Context & AI engineering
25,772 rows, by stacks then stars
1,865 of these skill files have been read, by 1,328 distinct authors, and what they tell an agent counted. What Context & AI engineering authors agree on, and what they forbid
pinkpixel-dev/skills-collection-1/SKILLS/claude-d3js-skill Skill
9★ repoThis skill provides guidance for creating sophisticated, interactive data visualisations using d3.js.
Claude in chrome troubleshooting
pinkpixel-dev/skills-collection-1/SKILLS/claude-in-chrome-troubleshooting Skill
9★ repoDiagnose and fix Claude in Chrome MCP extension connectivity issues. Use when mcp__claude-in-chrome__* tools fail, return "Browser extension is not connected", or behave erratically.
pinkpixel-dev/skills-collection-1/SKILLS/claude-monitor Skill
9★ repoMonitor de performance do Claude Code e sistema local. Diagnostica lentidao, mede CPU/RAM/disco, verifica API latency e gera relatorios de saude do sistema.
The same file is in 1 other repository
pinkpixel-dev/skills-collection-1/SKILLS/claude-scientific-skills Skill
9★ repoScientific research and analysis skills
The same file is in 3 other repositories
pinkpixel-dev/skills-collection-1/SKILLS/claude-settings-audit Skill
9★ repoAnalyze a repository to generate recommended Claude Code settings.json permissions. Use when setting up a new project, auditing existing settings, or determining which read-only bash commands to allow. Detects tech stack, build tools, and monorepo structure.
The same file is in 1 other repository
pinkpixel-dev/skills-collection-1/SKILLS/claude-speed-reader Skill
9★ repo-Speed read Claude's responses at 600+ WPM using RSVP with Spritz-style ORP highlighting
The same file is in 3 other repositories
Claude win11 speckit update skill
pinkpixel-dev/skills-collection-1/SKILLS/claude-win11-speckit-update-skill Skill
9★ repoWindows 11 system management
The same file is in 3 other repositories
pinkpixel-dev/skills-collection-1/SKILLS/code-review-ai-ai-review Skill
9★ repoYou are an expert AI-powered code review specialist combining automated static analysis, intelligent pattern recognition, and modern DevOps practices. Leverage AI tools (GitHub Copilot, Qodo, GPT-5, C
The same file is in 3 other repositories
pinkpixel-dev/skills-collection-1/SKILLS/comm-lit-review Skill
9★ repoCommunications-domain literature review with Claude-style knowledge-base-first retrieval. Use when the task is about communications, wireless, networking, satellite/NTN, Wi-Fi, cellular, transport protocols, congestion control, routing, scheduling, MAC/PHY, rate adaptation, channel estimation, beamforming, or communication-system research and the user wants papers, related work, a survey, or a landscape summary. Search Zotero, Obsidian, and local paper folders first when available, then search IEEE Xplore, ScienceDirect, ACM Digital Library, and broader web in that order.
The same file is in 3 other repositories
Conducting memory forensics with volatility
pinkpixel-dev/skills-collection-1/SKILLS/conducting-memory-forensics-with-volatility Skill
9★ repoPerforms memory forensics analysis using Volatility 3 to extract evidence of malware execution, process injection, network connections, and credential theft from RAM dumps captured during incident response. Covers memory acquisition, process analysis, DLL inspection, and malware detection. Activates for requests involving memory forensics, RAM analysis, Volatility framework, memory dump investigation, volatile evidence analysis, or live memory acquisition.
The same file is in 1 other repository
pinkpixel-dev/skills-collection-1/SKILLS/context-agent Skill
9★ repoAgente de contexto para continuidade entre sessoes. Salva resumos, decisoes, tarefas pendentes e carrega briefing automatico na sessao seguinte.
The same file is in 1 other repository
pinkpixel-dev/skills-collection-1/SKILLS/context-fundamentals Skill
9★ repoThis skill should be used when the user asks to "understand context", "explain context windows", "design agent architecture", "debug context issues", "optimize context usage", or discusses context components, attention mechanics, progressive disclosure, or context budgeting. Provides foundational understanding of context engineering for AI agent systems.
Context management context restore
pinkpixel-dev/skills-collection-1/SKILLS/context-management-context-restore Skill
9★ repoUse when working with context management context restore
The same file is in 3 other repositories
Context management context save
pinkpixel-dev/skills-collection-1/SKILLS/context-management-context-save Skill
9★ repoUse when working with context management context save
The same file is in 11 other repositories
pinkpixel-dev/skills-collection-1/SKILLS/context-manager Skill
9★ repoElite AI context engineering specialist mastering dynamic context management, vector databases, knowledge graphs, and intelligent memory systems.
