dootsabha
Orchestrates multiple AI coding CLIs (Claude, Codex, Antigravity, Grok) as a council. Use for a second opinion from another model, multi-perspective code…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-09 00:13
Coding & development
40,275 results
injective-ai-cost-optimization
Optimize AI API costs for agentic trading bots. Covers Anthropic token cost tracking, web search cost management, CoinGecko/Massive.com data sourcing, shared…
planet-bulk-download
Download PlanetScope imagery at scale (hundreds to 100k+ AOIs) via the Planet Python SDK v2. Covers search/activate/extract phases, COG /vsicurl/ vs Orders…
transformers
Loading and using pretrained models with Hugging Face Transformers. Use when working with pretrained models from the Hub, running inference with Pipeline API,…
plan
Breaks down feature requests into sequential, implementable tasks with code changes under 50 lines each. Use when planning new features, refactors, or…
creating-rules
Creates Claude Code rules (.claude/rules/*.md) with YAML frontmatter and path-specific scoping. Use when creating project rules, coding standards, or…
040-planning-plan-mode
Use when creating a plan using Plan model and enhancing structured design plans in Cursor Plan mode for Java implementations. Use when the user wants to create…
git-history-recon
Analyze git repository history to produce a codebase risk profile before code review. Probes repo size, runs 7 parallel git analysis pipelines (hotspots, bug…
plannotator-review
Open interactive code review for current changes using Plannotator UI
guidewire-common-errors
Debug and fix common Guidewire InsuranceSuite errors. Use when encountering API errors, Gosu exceptions, validation failures, or integration issues in…
guidewire-cost-tuning
Optimize Guidewire Cloud costs including license management, resource allocation, API usage optimization, and cloud infrastructure right-sizing. Trigger with…
guidewire-multi-env-setup
Configure multi-environment setup for Guidewire InsuranceSuite including development, staging, and production environments with proper isolation and promotion…
speech
Use when the user asks for text-to-speech narration or voiceover, accessibility reads, audio prompts, or batch speech generation via the OpenAI Audio API; run…
vertex-ai-api-dev
Guides the usage of Gemini API on Google Cloud Vertex AI with the Gen AI SDK. Use when the user asks about using Gemini in an enterprise environment or…
create-pr
Drafts, opens, or updates a pull request (GitHub) or merge request (GitLab) that follows the repo's own conventions (base branch, title shape, template, ticket…
submit-changes
Drafts, opens, or updates a pull request (GitHub) or merge request (GitLab) that follows the repo's own conventions (base branch, title shape, template, ticket…
spring-boot-best-practices
Coding standards and architectural discipline for Spring Boot 3 + Java 21 + MyBatis Plus projects. Covers layered dependencies, Chinese cryptographic algorithms SM2/SM3/SM4, MyBatis Plus entities and primary key strategies, multi-dialect database migrations, R/RList/RPage response wrappers, DTO responsibility boundaries, authentication framework selection (Spring Security /…
implement-spec
Implement the result of /to-spec and /to-tickets in code.
pr
Use when writing a PR body.
retro
Conduct a retrospective on a coding session.
designing-tidy-r-functions
Use when designing R function APIs, reviewing R code for design issues, writing functions for R packages, or evaluating argument ordering and naming decisions.…
next-browser
Debug Next.js/React pages using the @vercel/next-browser CLI. Suitable for tasks that need to use shell commands to obtain browser-state information, including page opening and navigation, screenshots, React component tree, props, hooks, PPR shell, Cache Components, errors, logs, network requests, …
citation-system
Invoke when the system indicates a need to design citation formats, information traceability mechanisms, or source attribution systems. Applicable to scenarios such as document question answering, retrieval-augmented generation (RAG), code citation, and browser assistance where users need to trace information sources. Not applicable to purely creative output (such as stories or poetry), not applicable to common-sense question answering that requires no source tracing, and not applicable to injection defense (although both involve content trustworthiness).
coding-agent
Coding assistant using agent CLIs (Codex, Claude Code) for reviews, refactoring, and implementation. Primary mode: direct CLI with session resume and…