Loading...
Loading...
Found 62 Skills
Imports a Claude Design (claude.ai/design) handoff bundle and scaffolds the proposed components into the project. Accepts a bundle URL or local file, parses and validates the schema, deduplicates components against the existing codebase via component-search, then pipes the survivors through the design-to-code pipeline. Writes provenance metadata so future imports can detect drift between design versions. Use after exporting a handoff bundle from claude.ai/design — this is the entry point that turns a design into code.
Bridge Claude Code auto-memory into AgentDB with ONNX embeddings, deduplicate, and enable unified cross-project search
Multi-stage fuzzy matching pipeline for entity reconciliation. PostgreSQL trigram pre-filter, salient overlap check, and multi-factor similarity scoring.
Use when auditing, trimming, or restructuring AI skill files to reduce context-window consumption. Trigger whenever a SKILL.md exceeds 120 lines, skills share duplicated content, AGENTS.md has large inline blocks, or the user asks to optimize, slim down, or reduce token usage of their skills.
Run Codex, Claude Code, and Gemini CLI reviews against the current branch concurrently, deduplicate the findings, and report only the review comments that are still valid for the current codebase.
Structured code review using tiered persona agents, confidence-gated findings, and a merge/dedup pipeline. Use when reviewing code changes before creating a PR.
Investigate a cluster of GitHub issues and PRs, determine canonical candidates, post duplicate/related status, preserve contributor credit, and execute cleanup actions (comments, closes, labels, changelog touchpoints).
Design webhook/event pipelines for Solana activity with idempotency, dedupe, retries, and ordering. Use when consuming RPC/webhook feeds.
Aggregate and deduplicate recent news from multiple sources into concise topic summaries.
Scan the Obsidian wiki for page-level identity collisions — different pages covering the same concept under different names (e.g. "RSC" vs "React Server Components") — and merge them. Use this skill when the user says "dedup my wiki", "find duplicate pages", "merge duplicates", "identity resolution", "consolidate my wiki", "I have duplicate pages", or "my wiki has two pages for the same thing". Distinct from wiki-lint (which checks structure) and cross-linker (which adds links) — this skill makes destructive page-level merges and requires careful confirmation.
Use Neo4j memory MCP for creating/updating linked memories (entities, relations), de-duplication (DRY), and retrieval queries for project continuity. Use when saving global learnings or querying graph relationships.
Smart CSV importer with format auto-detection. Handles major banks in Canada and US, plus payment platforms (Stripe, PayPal, Wise, WeChat Pay, Alipay) and browser-assisted exports gathered through `/cfo-statement-export`. Use when importing bank or credit card CSV exports. CLEAR step: C (Capture)