Research and LLM engineering: deep research with scenario checklists, search routing across MCPs, LLM cost discipline (regex-first parsing + model routing)
Plugin research from marketplace yifan-personal in Davie521/claude-skills. Commands read from the repo's manifest — 12 days ago.
llm-cost-disciplineCost discipline for LLM pipelines — parse structured text with regex first and escalate only flagged items to an LLM, route the cheapest sufficient model tier by task size, track budget, retry narrowly, cache prompts. Use when building LLM pipelines, controlling API costs, or choosing between regex
researchMulti-source deep research. Prefers the exa MCP for search (firecrawl for scraping), falls back to the bundled /deep-research workflow or built-in WebSearch when they are absent. Searches the web, synthesizes findings, and delivers cited reports with source attribution. Use when the user wants thoro
search-routingSingle decision skill for all web search needs. exa is the default search backend (including `site:` and Chinese queries); firecrawl is for scraping pages exa cannot fetch, and firecrawl_search is only a fallback. Asks user before invoking expensive deep modes. Use this BEFORE any web search call wh
Dev workflow: Git PR pipeline with a Codex review gate (fix and re-review until it passes) + auto-merge, no-CI detection (cpr), deep-plan (restate/risk/phase + mandatory worktree), diagnosis loop, plan grilling (grill-with-docs: lite mode + ADR format), codebase deepening, throwaway prototype, conversation-to-PRD, issue triage state machine, caveman compressed-comms, cleanup (end-of-session teardown + memory persistence)
10 skills
Code quality: TDD discipline, E2E testing patterns, AI regression testing, click-path audit, santa-method adversarial verification, security review checklist, .claude config scan, Plankton write-time enforcement
8 skills
Multi-language code review: /code-review dispatches to language-specific reviewer (Python, TypeScript, Swift) plus mandatory security-reviewer. General code-reviewer fallback.
1 command · 5 agents
Web stack: REST API design, Docker, deployment, MCP servers, Bun runtime, content-hash caching
6 skills
Document tools: A4 cheatsheets, doc co-authoring, PDF, visa translation, codebase-to-course interactive tutorials
5 skills
Invoke Codex (read-only codex exec via ~/.local/bin/codex-run) for code review and design challenge.
2 skills · 2 commands
Talk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.
1 skill
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
Package any website or local web build into a lightweight desktop app with Pake CLI.
1 skill
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.