Ten skills that test your agent harness on your own machine: sandbox reach, guardrails, 'tests pass' claims, rules the agent breaks, token waste, regressions after updates, MCP tool design, and a test drive of coding agents on tasks from your own git history.
★not rated 1.5k▲
+39 3d agoA
tokens not measured
CC-BY-SA-4.0
Persistent trade memory for AI trading agents: record trades, recall the losing ones from similar conditions before the next order, and review behaviour over time.
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.
Standardize 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.
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▲
+1 1mo agoA
tokens not measured
originalMIT
Manage TaskView projects and tasks from Claude Code — browse projects, view and create tasks, and log your work without leaving the terminal. Bundles the TaskView MCP server.
Build, migrate and review documentation sites with Sourcey: Markdown guides, OpenAPI and MCP references, Doxygen, Go and Rust, from a project's own sources.
Agent skill stack for manuscripts targeted at the American Economic Journal: Economic Policy (AEJ: Policy) — the American Economic Association's quarterly journal for economic analysis OF policy, spanning public economics and taxation, environmental and energy, health, education, labor and social insurance, regulation.
Mine your SpecStory coding histories (Claude Code, Codex, Cursor, Gemini, and more) into a persistent corpus, surface your reproducible workflows with corroborated evidence and outcome labels, and forge the ones you choose into skills installed across every agent harness.
★not rated 1.4k▲
+3 yesterdayA
tokens not measured
originalApache-2.0
Windows app development, packaging, and distribution. Helps with creating Windows installers (MSIX), code signing, certificates, Windows SDK and Windows App SDK setup, package identity for Windows APIs (push notifications, background tasks, share target), appxmanifest authoring, and Microsoft Store distribution.…
Repository knowledge engine plugin. Bundles CLI-backed slash commands (rb-setup / rb-init / rb-refresh / rb-ask) plus the agent-repo-init skill. Works in both Claude Code and Codex CLI.
C coding style rules and clang-format enforcement for AI coding agents, based on Tilen Majerle's C style guide.
★not rated 1.4k 13d agoA
tokens not measured
originalMIT
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: