Claude Skills by tools-only

Find and identify the CBaseEntity_GetHammerUniqueId virtual function in CS2 binary using IDA Pro MCP. Use this skill when reverse engineering CS2 server.dll or server.so to locate the GetHammerUniqueId vfunc by searching for the "hammerUniqueId" string and identifying the function that calls a vtable method guarded by an OR condition, then writes the result to a CUtlString member.

Find and identify the CBaseEntity_StartTouch, CBaseEntity_Touch, and CBaseEntity_EndTouch virtual functions in CS2 binary using IDA Pro MCP. Use this skill when reverse engineering CS2 server.dll or server.so to locate these touch-related virtual functions by searching for the "INVALID CGameEventStartTouchCollideAdaptor" string reference and analyzing the touch event handler functions.

High-level SDK for Azure AI Foundry project management with access to connections, datasets, indexes, and evaluations.

Generate lambda function generator operations. Auto-activating skill for AWS Skills. Triggers on: lambda function generator, lambda function generator Part of the AWS Skills skill category. Use when working with lambda function generator functionality. Trigger with phrases like "lambda function generator", "lambda generator", "lambda".

Create threat model creator operations. Auto-activating skill for Security Advanced. Triggers on: threat model creator, threat model creator Part of the Security Advanced skill category. Use when working with threat model creator functionality. Trigger with phrases like "threat model creator", "threat creator", "threat".

Generate firewall rule generator operations. Auto-activating skill for GCP Skills. Triggers on: firewall rule generator, firewall rule generator Part of the GCP Skills skill category. Use when working with firewall rule generator functionality. Trigger with phrases like "firewall rule generator", "firewall generator", "firewall".

Provides comprehensive Tailwind CSS utility-first styling patterns including responsive design, layout utilities, flexbox, grid, spacing, typography, colors, and modern CSS best practices. Use when styling React/Vue/Svelte components, building responsive layouts, implementing design systems, or optimizing CSS workflow.

> **⚠️ DEPRECATION NOTICE**: This package is deprecated. Migrate to `azure-monitor-opentelemetry-autoconfigure`. > > See [Migration Guide](https://github.com/Azure/azure-sdk-for-java/blob/main/sdk/monitor/azure-monitor-opentelemetry-exporter/MIGRATION.md) for detailed instructions. Export OpenTelemetry telemetry data to Azure Monitor / Application Insights.

Simplifies and refines code for clarity, consistency, and maintainability while preserving all functionality. Use when asked to "simplify code", "clean up code", "refactor for clarity", "improve readability", or review recently modified code for elegance. Focuses on project-specific best practices.

Comprehensive R package for command-line interface styling, semantic messaging, and user communication. Use this skill when working with R code that needs to: (1) Format console output with inline markup and colors, (2) Display errors, warnings, or messages with cli_abort/cli_warn/cli_inform, (3) Show progress indicators for long-running operations, (4) Create semantic CLI elements (headers, lists, alerts, code blocks), (5) Apply themes and customize output styling, (6) Handle pluralization i...

Comprehensive Obsidian vault management. USE WHEN obsidian, vault, note, daily note, PARA, inbox, knowledge capture, dataview, DQL, search vault, .base, bases, wikilink, frontmatter, second brain, markdown syntax, obsidian.nvim, OR obsidian API. Python-powered tools for search, creation, and vault health.

Configure with aggregation helper operations. Auto-activating skill for Data Analytics. Triggers on: aggregation helper, aggregation helper Part of the Data Analytics skill category. Use when working with aggregation helper functionality. Trigger with phrases like "aggregation helper", "aggregation helper", "aggregation".

Find and identify the CTriggerPush_Touch (CTriggerPush::Touch) virtual function in CS2 binary using IDA Pro MCP. Use this skill when reverse engineering CS2 server.dll or server.so to locate the CTriggerPush touch handler function by using vtable information and the inherited vtable index from CBaseEntity::Touch.

Comprehensive DAG failure diagnosis and root cause analysis. Use for complex debugging requests requiring deep investigation like "diagnose and fix the pipeline", "full root cause analysis", "why is this failing and how to prevent it". For simple debugging ("why did dag fail", "show logs"), the airflow entrypoint skill handles it directly. This skill provides structured investigation and prevention recommendations.

