Skills directory

AI-powered OSINT agent with interactive REPL, MCP server, and CLI for email/username/domain/IP/phone investigation using 11 integrated tools

Create podcasts from topics, URLs, or text. Triggers on: "做播客", "podcast", "播客", "录一期节目", "chat about", "discuss", "debate", "dialogue", "make a podcast about".

Review your local uncommitted working-tree changes (git diff plus untracked files) and return actionable improvement suggestions. Use before committing, when nothing has been pushed yet.

Develop and optimize rough CCF research ideas into problems, insights, mechanisms, and evidence plans. Use for 优化idea, 具象化idea, 找方向, 方向探索, and rescue routes when development is the requested deliverable. Judging whether an idea is worthwhil

Act as an interactive data analyst for ClickHouse-backed analytics. Use when the user asks questions about internal data, metrics, dashboards, telemetry, active users, revenue, funnels, trends, distributions, or wants an analyst-style conve

Vector embeddings with HNSW indexing, sql.js persistence, and hyperbolic support. 75x faster with agentic-flow integration. Use when: semantic search, pattern matching, similarity queries, knowledge retrieval. Skip when: exact text matching

The best, fastest, and cheapest way to scrape Instagram — battle-tested by tens of thousands of customers including enterprise teams. Use when the user wants to fetch Instagram posts, reels, profiles, hashtags, locations, comments, or user/

Instrument an application with Sentry — detect the platform, install and initialize the SDK if needed, and wire up any signal — error monitoring, tracing/performance, logging, metrics, profiling, session replay, user feedback, cron check-in

Audit existing CCF claims, numbers, terminology, and citations against supplied or verified evidence. Use for 引用核验, claim审计, 数字一致性, and BibTeX/context checks. Full scientific review belongs to ccf-paper-reviewer; new literature discovery be

Use when the user mentions DhanHQ, Dhan API, or wants to trade on Indian exchanges (NSE, BSE, MCX). Triggers for: place, modify, or cancel stock/F&O/commodity orders on Dhan; fetch portfolio holdings or positions; get live or historical mar

Review all currently unreviewed open pull requests, newest first, using the om-auto-review-pr skill and respecting in-progress claim locks.

Execute the implementation plan by processing and executing all tasks defined in tasks.md

Agent skill for planner - invoke with $agent-planner

Quantum-resistant, self-learning version control for AI agents with ReasoningBank intelligence and multi-agent coordination

Main application building orchestrator. Creates full-stack applications from natural language requests. Determines project type, selects tech stack, coordinates agents.

Design CCF experiment protocols and evidence schemas: datasets, baselines, metrics, ablations, and result-table contents. Use for 设计实验, 消融, benchmark planning, and 结果表证据结构. Preserve real values. Table styling/rendering belongs to ccf-visual

Assess research ideas for value, novelty, insight, and mechanism. Use for 思路审核, 靠谱吗, 值得做吗, 创新够不够, idea review, scoring, and ranking; no numeric-score request is needed. Default to concept-only review without experiment assessment, including

This skill should be used when analyzing CSV datasets, handling missing values through intelligent imputation, and creating interactive dashboards to visualize data trends. Use this skill for tasks involving data quality assessment, automat

Train reasoning and verifiable-task behavior with GRPO and reinforcement learning from verifiable rewards (RLVR). Use when task success is algorithmically checkable (math, code, tool calls, structured output), when designing GRPO reward fun

Add one optional external Codex critique after the existing council has produced a decision draft. Use when an ambiguous, high-consequence decision would benefit from a separate model invocation's attempt to break the synthesis. Requires ex

Uses persistent markdown files for general planning, progress tracking, and knowledge storage (Manus-style workflow). Use for multi-step tasks, research projects, or general organization WITHOUT mentioning PRD. For PRD-specific work, use pr

Generate comprehensive Product Requirements Documents (PRDs) for product managers. Use this skill when users ask to "create a PRD", "write product requirements", "document a feature", or need help structuring product specifications.

SPARC development workflow: Specification, Pseudocode, Architecture, Refinement, Completion. A structured approach for complex implementations that ensures thorough planning before coding. Use when: new feature implementation, complex imple

Advanced swarm orchestration patterns for research, development, testing, and complex distributed workflows

Use when resizing images, generating thumbnails, serving responsive images, or optimizing image delivery with Tigris — covers Next.js, Remix, Rails, Django, Laravel, Express

Copy and text skill for antislop. Use when writing or editing prose: headlines, tone, CTAs, and anti-AI-writing patterns. Load with the core.

