an offline resolver; self-host Mirobody and connect an agent over MCP.
★not rated 1.4k▲
+9 3d agoA
tokens not measured
originalApache-2.0
Plain-language skills for coding agents, for the person running development who does not read code: session reports, decisions, next steps and the whole picture.
Build loop engineers: a file-based knowledge base your agents read/write (loops), plus a codebase harness (dev-local stack, e2e gate, an isolated cloud box per agent via crabbox, and verify-before-ship) so loops can run, test, and ship code autonomously. Plus an SEO growth playbook distilled from two production…
★not rated 1.3k▲
+5 1mo agoA
tokens not measured
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: