AI-powered development platform — 24 agents, 19 MCP servers, 21 skills for end-to-end software development across React, React Native, Flutter, .NET, and NestJS.
★not rated 4 3mo agoA
tokens not measured
originalApache-2.0
hippocampus — perception and memory for coding agents: task registry, outcome ledger, and background clerks that turn transcripts into evidence. Records; never enforces. CLI and slash commands are hippo.
★not rated 4
changed yesterdayA
tokens not measured
originalMIT
Dolt/DoltHub version-control toolkit for Claude Code, via the dolthub/dolt-mcp server. A version-control-surface skill + expert agents over a Dolt backend — diagnosing DoltHub visibility, taming server sprawl, auditing the graph, and recovering incidents — with a verb-class mutation gate that keeps destructive ops…
★not rated 4 14d agoA
tokens not measured
originalApache-2.0
Deep Ass Research (DAR) — deep, multi-source, primary-sourced research into a backlinked Obsidian vault: fan-out scout/diver subagents, adversarial verification, and a synthesized Map-of-Content + report.
★not rated 4 1mo agoA
tokens not measured
originalMIT
A collection of skills for non-developers who want to turn an idea into a launched product. It covers engineering, product work, interface design, writing, and deployment.
Adaptive socratic mentor for Claude Code. One dial: the level decides how much of the work is yours. At 3 it writes skeletons and every function body is yours; at 5 it writes nothing and just asks. A PreToolUse gate enforces it, so levelling up means it does less for you, not more.
★not rated 4
changed 3d agoA
tokens not measured
originalMIT
Autopilot for spec-driven development. The human signs off and merges; planwright flies the spec. Scales to a multi-spec fleet: an agentic software factory on Claude Code primitives.
★not rated 4▲
+1
changed todayA
tokens not measured
originalMIT
Working prototype of Skill Heaven for Claude Code, actively tested for public use. One mechanic — /summon, one skill into context for one session, nothing installed — on one line: zero · low · med · high · xhigh · max · ultra, whose four surfaces are contiguous bands read from the current rung. /skill-zero is the…
Transforms text content into stunning self-contained HTML magazine pages with a real paper-magazine feel — paginated, image-rich, and print-inspired typography.
★not rated 4 5mo agoA
tokens not measured
originalMIT
Agent skills honed on real work — short, self-contained rule sets distilled from concrete engineering failures, so an agent (or human) can apply the lesson without the original context.
★not rated 4▲
+1
changed todayA
tokens not measured
CC-BY-4.0
Two complementary modern-C++ (C++17) native-addon skills for Claude Code. resource-review traces object and resource lifetimes and reports only proven memory/resource defects (use-after-free, double-free, leaks, out-of-bounds, integer overflow, data races, Node-API handle/reference/threadsafe-function misuse), using a.
★not rated 4▲
+1 5d agoA
tokens not measured
originalMIT
A team of agents for planning, researching, analyzing, writing, and reviewing social-science academic papers, with outputs in Word and Markdown formats.
★not rated 4▲
+1 1mo agoA
tokens not measured
originalMIT