Apply exact Tailwind arbitrary shadow utilities for polished, layered neutral elevation. Use when compact cards, controls, panels, popovers, hero media, feature callouts, or modal-like containers need refined shadows without default Tailwin

Create, update, or validate a product brief. Use when the user wants help producing, editing, or validating a brief

Set up, adopt, refresh, or audit a repository's agent instructions (the AGENTS.md block) so AI agents work well in that repo. Also records observed agent mistakes as pitfalls. Use when invoked by name

Diagnoses GKE nodes reporting NotReady or Unknown status by inspecting node conditions, events, kubelet/containerd logs, and node metrics, then proposing safe remediations. Use when nodes show NotReady, when the kubelet stops posting node s

Core principles of SEO including E-E-A-T, Core Web Vitals, technical foundations, content quality, and how modern search engines evaluate pages.

Fine-tune vision-language models (VLMs) with supervised learning on image+text data. Use when adapting a VLM to a visual domain or task, configuring frozen-vision-tower LoRA, or debugging a VLM fine-tune that trains without learning.

Agent skill for repo-architect - invoke with $agent-repo-architect

Scan recent arXiv/OpenReview papers, venue feeds, labs, and competitors for overlap. Use for 竞品监控, 新论文追踪, 论文跟踪, and recurring novelty watch. Give dated evidence and changes since the prior scan. Broad related-work retrieval belongs to ccf-l

Query Coralogix infrastructure resources with the `cx infra` CLI: resource types, filterable attributes, resource lists, health, raw data and configuration changes. Use when the user asks to "show resource types", "list infrastructure resou

Creates Cloud Storage on Google Cloud (also known colloquially as GCS) buckets. Analyzes the workload (sensitive data, media hosting, ingestion, web hosting, archiving, backup, logging, analytics, AI/ML, or general-purpose), validates proje

.NET 10 minimal APIs — the default for building HTTP endpoints. Covers MapGroup, endpoint filters, TypedResults, OpenAPI metadata, parameter binding, and route conventions. Load this skill when creating API endpoints, configuring routing, s

Author a new OM skill from a brief, or split an oversized SKILL.md into layered references/ files — conservatively, behind the lint + completeness gate. Knows the layering philosophy, lint invariants, tracker abstraction, and the cross-skil

Use when creating or configuring a next-safe-action client, defining actions with input/output validation, handling server errors, or setting up createSafeActionClient with Standard Schema (Zod, Yup, Valibot)

Agent skill for swarm-memory-manager - invoke with $agent-swarm-memory-manager

Manages WhatsApp messaging through AWS End User Messaging Social. Covers managing templates (create, update, delete, library), sending messages (utility/marketing/auth templates and freeform), uploading and managing media, configuring event

Comprehensive GitHub release orchestration with AI swarm coordination for automated versioning, testing, deployment, and rollback management

AI-assisted pair programming with multiple modes (driver$navigator$switch), real-time verification, quality monitoring, and comprehensive testing. Supports TDD, debugging, refactoring, and learning sessions. Features automatic role switchin

Convert evaluation traces and production logs into SFT examples and preference pairs. Use when graded traces or failure examples exist and need to become training data, when applying rejection sampling to model outputs, or when building DPO

This skill should be used when the user asks to "fix janky CSS animation", "make animation 60fps", "stop layout thrashing", "animate width/height/top/left smoothly", "convert animation to transform", "animate box-shadow performantly", "anim

Agent skill for orchestrator-task - invoke with $agent-orchestrator-task

Required first preflight before every CCFA skill, including research, review, retrieval, experiments, visuals, and maintenance. Keep reasoning and communication direct, remove empty defensive framing, and preserve evidence and uncertainty.

Orchestrate a configurable, multi-member CLI planning council (Codex, Claude Code, Gemini, OpenCode, or custom) to produce independent implementation plans, anonymize and randomize them, then judge and merge into one final plan. Use when yo

Use when user specfically says 'plan harder'.

Turso Cloud — fully managed SQLite-compatible database platform, accessed over the network. Use when connecting an application to a Turso Cloud database, creating or scoping auth tokens (JWT, fine-grained permissions, JWKS/external auth pro