Build and maintain Claude Skills representing your favourite experts' worldviews. Scrapes LinkedIn (Apify), RSS, podcast snips, and other sources you configure; judges each excerpt for signal vs noise; distills into compact Claude Skills with frameworks, principles, and voice samples. Invoke via…
★not rated 5 2mo agoA
tokens not measured
originalMIT
Two skills that bracket the moment an AI product's architecture gets decided: small-council-blueprint forces a written architecture before any code is touched, small-council-audit tears it apart before you build on it.
Production-ready Claude skills for LinkedIn growth by Taplio: post writing, hook generation, carousels, repurposing, story extraction, CTA optimization, niche and audience definition, content pillars and calendar planning, profile optimization, and analytics interpretation. Integrates with the Taplio MCP when…
★not rated 5 1mo agoA
tokens not measured
originalMIT
Build a living profile of your partner from chat history — personality analysis, interest mapping, occasion tracking, gift ideas, dating plans, and relationship insights.
One loop for clear knowledge work: check whether evidence is strong enough for the next action, shape the deliverable one useful question at a time, draft from an approved spec, review the result, and remember what you like. Missing decisions, evidence limits, readiness, and required human approval stay visible.
★not rated 5 1mo agoA
tokens not measured
originalMIT
Focused SEO skills: keyword research, on-page and technical audits, AI-search optimization, traffic diagnosis, site-health triage, competitor and content audits, and programmatic SEO, with content companions.
★not rated 5 1mo agoA
tokens not measured
originalMIT
Adversarial, attacker-minded security review of untrusted code before you install it. A read-only scanner plus a five-persona reasoning pass, ending in a GO / GO-WITH-MITIGATIONS / NO-GO verdict.
★not rated 5 1mo agoA
tokens not measured
originalMIT
Language-agnostic autonomous codebase improvement loop using isolated git worktrees. Every experiment runs on its own branch — main is never touched until a winning change is merged. Works with any language or framework.
★not rated 5 6mo agoA
tokens not measured
originalMIT
Two composable Claude Code skills for writing peer-review rebuttals: write-rebuttal (overall process — Parikh–Batra–Lee method, 18 tactics, AC-facing structure) and nlp-rebuttal (per-concern playbook — 28 reviewer-concern scenarios with answer templates).
★not rated 5 1mo agoA
tokens not measured
originalMIT
Automatically compress large natural text or log files before processing using LLMLingua to save tokens. Trigger when the user pastes massive text blobs, asks to analyze a large file (logs, docs, transcripts), or provides a prompt too large for the context window.
★not rated 5 4mo agoC
tokens not measured
originalMIT
Four stateless PreToolUse gates, a PostToolUse JSON-config guard, and a docs-consolidation trigger. Denies a git commit that changes code without staging its covering docs (per-plugin README/CLAUDE.md pairs, or the nearest README/CLAUDE/AGENTS walking up); asks before a new-project scaffold command (npm create vite…
★not rated 5
changed 5d agoA
tokens not measured
originalMIT
Marketing copy where every claim is traced to a fetched source, labeled, and adversarially verified before it ships — landing pages, launch emails, metadata, and copy audits.
★not rated 5 27d agoA
tokens not measured
originalMIT
Economic Mind plugin. Ships data skills that turn Economic Mind connector data into rigorous, fully-sourced financial and market analysis. Company-at-a-glance financial snapshots, competitor benchmarking, and bottom-up market sizing stress-tested against independent cross-checks. Every figure traces back to its source.
End-to-end pipeline: pull a task from the project's task tracker (Redmine today) by ID, implement it with the Claude CLI, verify the result in a real browser via the claude-in-chrome extension, and keep the tracker ticket in sync throughout.
★not rated 5
changed todayA
tokens not measured
originalMIT
Headless Ghost CMS blog for Next.js App Router — Content API client, ISR + webhook revalidation, tag/author/paged archives with author bio + social rendering, SEO metadata + JSON-LD, sitemap, Ghost koenig-card styling, blur-up images. Battle-tested patterns with copy-paste templates.
★not rated 5 1mo agoA
tokens not measured
originalMIT
Bilingual skills for writing IEEE communications-journal papers (JSAC, TWC, TC/TCOM, WCL, CL): literature search with DOI/BibTeX verification, drafting with target-journal routing, learning-based and emerging-paradigm system models, reproducible methods, language polishing, IEEE citation/IEEEtran formatting…
★not rated 5 2mo 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: