Claude Skills by kmshihab7878

Onboard or refresh the AI OS context by interviewing the user with the 7-question intake. Populates context/, seeds connections.md, and logs the run in decisions/log.md. NEVER auto-fills identity from session environment — all PII fields require explicit user input. Triggered by /onboard or when the user explicitly asks to onboard / re-onboard / refresh context.

Task routing, risk assessment, execution modes, and completion standards for meaningful work.

OSINT investigation and reconnaissance workflows. Username enumeration, domain intelligence, dark web monitoring, social media analysis, and structured investigation methodology. Use for authorized OSINT research, threat intelligence, and security investigations.

Automated academic paper and technical content scanning for the Research department. Discovers relevant papers from arXiv, conference proceedings, and tech blogs. Extracts key findings, scores applicability to CoreMind, and feeds the research self-improvement loop. Use when scanning for new research, evaluating papers, building literature reviews, or running the research UAOP pipeline.

Create new agents in Paperclip with governance-aware hiring. Use when you need to inspect adapter configuration options, compare existing agent configs, draft a new agent prompt/config, and submit a hire request.

Create new Paperclip plugins with the current alpha SDK/runtime. Use when scaffolding a plugin package, adding a new example plugin, or updating plugin authoring docs. Covers the supported worker/UI surface, route conventions, scaffold flow, and verification steps.

Interact with the Paperclip control plane API to manage tasks, coordinate with other agents, and follow company governance. Use when you need to check assignments, update task status, delegate work, post comments, set up or manage routines (recurring scheduled tasks), or call any Paperclip API endpoint. Do NOT use for the actual domain work itself (writing code, research, etc.) — only for Paperclip coordination.

Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.

Generate professional PowerPoint presentations from structured content. Slide layouts, themes, charts, tables, speaker notes. Uses python-pptx. Use when creating presentations, pitch decks, reports as slides, or converting content to PPTX format.

Design, optimize, and communicate SaaS pricing — tier structure, value metrics, pricing pages, and price increase strategy. Use when building a pricing model from scratch, redesigning existing pricing, planning a price increase, or improving a pricing page. Trigger keywords: pricing tiers, pricing page, price increase, packaging, value metric, per seat pricing, usage-based pricing, freemium, good-better-best, pricing strategy, monetization, pricing page conversion, Van Westendorp. NOT for bro...

Automated competitor feature tracking, user feedback clustering, and feature validation for the Product department. Monitors competitor launches, aggregates user feedback signals, clusters by theme, and feeds the product self-improvement loop. Use when tracking competitor features, analyzing user feedback, validating feature hypotheses, or running the product UAOP pipeline.

Production monitoring with Grafana, Prometheus, Loki, and OpenTelemetry for containerized Python services on AWS EKS

Scaffold a new project with CLAUDE.md, agents, skills, rules, and hooks pre-configured for the project type. Triggers on "new project", "scaffold project", "create template", "init project", "bootstrap project". Provide the project type as argument (python, nextjs, fullstack, api, flutter).

Enforce evidence-backed promotion criteria for candidate learnings. Use when the user runs /evolution promote <id>. Wraps bin/evolve-promote.sh and explains why each gate passed or failed. Never promotes on its own judgment — always runs the script.

9-mode prompt reliability framework: diagnose, repair, stress-test, constrain, lock, architect, audit, prune, and self-improve prompts, skills, and workflows. Treats prompting as engineering.

Hypothesis property-based testing strategies for Python with custom strategies for financial data, API responses, and stateful testing

Produce a prune report: stale candidates, stale promoted learnings, and suspected regressions. Use weekly or when startup context feels noisy. Read-only — writes a report but never removes anything on its own.

Python code quality enforcement with Ruff, pyright, Vulture, and deptry for linting, formatting, type checking, dead code, and dependency hygiene

Senior Quality Manager Responsible Person (QMR) for HealthTech and MedTech companies. Provides quality system governance, management review leadership, regulatory compliance oversight, and quality performance monitoring per ISO 13485 Clause 5.5.2.

Bidirectional Qwen↔Claude task routing with Claude-style thinking — offload worker tasks, escalate complex tasks, unified model routing

RAG architecture patterns and optimization. Chunking strategies, embedding selection, retrieval tuning, multimodal RAG, agentic RAG, and memory systems. Use when building knowledge retrieval systems, agent memory, or optimizing LLM context usage.

Catalog + task router for React Bits — 130 open-source animated, interactive, fully customizable React components (DavidHDev/react-bits, 38k★). Use when user wants animated React UI: animated text (blur, shiny, decrypt, split, scroll-reveal), interactive animations (cursor effects, click spark, magnet, splash), shader/canvas backgrounds (aurora, galaxy, particles, liquid chrome, prism), or polished components (dock, card swap, magic bento, tilted card, glass surface). Maps design briefs to th...

Cross-session search combining claude-mem semantic vector search with conversation history grep for comprehensive memory recall

Guidance for evaluating review feedback, applying valid changes, and responding with evidence.

Parameterized YAML workflow recipes — create, run, list, and compose shareable automation packages with typed inputs, sub-recipes, and extension bundling (inspired by Goose)

Automated releases with Release Please, Renovate, conventional commits, semantic versioning, and CHANGELOG generation

Remotion video animation patterns from JonnyBurger's workflow. Spring physics, typewriter effects, 3D transforms, staggered reveals, flip transitions, composition architecture. Use when building Remotion compositions or programmatic video animations.

Search and research workflow patterns. Research depth levels, source credibility assessment, multi-hop reasoning, search query formulation, and citation management. Use when conducting research, evaluating sources, or synthesizing findings.

Mobile-first responsive layout patterns for React/Next.js/Tailwind apps. Breakpoints, container queries, fluid typography with clamp(), responsive grids, viewport units (svh), table-to-card conversion, adaptive navigation. Use when building layouts that must adapt across mobile, tablet, and desktop viewports.

Security review and hardening patterns. OWASP Top 10 checklist, secrets scanning, auth patterns, input validation, and container security. Use when auditing code, reviewing PRs for security, or implementing auth/authz.

Produce an end-of-session report: what happened, what worked, what friction recurred, and which candidate learnings emerged. Use when the user asks /evolution report or invokes this manually at session end. Writes to evolution/reports/, never to stable/.

Confirm the evolution layer is active at session start and report what was injected. Use at the start of any session where behavior may have recently changed, or when the user asks what guidance is active. Read-only — does not modify stable/.

Sim Studio AI agent orchestration — build, deploy, and invoke visual workflows as MCP tools. Use when automating multi-step tasks, creating agent workflows, or orchestrating AI pipelines via Sim Studio.

Build, validate, and improve Claude Code skills. Design-first workflow with YAML frontmatter validation, progressive disclosure, and quality assessment. Use when creating new skills, improving existing ones, auditing skill quality, or troubleshooting skill triggering issues.

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

Self-evolving skill lifecycle with three triggers: post-execution fix, degradation detection, and periodic metric review. Skills improve automatically based on real execution data.

Run SocratiCode-assisted exploration before broad Read/Grep on a non-trivial code task. Falls back gracefully to code-review-graph MCP when SocratiCode isn't installed. Used implicitly by /ship, /audit-deep, /fix-root, /review.

Structured logging patterns with loguru and structlog for Python services, JSON output, correlation IDs, and Loki/Grafana integration

Guidance for assigning, coordinating, and reviewing focused subagent work.

Guidance for using a red-green-refactor cycle before changing production behavior.

Automated test coverage gap detection and targeted test generation. Analyzes codebase for untested functions, uncovered branches, missing edge cases, and regression gaps. Produces prioritized test generation targets ranked by bug risk. Use when assessing test coverage, finding untested code, planning test sprints, or running the Quality department's UAOP self-improvement loop.

Testing strategy and patterns. Test pyramid, AAA pattern, TDD workflow, coverage targets, edge case checklists, and framework-specific patterns. Use when writing tests, designing test strategies, or reviewing test quality.

Automated CVE and threat intelligence aggregation, prioritization, and patch tracking for the Security department. Scans vulnerability databases, threat feeds, and dependency reports. Ranks threats by exploitability × impact, tracks patch SLAs, and feeds the security self-improvement loop. Use when scanning for vulnerabilities, triaging CVEs, tracking patch compliance, or running the security UAOP pipeline.

Zero-shot time series forecasting with Google's TimesFM foundation model. Use this skill when forecasting ANY univariate time series — sales, sensor readings, stock prices, energy demand, patient vitals, weather, or scientific measurements — without training a custom model. Supports both basic forecasting and advanced covariate forecasting (XReg) with dynamic and static exogenous variables. Automatically checks system RAM/GPU before loading the model, validates dataset fit before processing, ...

UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 9 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles...

Cognitive depth engine for Claude Code. Defines 5 thinking modes (quick → council), activation triggers, quality bars, reasoning scaffolds, and the ultrathink protocol for complex multi-domain decisions. Use when a task requires deep synthesis before action — architecture decisions, security reviews, strategic planning, cross-system design. Pairs with /ultraplan for full execution.

Use when you need to ask questions about a codebase or understand code using a knowledge graph

CoreMind specific knowledge graph queries with governance-aware layer mapping and agent hierarchy understanding

Launch the interactive web dashboard to visualize a codebase's knowledge graph

Use when you need to analyze git diffs or pull requests to understand what changed, affected components, and risks