diskd-ai
@diskd-ai Organization
Public Skills
ccbox-insights
by diskd-ai
Summarize lessons learned from ccbox session logs (projects/sessions/history/skills) so the agent can do better next time. Produce copy-ready instruction updates (project + global) backed by evidence, with optional skill-span context to attribute failures to specific skills. Use when asked to run /ccbox:insights, generate a "lessons learned" memo, or propose standing instructions from session history.
ccbox
by diskd-ai
Inspect and summarize local Codex/Claude session logs using the ccbox CLI (projects, sessions, history). Use when asked to list discovered projects, find sessions for the current repo/folder, print a session timeline, or produce an evidence-based “what happened” report from a session .jsonl log under CODEX_SESSIONS_DIR.
gemini-api
by diskd-ai
Google Gemini API integration for building AI-powered applications. Use when working with Google's Gemini API, Python SDK (google-genai), TypeScript SDK (@google/genai), multimodal inputs (image, video, audio, PDF), thinking/reasoning features, streaming responses, structured outputs with JSON schemas, multi-turn chat, system instructions, image generation (Nano Banana), video generation (Veo), music generation (Lyria), embeddings, document/PDF processing, or any Gemini API integration task. Triggers on mentions of Gemini, Gemini 3, Gemini 2.5, Google AI, Nano Banana, Veo, Lyria, google-genai, or @google/genai SDK usage.
redmine-cli
by diskd-ai
"Manage Redmine issues/tickets from the command line via the Redmine REST API using a red-cli-style interface. Uses ~/.red/config.json for auth (server + api-key) with optional local overrides in ./.red/config.json. Use when you need to create issues (defaults to Task tracker), list issues/projects, view issues (with journals), add journal notes/comments (public or private), edit issue fields (subject, description, status, priority, tracker, parent, assigned-to), manage issue relations (relates, blocks, duplicates, precedes, follows), update/remove existing comments (journals) by journal id, filter/sort/paginate lists, or troubleshoot Redmine CLI configuration (project-id/user-id, multi-instance --rid). Triggers on Redmine, red-cli, issue create/list/view/note/edit/relate/comment, subtask, parent, relation, --rid, .red/config.json, api-key, project-id, user-id, or requests to automate Redmine from a CLI."
design-doc
by diskd-ai
Create technical design documents for new features, systems, refactoring plans, API designs, and database schemas. Use when asked to write a design doc, TRD (technical requirements document), RFC, or system design document. Triggers on requests like "write a design doc for X", "design the Y feature", "create a technical spec", or "plan the architecture for Z".
claude-api
by diskd-ai
Anthropic Claude API integration for building AI-powered applications. Use when working with Anthropic's Messages API, Claude SDKs (Python or TypeScript), tool use/function calling, vision/image inputs, streaming responses, prompt caching, message batches, token counting, extended thinking, PDF processing, or any Claude API integration task.
tilt-config
by diskd-ai
Create, update, and troubleshoot Tilt configuration (Tiltfile, Tiltfile extensions, and common Tiltfile API usage like docker_build/custom_build/live_update, k8s_yaml/k8s_resource, local_resource, and Docker Compose/Helm workflows). Use when asked to add Tilt to a repository, adjust dev-environment orchestration, or debug Tiltfile evaluation/resource update issues. Prefer consulting the local Tilt documentation source at /Users/alexeus/src/tilt.build/docs (and the generated API includes under /Users/alexeus/src/tilt.build/src/_includes/api) when available.
clarify
by diskd-ai
Clarify redmine task skill
human-interface-guidelines-1992
by diskd-ai
Apply and review classic desktop UI designs against the 1992 Human Interface Guidelines. Use when designing or auditing menus, windows, dialog/alert boxes, controls, icons, color, mouse/keyboard behaviors, language/messages/help (including Balloon Help), localization/worldwide compatibility, accessibility (universal access), and collaborative-computing UX for desktop-style interfaces.
code-review
by diskd-ai
"Review code with a structured, high-signal review process. Use when asked to review code, review a PR/MR (GitHub PRs via gh, GitLab MRs via glab), review a codebase, give feedback on a changelist, audit code quality, or perform a code review. Supports both diff/PR reviews and full codebase reviews. Produces actionable findings with severity labels, exact file+line citations, and a final verdict. Covers design, functionality, complexity, tests, naming, comments, style, documentation, security, and performance."
openai-api
by diskd-ai
OpenAI API integration for building AI-powered applications. Use when working with OpenAI's Chat Completions API, Python SDK (openai), TypeScript SDK (openai), tool use/function calling, vision/image inputs, streaming responses, DALL-E image generation, Whisper audio transcription, text-to-speech, embeddings, Assistants API, fine-tuning, or any OpenAI API integration task. Triggers on mentions of OpenAI, GPT-4, GPT-4o, GPT-5, o1, o3, o4, DALL-E, Whisper, Sora, or OpenAI SDK usage.
prompting
by diskd-ai
Prompt engineering guidance for writing and improving LLM prompts. Use when asked to (1) write a prompt for a specific task, (2) review or improve an existing prompt, (3) design system prompts for AI assistants, (4) structure prompts for specific output formats (JSON, XML, markdown), or (5) apply prompt engineering techniques like few-shot, chain-of-thought, or role prompting.
cerebras-api
by diskd-ai
Cerebras API integration for building AI-powered applications with ultra-fast LLM inference. Use when working with Cerebras's Chat Completions API, Python SDK (cerebras_cloud_sdk), TypeScript SDK (@cerebras/cerebras_cloud_sdk), tool use/function calling, structured outputs with JSON schemas, reasoning models with thinking tokens, streaming responses, or any Cerebras API integration task. Triggers on mentions of Cerebras, Cerebras Inference, Llama on Cerebras, Qwen on Cerebras, GLM, or fast LLM inference needs.
groq-api
by diskd-ai
Groq API integration for building AI-powered applications with ultra-fast LLM inference. Use when working with Groq's Chat Completions API, Python SDK (groq), TypeScript SDK (groq-sdk), tool use/function calling, vision/image processing, audio transcription with Whisper, streaming responses, text-to-speech, content moderation with Llama Guard, batch processing, or any Groq API integration task. Triggers on mentions of Groq, GroqCloud, or fast LLM inference needs.
together-api
by diskd-ai
Together AI API integration for building AI-powered applications with open-source models. Use when working with Together's Chat Completions API, Python SDK (together), TypeScript SDK (together-ai), CLI tool, tool use/function calling, vision/image understanding, image generation (FLUX, Stable Diffusion), video generation (Veo, Sora, Kling), audio transcription (Whisper), text-to-speech, streaming responses, embeddings, reranking, fine-tuning, or any Together AI API integration task. Triggers on mentions of Together AI, Together API, GroqCloud, open-source LLM inference, FLUX image generation, or Whisper transcription via Together.