> Migrated from the former `sf-ai-agentforce-legacy/docs/actions-reference.md` on 2026-02-07. > For context-aware descriptions, instruction references, and input binding patterns, see [action-patterns.md](action-patterns.md). > For prompt template actions (`generatePromptResponse://`), see [action-prompt-templates.md](action-prompt-templates.md). Complete guide to Agent Actions in Agentforce: Flow, Apex, API actions, escalation routing, and GenAiFunction metadata. ---

> Migrated from the former `sf-ai-agentforce-legacy/references/actions-reference.md` on 2026-02-07. > For context-aware descriptions, instruction references, and input binding patterns, see [action-patterns.md](action-patterns.md). > For prompt template actions (`generatePromptResponse://`), see [action-prompt-templates.md](action-prompt-templates.md). Complete guide to Agent Actions in Agentforce: Flow, Apex, API actions, escalation routing, and GenAiFunction metadata. ---

> Migrated from the former `sf-ai-agentforce-legacy/references/actions-reference.md` on 2026-02-07. > For context-aware descriptions, instruction references, and input binding patterns, see [action-patterns.md](action-patterns.md). > For prompt template actions (`generatePromptResponse://`), see [action-prompt-templates.md](action-prompt-templates.md). Complete guide to Agent Actions in Agentforce: Flow, Apex, API actions, escalation routing, and GenAiFunction metadata. ---

Universal principles for writing maintainable code. Stack-specific details should live in project CLAUDE.md files.

Git-backed issue tracker for AI agents. Track all work as Pebble issues.

Git-backed issue tracker for AI agents. Track all work as Pebble issues.

You're not a chatbot. You're not an assistant waiting to be told what to do. You're a craftsman with access to powerful tools, working alongside a human who trusts you with their codebase.

You're not a chatbot. You're not an assistant waiting to be told what to do. You're a craftsman with access to powerful tools, working alongside a human who trusts you with their codebase.

You're not a chatbot. You're not an assistant waiting to be told what to do. You're a craftsman with access to powerful tools, working alongside a human who trusts you with their codebase.

Use for broad codebase research when you don't know where to look, need to understand "how does X work?", or want comprehensive findings across many files. Returns file paths, line numbers, code snippets, and negative results. Read-only — cannot modify files.

Use when you have a detailed, unambiguous implementation spec (e.g., "add export for function X in file Y"). Executes the spec, runs typecheck/tests, reports results. Spawn multiple in parallel for independent tasks. Does NOT ask questions — reports ambiguity and stops.

Validate a plan before implementation. Use before exiting Plan mode. Pass the plan file path and any additional context files. Returns JSON with findings and score (must reach 9+ to proceed).

Validate a plan before implementation. Use before exiting Plan mode. Pass the plan file path and any additional context files. Returns JSON with findings and score (must reach 9+ to proceed).

Automated code improvement and cleanup.

Quantitative benchmark of LLM code refactoring skill.

I'll help you restructure your code systematically - preserving functionality while improving structure, readability, and maintainability. Arguments: `$ARGUMENTS` - files, directories, or refactoring scope **KEY FEATURE: Built-in validation and refinement after EVERY change ensures nothing breaks and no code is left behind. The AI will automatically fix its own mistakes during the refactoring process.** **SESSION FILES LOCATION: Always use refactor/ folder in current directory**

Use for mechanical refactors across the codebase — "rename X to Y", "extract this to a helper", "move function to shared module". Performs comprehensive symbol search, updates all imports/exports, verifies with typecheck/tests. Flags ambiguous cases for human review.

Perform a comprehensive codebase refactor, bug-fix sweep, and documentation sync.

**When to plan**: New features touching multiple files, refactoring with unclear scope, architecture changes, bug fixes with unclear root cause. **Interview first**: Before non-trivial tasks, use `AskUserQuestion` iteratively. For complex tasks, up to 40 questions across multiple rounds. **Workflow**: 1. Interview the user thoroughly 2. Check existing ADRs in `.meridian/adrs/` for relevant architectural decisions 3. Research the codebase (direct tools or Explore agents) 4. Follow the `/planni...

**When to plan**: New features touching multiple files, refactoring with unclear scope, architecture changes, bug fixes with unclear root cause. **Interview first**: Before non-trivial tasks, use `AskUserQuestion` iteratively. For complex tasks, up to 40 questions across multiple rounds. **Workflow**: 1. Interview the user thoroughly 2. Check existing ADRs in `.meridian/adrs/` for relevant architectural decisions 3. Research the codebase (direct tools or Explore agents) 4. Follow the `/planni...

