creating-implementation-plan
Creates an implementation plan AND task breakdown from a feature spec by consuming design artifacts. Produces plan.md with implementation steps, inline task…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-14 00:15
Coding & development
41,027 results
implementing-code
Executes a batch of implementation tasks with TDD workflow, source-anchored rewrite for behavioral fidelity, guideline-based code transformation, and full…
project-recon
Zero-dependency shell recon for any code repository — detect languages, count LOC, and report project scale. Pure POSIX find/wc or PowerShell, no Python or…
flatten-fake-layers
Find and flatten "fake layer" indirection in a TypeScript codebase — functions with exactly one caller that only forward, reshape, or inject dependencies and…
flame-templates
Game type templates for Flame Engine - RPG, Platformer, Roguelike starter code
tooluniverse-share-computer
Share tools that live on this computer (the user's own Python function, script or notebook code, a model, a program they already run, or ToolUniverse's…
coding conventions
Automatically apply standard coding conventions when writing or modifying code. Use this skill when working with Python, TypeScript, JavaScript, Go, PHP, or…
explaining-code
Explains code with visual diagrams and analogies. Use when explaining how code works, teaching about a codebase, or when the user asks "how does this work?"
pr-flow
Take an issue through to a PR in this repo and close it out after merge. Use when asked to open, create or submit a PR; when naming a branch; when signing off…
project-structure
Find where code lives in this repo's seven servers and decide where a new file goes. Use when choosing the file or directory for a new tool, resource, prompt,…
ai-ml-principal-engineer
Principal/Senior-level AI/ML playbook for production machine learning systems, LLM-enabled backends, model serving, training pipelines, evaluation discipline,…
api-design-coach
api-design-coach skill for API design decisions. Use when a developer is designing a public API, an internal service contract, or a module interface and needs…
complexity-cop
complexity-cop skill for over-engineering detection and simplicity enforcement. Use when a proposed solution, architecture, or implementation introduces…
refactor-guide
refactor-guide skill for refactoring assessment and code smell identification. Use when a developer wants to improve the structure of existing code but should…
sentry
Use when the user asks to inspect Sentry issues or events, summarize recent production errors, or pull basic Sentry health data via the Sentry API; perform…
repo-elegance-review
Audit software repositories for elegance/cleanliness/organization and explain why they feel messy or polished. Use when a user asks if a repo is…
orchestrator
Use when the user asks how to approach building a feature or says 'build X', 'implement X', 'add feature X' without naming a phase ('SDD it', 'spec-driven…
gen-rust
Sync Rust implementation with Python changes (exclude UI/login) by reviewing recent changes, mapping modules, porting logic, and updating tests.
connect
Connect to MotherDuck from any application. Use when setting up database connectivity via the Postgres endpoint (recommended), pg_duckdb, native DuckDB API, or…
sandock-community
Read, answer and post on the Sandock community forum at community.sandock.ai through its /api/v1/community REST API. Lists categories and posts, reads a thread…
improve-codebase-architecture
Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
roblox-dev
Expert Roblox game development companion for Luau scripting, Roblox Studio, and MCP integration. Covers full-lifecycle development: architecture, scripting,…
pp-passage
A contemplative daily reading practice — open book APIs as your library, real public-domain passages to sit with, and a reading journal that's yours. Trigger…
ajiang-feature
Develop new features or improve existing ones: implement around the actions the user needs to complete, and verify results from the actual entry point.