The same file is in 2 other repositories
pinkpixel-dev/skills-collection-1/SKILLS/context-window-management Skill
9★ repoYou're a context engineering specialist who has optimized LLM applications handling millions of conversations. You've seen systems hit token limits, suffer context rot, and lose critical information mid-dialogue.
The same file is in 1 other repository
pinkpixel-dev/skills-collection-1/SKILLS/conversation-memory Skill
9★ repoPersistent memory systems for LLM conversations including short-term, long-term, and entity-based memory Use when: conversation memory, remember, memory persistence, long-term memory, chat history.
The same file is in 3 other repositories
pinkpixel-dev/skills-collection-1/SKILLS/copilot-sdk Skill
9★ repoBuild applications that programmatically interact with GitHub Copilot. The SDK wraps the Copilot CLI via JSON-RPC, providing session management, custom tools, hooks, MCP server integration, and streaming across Node.js, Python, Go, and .NET.
The same file is in 1 other repository
pinkpixel-dev/skills-collection-1/SKILLS/crypto-bd-agent Skill
9★ repoProduction-tested patterns for building AI agents that autonomously discover, > evaluate, and acquire token listings for cryptocurrency exchanges.
The same file is in 1 other repository
Deploying edr agent with crowdstrike
pinkpixel-dev/skills-collection-1/SKILLS/deploying-edr-agent-with-crowdstrike Skill
9★ repoDeploys and configures CrowdStrike Falcon EDR agents across enterprise endpoints to enable real-time threat detection, behavioral analysis, and automated response. Use when onboarding endpoints to EDR coverage, configuring detection policies, or integrating Falcon telemetry with SIEM platforms. Activates for requests involving CrowdStrike deployment, Falcon sensor installation, EDR policy configuration, or endpoint detection and response.
The same file is in 1 other repository
pinkpixel-dev/skills-collection-1/SKILLS/design-orchestration Skill
9★ repoOrchestrates design workflows by routing work through brainstorming, multi-agent review, and execution readiness in the correct order.
The same file is in 2 other repositories
Detecting ai model prompt injection attacks
pinkpixel-dev/skills-collection-1/SKILLS/detecting-ai-model-prompt-injection-attacks Skill
9★ repoDetects prompt injection attacks targeting LLM-based applications using a multi-layered defense combining regex pattern matching for known attack signatures, heuristic scoring for structural anomalies, and transformer-based classification with DeBERTa models. The detector analyzes user inputs before they reach the LLM, flagging direct injections (system prompt overrides, role-play escapes, instruction hijacking) and indirect injections (encoded payloads, multi-language obfuscation, delimiter-based escapes). Based on the OWASP LLM Top 10 (LLM01:2025 Prompt Injection) and Simon Willison's prompt injection taxonomy. Activates for requests involving prompt injection detection, LLM input sanitization, AI security scanning, or prompt attack classification.
pinkpixel-dev/skills-collection-1/SKILLS/dispatching-parallel-agents Skill
9★ repoUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
The same file is in 1 other repository
pinkpixel-dev/skills-collection-1/SKILLS/enhance-prompt Skill
9★ repoTransforms vague UI ideas into polished, Stitch-optimized prompts. Enhances specificity, adds UI/UX keywords, injects design system context, and structures output for better generation results.
The same file is in 6 other repositories
pinkpixel-dev/skills-collection-1/SKILLS/evaluation Skill
9★ repoThis skill should be used when the user asks to "evaluate agent performance", "build test framework", "measure agent quality", "create evaluation rubrics", or mentions LLM-as-judge, multi-dimensional evaluation, agent testing, or quality gates for agent pipelines.
The same file is in 1 other repository
Exploiting constrained delegation abuse
pinkpixel-dev/skills-collection-1/SKILLS/exploiting-constrained-delegation-abuse Skill
9★ repoExploit Kerberos Constrained Delegation misconfigurations in Active Directory to impersonate privileged users via S4U2self and S4U2proxy extensions for lateral movement and privilege escalation.
Extracting config from agent tesla rat
pinkpixel-dev/skills-collection-1/SKILLS/extracting-config-from-agent-tesla-rat Skill
9★ repoExtract embedded configuration from Agent Tesla RAT samples including SMTP/FTP/Telegram exfiltration credentials, keylogger settings, and C2 endpoints using .NET decompilation and memory analysis.
Extracting credentials from memory dump
pinkpixel-dev/skills-collection-1/SKILLS/extracting-credentials-from-memory-dump Skill
9★ repoExtract cached credentials, password hashes, Kerberos tickets, and authentication tokens from memory dumps using Volatility and Mimikatz for forensic investigation.
The same file is in 1 other repository
Extracting memory artifacts with rekall
pinkpixel-dev/skills-collection-1/SKILLS/extracting-memory-artifacts-with-rekall Skill
9★ repoUses Rekall memory forensics framework to analyze memory dumps for process hollowing, injected code via VAD anomalies, hidden processes, and rootkit detection. Applies plugins like pslist, psscan, vadinfo, malfind, and dlllist to extract forensic artifacts from Windows memory images. Use during incident response memory analysis.
Figma create design system rules
pinkpixel-dev/skills-collection-1/SKILLS/figma-create-design-system-rules Skill
9★ repoGenerates custom design system rules for the user's codebase. Use when user says "create design system rules", "generate rules for my project", "set up design rules", "customize design system guidelines", or wants to establish project-specific conventions for Figma-to-code workflows. Requires Figma MCP server connection.
The same file is in 1 other repository
pinkpixel-dev/skills-collection-1/SKILLS/figma Skill
9★ repoUse the Figma MCP server to fetch design context, screenshots, variables, and assets from Figma, and to translate Figma nodes into production code. Trigger when a task involves Figma URLs, node IDs, design-to-code implementation, or Figma MCP setup and troubleshooting.
The same file is in 5 other repositories
pinkpixel-dev/skills-collection-1/SKILLS/filesystem-context Skill
9★ repoThis skill should be used when the user asks to "offload context to files", "implement dynamic context discovery", "use filesystem for agent memory", "reduce context window bloat", or mentions file-based context management, tool output persistence, agent scratch pads, or just-in-time context loading.
Hardening linux endpoint with cis benchmark
pinkpixel-dev/skills-collection-1/SKILLS/hardening-linux-endpoint-with-cis-benchmark Skill
9★ repoHardens Linux endpoints using CIS Benchmark recommendations for Ubuntu, RHEL, and CentOS to reduce attack surface, enforce security baselines, and meet compliance requirements. Use when deploying new Linux servers, remediating audit findings, or establishing security baselines for Linux infrastructure. Activates for requests involving Linux hardening, CIS benchmarks for Linux, server security baselines, or Linux configuration compliance.
The same file is in 1 other repository
Hardening windows endpoint with cis benchmark
pinkpixel-dev/skills-collection-1/SKILLS/hardening-windows-endpoint-with-cis-benchmark Skill
9★ repoHardens Windows endpoints using CIS (Center for Internet Security) Benchmark recommendations to reduce attack surface, enforce security baselines, and meet compliance requirements. Use when deploying new Windows workstations or servers, remediating audit findings, or establishing organization-wide security baselines. Activates for requests involving Windows hardening, CIS benchmarks, GPO security baselines, or endpoint configuration compliance.
The same file is in 1 other repository
pinkpixel-dev/skills-collection-1/SKILLS/huggingface-community-evals Skill
9★ repoRun evaluations for Hugging Face Hub models using inspect-ai and lighteval on local hardware. Use for backend selection, local GPU evals, and choosing between vLLM / Transformers / accelerate. Not for HF Jobs orchestration, model-card PRs, .eval_results publication, or community-evals automation.
pinkpixel-dev/skills-collection-1/SKILLS/huggingface-llm-trainer Skill
9★ repoThis skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV scripts with PEP 723 format, dataset preparation and validation, hardware selection, cost estimation, Trackio monitoring, Hub authentication, and model persistence. Should be invoked for tasks involving cloud GPU training, GGUF conversion, or when users mention training on Hugging Face Jobs without local GPU setup.
TeoSlayer/pilot-skills/skills/pilot-agent-marketplace-setup Skill
9★ repoDeploy a decentralized agent marketplace with 4 agents. Use this skill when: 1. User wants to set up an agent capability marketplace 2. User is configuring a directory, matchmaker, escrow, or gateway agent 3. User asks about capability discovery, auctions, or escrow settlement Do NOT use this skill when: - User wants to discover a single agent (use pilot-discover instead) - User wants to run a single auction (use pilot-auction instead)
TeoSlayer/pilot-skills/skills/pilot-consensus Skill
9★ repoDistributed voting and agreement protocols for multi-agent decision making. Use this skill when: 1. Multiple agents need to agree on a value or decision 2. You need Byzantine fault-tolerant consensus in a swarm 3. You want to coordinate distributed transactions or state changes Do NOT use this skill when: - A single leader can make decisions (use pilot-leader-election) - You only need eventual consistency (use pilot-gossip)
TeoSlayer/pilot-skills/skills/pilot-mcp-bridge-fleet-setup Skill
9★ repoDeploy an MCP and A2A bridge fleet with 3 agents. Use this skill when: 1. User wants to bridge MCP servers or A2A agents onto the Pilot network 2. User is configuring an MCP gateway, A2A bridge, or tool registry agent 3. User asks about connecting different agent ecosystems over Pilot tunnels Do NOT use this skill when: - User wants a single MCP bridge (use pilot-mcp-bridge instead) - User wants a single A2A connection (use pilot-a2a-bridge instead)
TeoSlayer/pilot-skills/skills/pilot-mcp-bridge Skill
9★ repoMCP server wrapping the Pilot daemon for OpenClaw/Claude Code integration. Use this skill when: 1. You need to expose Pilot Protocol operations as MCP tools 2. You want to integrate Pilot into Claude Code or OpenClaw workflows 3. You're building an AI agent that needs to communicate over Pilot Do NOT use this skill when: - You need direct pilotctl access (use pilot-protocol skill instead) - The daemon is not running - You're working in a non-MCP environment
TeoSlayer/pilot-skills/skills/pilot-service-agents-language Skill
9★ repoLanguage and NLP services — translation, text-to-speech, dictionaries, word tools, Bible text, linguistic corpora. Use this skill when: 1. Translating text between languages (gcp-translate, premium) 2. Finding synonyms, rhymes, related words (Datamuse) 3. Fetching word definitions or dictionary entries Do NOT use this skill when: - Running your own LLM inference — these are specific narrow NLP APIs - Document summarisation (call any agent's /summary subcommand instead)
Pilot supply chain orchestrator setup
TeoSlayer/pilot-skills/skills/pilot-supply-chain-orchestrator-setup Skill
9★ repoDeploy a supply chain orchestration pipeline with 4 agents. Use this skill when: 1. User wants to set up coordinated inventory, logistics, procurement, and compliance agents 2. User is configuring warehouse management with automated reorder workflows 3. User asks about supply chain automation, procurement pipelines, or shipping compliance Do NOT use this skill when: - User wants a single inventory dashboard (use pilot-metrics instead) - User wants to send a one-off alert for low stock (use pilot-alert instead) - User only needs webhook integration with a supplier API (use pilot-webhook-bridge instead)
TeoSlayer/pilot-skills/skills/pilot-swarm-config Skill
9★ repoDistributed configuration management for agent swarms with versioned updates. Use this skill when: 1. Multiple agents need to share configuration settings 2. You need to push config updates to all swarm members 3. You want versioned config with rollback capability Do NOT use this skill when: - Configuration is static and set at startup (use local config files) - Each agent has unique config (no sharing needed)
TeoSlayer/pilot-skills/skills/pilot-swarm-join Skill
9★ repoJoin or create agent swarms with auto-discovery and peer mesh formation. Use this skill when: 1. An agent needs to join an existing swarm or create a new one 2. You need to discover and connect to peers in a named swarm 3. You want to establish bidirectional trust with swarm members Do NOT use this skill when: - You only need point-to-point communication (use pilot-p2p-connect) - You need structured topologies like star or tree (use pilot-formation)
samzong/agent-brains/skills/agent-loader Skill
9★ repoLoad or list repo-scoped and user-scoped agent brains. Use when the user asks to load an agent by name, list available agents, inspect agent descriptions or workflows, or start a session or task with a personal agent brain.
emaraschio/cursor-commands/.cursor/skill-contracts/agent-risk-review Skill
9★ repoProduces a one-page agent permission brief (allowed, approval-required, forbidden, limits, logging, rollback, first-week test plan) before granting an AI agent access to a system, tool, or account. Use for agent risk review, permission design, MCP/tool access planning, or "what should the agent be allowed to do?"
emaraschio/cursor-commands/.cursor/skill-contracts/agent-work-receipt Skill
9★ repoProduces a conservative agent work receipt after completed work: finished output, time estimates, review burden, risks, and value judgment. Use when the user invokes /agent-work-receipt, asks for a work receipt, or wants to measure agent productivity honestly after a session.
emaraschio/cursor-commands/.cursor/skill-contracts/define-agent-goal Skill
9★ repoTurn a rough task into an agent Goal (outcome, verification with 3 to 5 success criteria, constraints, boundaries, iteration policy, stopping condition, and helper goals when parallel work is implied) so an agent can run with minimal babysitting. Plan-only, no execution in the same turn. Use for Goal, delegate, run without babysitting, or before long autonomous work. Pair with requirement-to-implementation for code delivery afterward.
emaraschio/cursor-commands/.cursor/skill-contracts/prompt-eval-debug Skill
9★ repoDebug and improve any prompt without rewriting blindly. Builds a tiny eval suite (control, edge, capability-boundary cases), diagnoses failures as prompt issue, missing tool or capability, or harness/workflow issue, and proposes the smallest next change. Use for prompt debugger, eval suite, improve prompt, or before editing catalog eval/cases.md.
emaraschio/cursor-commands/.cursor/skill-contracts/structure-prompt Skill
9★ repoTurn a rough request into a structured, production-grade prompt. Classifies which prompting dimensions apply (product verification, structured high-stakes detail, constraints-upfront, scannable structure, search priority, internal-first sourcing), fills a prompt template, and returns a copyable prompt plus a note on what was applied or omitted. Use for prompt architect, structure a prompt, harden a prompt, or turn an ask into a production prompt.
emaraschio/cursor-commands/.cursor/skill-contracts/update-memory-bank Skill
9★ repoSync memory bank with repository state
emaraschio/cursor-commands/plugin/.cursor/skill-contracts/agent-risk-review Skill
9★ repoProduces a one-page agent permission brief (allowed, approval-required, forbidden, limits, logging, rollback, first-week test plan) before granting an AI agent access to a system, tool, or account. Use for agent risk review, permission design, MCP/tool access planning, or "what should the agent be allowed to do?"
emaraschio/cursor-commands/plugin/.cursor/skill-contracts/agent-work-receipt Skill
9★ repoProduces a conservative agent work receipt after completed work: finished output, time estimates, review burden, risks, and value judgment. Use when the user invokes /agent-work-receipt, asks for a work receipt, or wants to measure agent productivity honestly after a session.
emaraschio/cursor-commands/plugin/.cursor/skill-contracts/define-agent-goal Skill
9★ repoTurn a rough task into an agent Goal (outcome, verification with 3 to 5 success criteria, constraints, boundaries, iteration policy, stopping condition, and helper goals when parallel work is implied) so an agent can run with minimal babysitting. Plan-only, no execution in the same turn. Use for Goal, delegate, run without babysitting, or before long autonomous work. Pair with requirement-to-implementation for code delivery afterward.
emaraschio/cursor-commands/plugin/.cursor/skill-contracts/prompt-eval-debug Skill
9★ repoDebug and improve any prompt without rewriting blindly. Builds a tiny eval suite (control, edge, capability-boundary cases), diagnoses failures as prompt issue, missing tool or capability, or harness/workflow issue, and proposes the smallest next change. Use for prompt debugger, eval suite, improve prompt, or before editing catalog eval/cases.md.
emaraschio/cursor-commands/plugin/.cursor/skill-contracts/structure-prompt Skill
9★ repoTurn a rough request into a structured, production-grade prompt. Classifies which prompting dimensions apply (product verification, structured high-stakes detail, constraints-upfront, scannable structure, search priority, internal-first sourcing), fills a prompt template, and returns a copyable prompt plus a note on what was applied or omitted. Use for prompt architect, structure a prompt, harden a prompt, or turn an ask into a production prompt.
emaraschio/cursor-commands/plugin/.cursor/skill-contracts/update-memory-bank Skill
9★ repoSync memory bank with repository state
JordanGunn/nunchuck/skills/prompt/prompt-compile Skill
9★ repoCompile the YAML artifact into PROMPT.md with deterministic structure. A final agent pass polishes for fluidity, conciseness, and correctness.
JordanGunn/nunchuck/skills/prompt/prompt-exec Skill
9★ repoExecute the forged prompt exactly as written. Requires explicit consent and a ready artifact. Deletes artifact after successful execution.
JordanGunn/nunchuck/skills/prompt/prompt-forge Skill
9★ repoShape, refine, and stabilize human intent into a canonical prompt artifact. Iteratively clarifies ambiguity until user confirms readiness.