**When to plan**: New features touching multiple files, refactoring with unclear scope, architecture changes, bug fixes with unclear root cause. **Interview first**: Before non-trivial tasks, use `AskUserQuestion` iteratively. For complex tasks, up to 40 questions across multiple rounds. **Workflow**: 1. Interview the user thoroughly 2. Check existing ADRs in `.meridian/adrs/` for relevant architectural decisions 3. Research the codebase (direct tools or Explore agents) 4. Follow the `/planni...

CodeRabbit AI reviews PRs automatically after creation. First review takes up to 7 minutes — check CI status ('pending' = in progress).

**Plan:** ALMA Memory Landing Page **What:** Created comprehensive design plan for conversion-focused developer landing page **Files Updated:** - None (planning phase) **Notes:** User approved plan with "go - approved!" --- **Plan:** ALMA Memory Landing Page **What:** Read existing documentation to gather content **Files Read:** - /mnt/d/1.GITHUB/ALMA-memory/site-docs/about/story.md - /mnt/d/1.GITHUB/ALMA-memory/site-docs/comparison/mem0-vs-alma.md - /mnt/d/1.GITHUB/ALMA-memory/

ALMA supports hierarchical memory sharing between agents, enabling knowledge transfer without duplicating data.

The ALMA TypeScript SDK provides a type-safe client for interacting with ALMA Memory from JavaScript and TypeScript applications.

**Source URL:** [https://googleapis.github.io/js-genai/release_docs/index.html](https://googleapis.github.io/js-genai/release_docs/index.html) ---

I was building AI agents for automated testing - Helena for frontend QA, Victor for backend verification. They worked great... until they didn't. **The same mistakes kept happening:** - Helena would use `sleep(5000)` for waits, causing flaky tests - Victor would forget that the API uses JWT with 24-hour expiry - Both agents would repeat failed strategies session after session Every conversation started fresh. No memory. No learning. Just an expensive LLM making the same mistakes I'd a

**Status:** authoritative *as implemented in code* (not aspirational). **Scope:** This document describes the **current** request/iteration loop and the **node orchestrator** (tool dispatch + tool returns + usage/thought recording) so the system can be replaced cleanly. **Source of truth:** code only. Primary code locations: - Request loop (per user message): `src/tunacode/core/agents/main.py` - `RequestOrchestrator` (class) - `process_request(...)` (function) - Node orchestrator (per streame...

> **HISTORICAL DOCUMENT**: This analysis from 2026-01-30 explored memory integration strategies and recommended task-file consumers, .claude/rules/, and structured MEMORIES.md sections. The actual implementation (Memory System v3, 2026-01-31) implemented an append-only event store with auto-capture from checkpoints instead. See [docs/index.md](index.md#memory-system-v3) for the current implementation. > **Generated by**: `/heavy` (5 Opus agents, 3 rounds, adversarial dialogue + red-team) > **...

> **HISTORICAL DOCUMENT**: This analysis from 2026-01-30 explored memory integration strategies and recommended task-file consumers, .claude/rules/, and structured MEMORIES.md sections. The actual implementation (Memory System v3, 2026-01-31) implemented an append-only event store with auto-capture from checkpoints instead. See [docs/index.md](index.md#memory-system-v3) for the current implementation. > **Generated by**: `/heavy` (5 Opus agents, 3 rounds, adversarial dialogue + red-team) > **...

Exhaustive codebase audit for architectural health, maintainability, and scalability

Audit environment variables for fallback patterns, missing values, and config-dependent runtime behavior

Exhaustive sweep to identify and remove AI-generated code slop

Exhaustive audit of all Markdown documentation for gaps, staleness, and structure

Establish performance benchmarks and optimize Next.js + FastAPI apps

Integrating Compound Engineering and Supermemory into the Namshub Agent Harness This research was conducted on January 30th, 2026, using heavy multi-perspective analysis with twelve Opus agents across four rounds. Two repositories were analyzed -- compound-engineering-plugin with six thousand two hundred stars, and claude-supermemory. Executive Summary Two open-source projects solve the same fundamental problem -- Claude Code sessions don't learn from each other. Each session starts from scra...