81,896 mods in this category, of every kind an
agent can take. Each one carries what it costs per session, what the
scan found, and whether it is the original.
10 Claude Code skills: D2 diagrams, Typst documents with a parallel review, mind maps, web image search, Wayback page recovery, SEC EDGAR filings, and a verify-before-done check.
★not rated 2
changed 7d agoA
tokens not measured
originalMIT
Test a new official Claude Code version against AI Manager's agreed privacy and workflow requirements, using offsite sandboxes, exact artifacts, retained evidence and a cold code review. Use when explicitly asked to audit or sandbox-test a Claude upgrade before approving it for use. Claude only for now; Codex testing…
A project-local verification guide that teaches an agent how to start and operate a real application like a user. It can cover web and desktop interfaces, command-line programs, services, libraries, or mobile applications, while recording evidence of the results.
The automatic half of Sutra: a layered operating contract at session start, short rule cards when they apply, hidden-Unicode warnings, a compaction brief, a verify-before-stop nudge under the strict profile, and the build-orchestrator workflow. Runs one Bash hook script, and installs the sutra skills plugin as a…
★not rated 2
changed todayA
tokens not measured
originalMIT
Parallel-batch spec-driven feature workflow (spec-setup, spec-investigate, spec-create, spec-implement, spec-verify, spec-review, spec-checkpoint, spec-ship) plus a portable SEO/GEO operations skill (generative-seo) for any codebase, and a pre-registered experiment skill (spec-experiment).
★not rated 2
changed todayA
tokens not measured
originalMIT
Art-directs a screen, dashboard, or site in image and video models before any code exists, then builds it and verifies the build against the approved mockup: layout lock, out-of-UI references distilled into a visual DNA, concept mockups, blind-critic iteration, motion found with image-to-video, a build spec, and a…
BETA. Convert a static HTML site — or anything that builds to one (Lovable, Bolt, v0, Next export) — into a standalone WordPress block theme: verified pixel by pixel, pages, blog, forms, menus, SEO and redirects, with no plugin required and verification gates at every stage. Two modes: Full (every gate repaired until…
Manage and analyze Google Ads, Meta Ads, Instagram, TikTok Ads, LinkedIn Ads and Microsoft Ads from Claude Code through Windsor.ai. Report on campaigns, keywords, search terms, quality score, impression share and cost per conversion, track Instagram post reach, saves and follower growth, and combine it all with GA4…
★not rated 1
changed 1mo agoA
tokens not measured
originalMIT
Multi-model collaborative problem-solving workflow with hardened backtest gates. Two rounds of brainstorm with a no-duplicate-thoughts rule between rounds, replay-not-stats backtests, walk-forward validation, sensitivity rejection, and per-quest verdict synthesis. Use when a hard problem stalls single-pass thinking…
SEO + GEO skills for Claude Code that work like a specification: every page skill audits the page, benchmarks it against the competitors that rank, and builds the fix. Audit any site, diagnose a traffic drop, fix technical SEO, write content that ranks on Google and gets cited by ChatGPT, Perplexity and AI Overviews…
★not rated 1
changed 2d agoA
tokens not measured
originalMIT
Polisade Orchestrator — autonomous development framework by Polisade. Claude operates as a full dev team: implement → test → PR → review → merge. (Technical id: polisade).
★not rated 1
changed 5d agoA
tokens not measured
originalApache-2.0
Archive and export historical X/Twitter account timelines from a public handle using a bundled bird-search backend, browser/session cookies, and optional local proxy. Use when the user asks to collect, export, archive, or analyze tweets/posts from a specific X/Twitter account over a date range, especially when they…
Extract exact design specs from Apple's official Figma UI kits into SwiftUI, build signed macOS apps from a single Swift file without an Xcode project, implement password-free root operations safely, and preflight harness gates that block tool calls. Includes a tested Swift package implementing each skill.
Local memory banks you keep — a localhost Hub UI + MCP connector for Claude. You curate titled, dated memory banks on your machine; Claude recalls them via MCP. Runs locally from the localkeep Python package. Needs 2 environment variables to run.
★not rated 1 3mo agoA
tokens not measured
originalMIT
Bootstrap a new Python project from a proven scaffold. Use whenever the user asks to start, create, scaffold, or set up a new Python tool, library, CLI, package, service, or experiment repo — or says 'set up a project the usual way'. Do NOT hand-roll a project structure from memory when this skill is available: run…
Audit registered upstream docs sources for drift since a prior commit SHA or date — detect new GA / preview features, syntax additions, deprecations, and harness or tooling changes that affect existing skills, rules, CLAUDE.md, settings.json, hooks, or the MCP templates. Sources live in a registry…
Detect, critique, and rewrite text to remove AI writing patterns — makes content sound human, specific, and credible. Use this skill whenever: writing any client-facing or published content from scratch; editing/polishing any draft that might sound "corporate AI"; asked to "make this sound more human", "remove AI…
A routing guide and builder for Prismstack, a collection of interactive skills for work in a specific field. It helps choose the right skill and load its instructions.
All the context, in one place for Claude Code, Codex, Gemini, and AI coding tools.
★not rated 1
changed 6d 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: