Writing & Editing

Agent skill 'customer-research' from coreyhaines31/marketingskills.

Agent skill 'marketing-council' from coreyhaines31/marketingskills.

Agent skill 'churn-prevention' from coreyhaines31/marketingskills.

Agent skill 'marketing-loops' from coreyhaines31/marketingskills.

Agent skill 'community-marketing' from coreyhaines31/marketingskills.

Agent skill 'write-swift' from emilkowalski/skills. Use when the task matches this skill's domain.

Compress natural language memory files (CLAUDE.md / AGENTS.md, todos, preferences) into caveman format to save input tokens. Preserves all technical substance, code, URLs, and structure. Compressed version overwrites the original file. Human-readable backup saved as FILE.original.md. Trigger: /caveman-compress FILEPATH or "compress memory file"

Synthesizes the current conversation and codebase context into a PRD, then writes or publishes it according to the caller's requested output target. Use when the user asks to turn an already-discussed idea, plan, or conversation into a PRD; use `grilling` first if key decisions are still unresolved.

Common code generation and code modification discipline for agent-flow. Use before and during implementation, TDD red/green/refactor, fix-loop, bug fixes, feature work, and any task where Codex, Claude, OMP, or another agent writes or changes code. Enforces start-before, during-implementation, and after-implementation checks without a scoring rubric.

Remove multi-vendor AI provenance marks: invisible Unicode (Layer A), statistical text watermarks via rewrite (Layer B, always offer), and C2PA/EXIF/XMP/container metadata on PNG/JPEG/WebP/SVG/PDF/DOCX/ODT/HTML/MD/TEX. Covers Claude, Gemini/SynthID-class, OpenAI provenance, and open-LLM sampling marks. Use when the user asks to strip watermarks, remove C2PA/Content Credentials, clean AI metadata, remove invisible Unicode, anti-detect clean AI output, or runs /remove-ai-marks (aliases: /remove-claude-marks).

Set up a repository for effective agent-assisted development. Orchestrates opt-in phases — curated skill recommendations based on the detected stack (web, React Native, iOS, Android, Python, …), a context-management playbook and stack-aware quality gates (lint/typecheck/react-doctor/…) written into CLAUDE.md, a permissions allowlist, deterministic hooks (including write-protection for vendored third-party skills), and supply-chain guards (minimum-release-age for bun/pnpm/uv). Use when the user asks to "set up this repo for agents", "agent setup", "what skills should I add", "recommend skills", "set up quality gates / guardrails", or is bootstrapping agent tooling in a new or existing project.

Configure which models pstack uses per role. Detects your available Claude models and writes a per-role override file that the user includes from their CLAUDE.md. Use for /setup-pstack, "configure pstack models", or changing pstack's model choices.

Turn accumulated project knowledge into a new coding-agent skill file that loads itself automatically next time the topic comes up — not a memory note you have to ask for, a standing capability. Write it from a cluster of standing rules, lessons, a repeated workflow, or a correction the user keeps having to make. Use this skill whenever a directorate mission ends with lessons worth keeping, whenever the user wants a correction or preference to stick permanently instead of being repeated — "make this a skill", "remember how to do this", "stop making that mistake", "stop telling me the same thing every time" — or whenever you notice the same instruction being given for the third time. Also use when editing, splitting, or retiring an existing skill in .claude/skills/.

Turns messy words, spelling mistakes, and error pastes into one paste-ready JSON worker prompt for n8n (default), LangChain, LangGraph, Google ADK, and Claude Code. Auto-picks Prompt, Context, Harness, Loop, Eval, Tool, or Workflow Engineering. Plans only; does not execute unless the user says execute. Use when the user asks to write prompt, compose prompt, meta-prompt, says my English is bad, pastes I see this error, or mentions n8n, langchain, langgraph, adk, claude code, agent, or workflow.

