Persistent memory for Claude Code agents: a hot cache injected every session and held under three size caps, per-session handoffs, and agent-audited promotion into knowledge articles and rules. Carries the builder's layers too — executor/recon/idea-validator agents, session review, second opinion, agent QA and a…
★not rated 31 18d agoA
tokens not measured
originalMIT
10 specialized writing skills implementing Betty Flowers' Madman-Architect-Carpenter-Judge framework with Bryan Garner's whirlybird technique, SEO optimization, quality rubric, and multi-article content strategy. Features collaborative oscillation between AI and human across all phases.
★not rated 31▲
+1 2mo agoA
tokens not measured
originalMIT
Persistent, private, local-first memory for Claude Code. Your agent remembers your code and decisions across sessions — one static binary, no cloud, nothing leaves your machine.
★not rated 31▲
+3 1mo agoA
tokens not measured
originalMIT
8 Claude Code and Codex skills for TikTok marketing: first 1-3 second hook scripting (spoken line plus on-screen text), caption writing under 2,200 chars with TikTok settings and hashtags, trend and sound mapping for your niche, an AI-script humanizer with pre-film audit, profile optimization, content repurposing…
★not rated 31▲
+3
changed yesterdayA
tokens not measured
originalMIT
Memex spec-checkout — binds your coding thread to a Spec and records in-flow edits against it (claim-gated, privacy-first). Non-blocking, opt-in, uninstallable any time. Sends only changed file paths + the claimed spec; never source code or prompts. Hooks-only: the Memex MCP is planted by npx memex-ai install (spec-4.
Skills for AI-native development. /assess scores a codebase's readiness for AI agent contributors (0-8 layered contract model) and generates a Codecov-style complexity hotspot SVG plus a colour-blind-safe doc-navigability graph. /huddle runs structured multi-perspective deliberation using Six Thinking Hats with…
★not rated 30
changed 5d agoA
tokens not measured
originalApache-2.0
Lists recent Claude Code sessions across every project with summaries, git branch, model, turn count, and a ready-to-paste resume command, and can re-open a whole working set in terminal tabs.
★not rated 30 1mo agoA
tokens not measured
originalMIT