AI & ML

huskydanny Skill

Verify specific claims in the thesis against independent sources

huskydanny Skill

Identify risk factors not adequately addressed in the thesis

huskydanny Skill

Aggregate and analyze news sentiment for a stock symbol

huskydanny Skill

Search for evidence that contradicts the investment thesis using independent sources

huskydanny Skill

Assess cash flow generation, debt levels, and financial stability

nimblebraininc Bundle

Build MCP servers end-to-end — scaffold a production-ready Python or TypeScript server from API docs, implement tools, validate the MCPB bundle, embed a skill resource, and release to the mpak registry. Covers the full lifecycle from API analysis to published bundle. Use when building a new MCP server, wrapping an API as MCP, or creating an integration. Triggers include "build an MCP server", "create a server for X", "/mcpb".

nimblebraininc Bundle

Best practices for MCP servers — how to name, describe and schema a tool so a model actually calls it, how resources and prompts differ, and what the boundary must never trust. Applies while authoring a new surface or as an audit of an existing one, grounded in the MCP specification and the tool-authoring guidance from Anthropic and OpenAI. Triggers include "MCP best practices", "name this tool", "audit this MCP server", "why won't the model call my tool", "/mcp-best-practices".

verygoodplugins Skill

Persistent AutoMem memory via the native AutoMem OpenClaw plugin tools.

gmh5225 Skill

Guide for LLM security attacks: prompt injection, jailbreaking, data extraction, and where to place resources in README.md.

cxxxr Skill

Playwright MCPを使用したブラウザ自動化。ページ操作、スクリーンショット、フォーム入力のパターン集

mbruhler Bundle

Use when user says "create workflow", "create a workflow", "design workflow", "orchestrate", "automate multiple steps", "coordinate agents", "multi-agent workflow". Creates orchestration workflows from natural language using Socratic questioning to plan multi-agent workflows with visualization.

cyrup-ai Skill

Memory system with three MCP tools: mcp__plugin_kg_kodegen__memory_list_libraries (discover namespaces), mcp__plugin_kg_kodegen__memory_memorize (store with embeddings), mcp__plugin_kg_kodegen__memory_recall (semantic search). Use for storing/retrieving knowledge by meaning. WHEN: User says "remember this", "recall", "what did I save", "my notes", "find my knowledge about". WHEN NOT: File operations (use fs_*), exact keyword search (use fs_search).

huskydanny Skill

Identify the primary trend direction and strength using price action

huskydanny Skill

Challenge the underlying assumptions in the investment thesis

huskydanny Skill

Evaluate earnings trends, beat rate, and quality signals

huskydanny Skill

Analyze Stochastic oscillator for momentum signals and divergences

huskydanny Skill

Calculate Fibonacci retracement levels and identify golden zone support/resistance

huskydanny Skill

Analyze valuation metrics (P/E, PEG, P/S) to assess fair value

leefowlercu Bundle

Turn a rough draft, vague ambition, or messy task brief into a powerful Codex /goal objective for long-running autonomous work. Use when the user asks to write, improve, format, sharpen, stress-test, or activate a Codex goal, thread goal, durable goal, or /goal prompt.

doyajin174 Skill

Generate investigation-to-fix prompts for expected-vs-actual mismatches: runtime errors, build failures, performance regressions. Creates external AI prompts AND runs internal investigation in parallel. Use when behavior differs from expectation — not for design flaws (use /research) or quality review (use /validation). MUST trigger on: "버그", "에러", "안돼", "깨졌어", "크래시", "crash", "bug", "error", "왜 안돼", "fix", "고장", "느려", "slow", "performance issue", "expected X but got Y", "작동 안 함", "실패", "fail", or any request where something was working and now isn't, or where output differs from expected result. NOT for: design flaws or architectural concerns (→ /research), quality review (→ /validation), tech exploration (→ /question). State routing: expected-vs-actual MISMATCH exists (something broken/slow/wrong). If design flaw → /research. If quality review → /validation. If exploring → /question.

doyajin174 Skill

Generate structured research prompts for external AI tools (ChatGPT, Gemini, Perplexity, etc.). Auto-reads project context, classifies research type, applies type-specific template, and outputs a self-contained prompt with evidence pack. MUST trigger on: "리서치 프롬프트", "research prompt", "외부 AI", "기술 조사", "비교 분석", "타당성 조사", "feasibility", "technology comparison", "조사해줘", "리서치", or any request to generate a prompt for pasting into an external AI. NOT for bug investigation or fix prompts (use problem-prompt-generator). State routing: user has 1-2 candidate approaches needing deep-dive. If no approach yet → /question. If artifact exists → /validation. If bug/error → /problem.