Recommended operator protocol for the wallop toolbox. Load this skill on startup and whenever the user mentions wallop, tool registry, wallop toc, wallop guard, wallop register, wallop doctor, information wall, developer factory, calendar_gateway (demo-only), time_ops_reader, vault graph, an unknown tool, or wants an existing script indexed in this repo. Conventions only. Direct Python imports remain allowed. Ask before writing tools/ or modifying the YAML catalog.

Use this skill when subclassing Renderable, writing a custom draw() method, handling pointer or click events on game objects, applying post effects and shaders, or controlling draw order. Covers the pos-relative draw contract, isKinematic and input, addPostEffect vs the deprecated shader property, and z-ordering. Triggers on: Renderable, extends Renderable, draw(, update(, isKinematic, pointerEvent, registerPointerEvent, onClick, addPostEffect, removePostEffect, ShaderEffect, addChild, z-order, anchorPoint, floating.

Apply IRQL graph functions to KQL or IRQL query results for Kusto Explorer visualization. Generates Lift_To_Graph mappings and composes Graph_Render_View, Graph_Fold_By_Property, Extract_Node_*, Enrich_Node_*, and Enrich_Graph_* calls. Accepts a supplied query or limited basic natural-language source request; it is not a general natural-language-to-KQL/IRQL skill. WHEN: Lift_To_Graph, Graph_Render_View, Graph_Fold_By_Property, IRQL graph enrichment, graph mapping for existing query results, icon-decorated graph, fold graph nodes. Use azure-kusto-graph for native make-graph analysis, graph-match, shortest paths, components, or persistent graphs.

Azure Identity library for .NET. Authentication library for Azure SDK clients using Microsoft Entra ID. Use for DefaultAzureCredential, managed identity, service principals, and developer credentials. Triggers: "Azure Identity", "DefaultAzureCredential", "ManagedIdentityCredential", "ClientSecretCredential", "authentication .NET", "Azure auth", "credential chain".

Compose IRQL (Incident Response Query Language) queries for Kusto cybersecurity investigations. Translates natural language hunting questions into composable IRQL pipelines using Get_*, Extract_*, and Enrich_* functions. WHEN: IRQL query, security hunt, threat hunting KQL, incident response query, compose hunting pipeline, failed logins, phishing investigation, lateral movement, process execution, file creation events.

Azure Event Hubs SDK for .NET. Use for high-throughput event streaming: sending events (EventHubProducerClient, EventHubBufferedProducerClient), receiving events (EventProcessorClient with checkpointing), partition management, and real-time data ingestion. Triggers: "Event Hubs", "event streaming", "EventHubProducerClient", "EventProcessorClient", "send events", "receive events", "checkpointing", "partition".

Azure Event Grid SDK for .NET. Client library for publishing and consuming events with Azure Event Grid. Use for event-driven architectures, pub/sub messaging, CloudEvents, and EventGridEvents. Triggers: "Event Grid", "EventGridPublisherClient", "CloudEvent", "EventGridEvent", "publish events .NET", "event-driven", "pub/sub".

Azure AI Projects SDK for .NET. High-level client for Azure AI Foundry projects including agents, connections, datasets, deployments, evaluations, and indexes. Use for AI Foundry project management, versioned agents, and orchestration. Triggers: "AI Projects", "AIProjectClient", "Foundry project", "versioned agents", "evaluations", "datasets", "connections", "deployments .NET".

Azure AI Agents Persistent SDK for .NET. Low-level SDK for creating and managing AI agents with threads, messages, runs, and tools. Use for agent CRUD, conversation threads, streaming responses, function calling, file search, and code interpreter. Triggers: "PersistentAgentsClient", "persistent agents", "agent threads", "agent runs", "streaming agents", "function calling agents .NET".

Generate post-run analysis reports for batch processing jobs. Analyzes manifests, timings, and failures to produce comprehensive markdown reports. Optionally sends to agent-inbox for cross-project communication.