rezkam Bundle

Drive the OpenAI Codex CLI non-interactively as a second agent. Use for Codex review sessions, persistent MCP conversations, exec worker delegation, liveness checks, status polling, reports, follow-up turns, stopping runs, and deleting run records. Trigger whenever the user mentions codex, codex review, adversarial or second-opinion review, talking to codex, continuous back-and-forth with codex, launching codex in MCP mode, delegating or scheduling implementation work to codex, checking whether a codex run is alive or progressing, managing codex sessions, cleaning up codex runs, or orchestrating codex as a non-interactive worker or reviewer from automation or workflows.

gmh5225 Skill

Guide for adversarial machine learning: adversarial examples, data poisoning, model backdoors, and evasion attacks.

rooseveltadvisors Bundle

Hybrid search (embedding + BM25) for retrieving relevant clinical note passages. Use for finding source evidence to support claims in summaries and recommendations.

rooseveltadvisors Bundle

Pydantic schema validation for agent outputs. Use to validate JSON against TableOfContents, ClinicalSummary, TreatmentPlan, and EvaluatorFeedback schemas before accepting agent responses.

rooseveltadvisors Bundle

JSON-based structured logging for audit trails and debugging. Use for logging all agent operations, quality metrics, errors, and execution times with daily rotation and automatic cleanup.

sjungling Bundle

This skill should be used when the user asks to "analyze data with SQLite", "query logs", "find patterns in test results", or "correlate errors across files". Automatically activates when parsing large output (>100 lines), correlating data from multiple sources, tracking state across operations, aggregating results (counts, averages, grouping), or querying the same dataset multiple times. Not for tiny datasets (<50 records) with a single simple query.

rezkam Bundle

Use browser-authenticated AI chat providers through reusable provider adapters and Browser Tools. Use this skill for ChatGPT provider-ID continuation, read-only reattach/watch, conversation listing, model profiles, and final or NDJSON output, as well as Grok, Gemini, and Perplexity browser-session work.

urrhb Skill

Convert a SPEC.md into a structured Kanban board with atomic tasks, dependencies, and acceptance criteria. Detects which PM tool MCP is available and adapts automatically.

supernovae-st Skill

Author, check and repair Nika workflows (.nika.yaml files — the workflow language for AI). Use when writing or editing a *.nika.yaml file, converting a repeated AI task or prompt chain into a workflow, or when nika check reports NIKA-XXXX findings to fix.

supernovae-st Skill

Diagnose and repair failed, paused or suspicious Nika runs from their traces (.nika/traces). Use when nika run exited red, a run paused on a prompt, a NIKA-XXXX runtime finding needs a root cause, a trace must be read or tamper-verified, or a fixed workflow needs a surgical partial rerun.

supernovae-st Skill

Convert existing automation — shell scripts, Python glue, Makefile targets, CI jobs, prompt chains in docs — into checkable .nika.yaml workflows. Use when a script wraps LLM calls or HTTP/file plumbing, a prompt chain lives in a README or notebook, or ad-hoc automation needs audit, cost bounds and replayable traces.

shareai-lab Bundle

Evaluate Agent Skill design quality with an opinionated, practice-derived rubric informed by public specifications and examples. Use when reviewing, auditing, comparing, or improving SKILL.md files and skill packages. Produces evidence-backed findings, optional multi-dimensional scoring, and prioritized changes; treat the result as diagnostic guidance, not official certification or a universal standard.

shareai-lab Bundle

Design and build AI agents for any domain. Use when users: (1) ask to "create an agent", "build an assistant", or "design an AI system" (2) want to understand agent architecture, agentic patterns, or autonomous AI (3) need help with capabilities, subagents, planning, or skill mechanisms (4) ask about AI coding agents, agent runtimes, or similar internals (5) want to build agents for business, research, creative, or operational tasks Keywords: agent, assistant, autonomous, workflow, tool use, multi-step, orchestration

shareai-lab Bundle

Transform an AI agent into a disciplined software development partner with strong judgment, transparent decisions, proportionate verification, and craftsmanship. Use for software implementation, feature work, bug fixing, refactoring, optimization, migrations, and sustained collaboration inside a codebase. Do not use merely because a task involves an AI agent; use a dedicated agent-design skill when the primary problem is agent architecture.

shareai-lab Bundle

Recover and review local human-AI conversations from Claude Code, Codex, opencode, Grok Build, and Cursor. Use when the user wants to revisit, search, extract, summarize, or compare work across Agent session stores, time ranges, projects, or named conversations. Follow the user's requested output; question clustering, problem-space mapping, artifact review, drift analysis, and insights are optional lenses.