obsidian-bases
Create and edit Obsidian Bases (.base files) with views, filters, formulas, and summaries. Use when working with .base files, creating database-like views of notes, or when the user mentions Bases, table views, card views, filters, or formulas in Obsidian.
mr-pr-summary
Draft concise, accurate merge request and pull request summaries from a branch diff. Use when the user asks to "create MR summary", "create PR summary", "write merge request description", "summarize this branch", "summarize the diff for review", or wants a paste-ready overview of changes, testing, and notable risks based on the current branch, target branch, commits, and local uncommitted edits.
json-canvas
Create and edit JSON Canvas files (.canvas) with nodes, edges, groups, and connections. Use when working with .canvas files, creating visual canvases, mind maps, flowcharts, or when the user mentions Canvas files in Obsidian.
ekoen-frontend-code-review
Production-grade code review for the eKoEN frontend codebase. Use when asked to review, audit, inspect, or harden eKoEN React/Next.js frontend code, pages, components, hooks, API clients, or state layers for bugs, performance bottlenecks, TypeScript safety issues, request inefficiency, state-management risks, memory leaks, rendering regressions, error-handling gaps, duplication, or maintainability problems, especially when a structured severity-ranked report with code locations, root causes, suggested fixes, and example refactors is required.
ekoen-backend-sql-performance-review
Review skill for eKoEN backend database-access performance. Use when asked to review, audit, inspect, or harden TypeScript backend changes that touch MikroORM, repositories, services, controllers, cron jobs, or SQL-facing logic, especially to catch N+1 queries, per-item lookups inside loops, repeated findOne/find patterns, wasteful hydration, duplicate reads, broad populate usage, app-side filtering of large result sets, or raw SQL escapes before merge.
defuddle
Extract clean markdown content from web pages using Defuddle CLI, removing clutter and navigation to save tokens. Use instead of WebFetch when the user provides a URL to read or analyze, for online documentation, articles, blog posts, or any standard web page. Do NOT use for URLs ending in .md — those are already markdown, use WebFetch directly.
codex-cli-subagent-transport
Use only when native subagent execution is unavailable and the caller needs one deterministic Codex CLI run with repo-local artifacts and a manifest-based result contract.
plugin-creator
Create and scaffold plugin directories for Codex with a required `.codex-plugin/plugin.json`, optional plugin folders/files, and baseline placeholders you can edit before publishing or testing. Use when Codex needs to create a new local plugin, add optional plugin structure, or generate or update repo-root `.agents/plugins/marketplace.json` entries for plugin ordering and availability metadata.
openai-docs
Use when the user asks how to build with OpenAI products or APIs and needs up-to-date official documentation with citations, help choosing the latest model for a use case, or explicit GPT-5.4 upgrade and prompt-upgrade guidance; prioritize OpenAI docs MCP tools, use bundled references only as helper context, and restrict any fallback browsing to official OpenAI domains.
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output should be a bitmap asset rather than repo-native code or vector. Do not use when the task is better handled by editing existing SVG/vector/code-native assets, extending an established icon or logo system, or building the visual directly in HTML/CSS/canvas.
spec-tasker
Use when `plan.md` is ready but `tasks.md` is missing, vague, oversized, unordered, or not verifiable.
spec-planner
Use when `spec.md` is ready but `plan.md` is missing, incomplete, risky, or not execution-ready.
spec-handoff
Prepare structured spec handoff state for paused, blocked, resumed, or transferred feature work. Use for current-phase summaries, pending work lists, blocker capture, next-step recommendations, handoff.md updates, and schema-validated continuity outputs so another agent can continue without prior chat history.
dida-cli
Manage Dida365 (滴答清单) tasks, projects, habits, focus records, tags, and countdowns from the terminal. Use this skill whenever the user asks to interact with Dida/滴答清单, manage tasks, list today's tasks, create/complete/delete tasks or projects, track habits, record pomodoro sessions, check reminders, or mention dida/dida365/dida-cli. Wraps the @suibiji/dida-cli npm package.
web-design-engineer
Build high-quality visual Web artifacts with HTML/CSS/JavaScript/React. Use whenever the user wants a visual, interactive, or presentational front-end deliverable: web pages, landing pages, dashboards, interactive prototypes, UI mockups, HTML slide decks, CSS/JS animations, data visualizations, design systems, or critique of visual work. Includes fact verification, brand asset handling, design direction for vague requests, and 5-dimension critique. Not for pure backend, CLI, data-processing, or non-visual tasks.
tavily-search
|
skill-creator
Create, improve, or debug Agent Skills for Pi and other Agent Skills-compatible harnesses. Use this skill whenever the user asks to make a new skill, turn a workflow into a reusable skill, install or adapt a Claude/Codex/Agent Skill, improve skill triggering, write SKILL.md frontmatter, add skill resources/scripts/evals, or troubleshoot why a skill is not loading or not triggering.
security-review
AI-powered codebase security scanner that reasons about code like a security researcher — tracing data flows, understanding component interactions, and catching vulnerabilities that pattern-matching tools miss. Use this skill when asked to scan code for security vulnerabilities, find bugs, check for SQL injection, XSS, command injection, exposed API keys, hardcoded secrets, insecure dependencies, access control issues, or any request like "is my code secure?", "review for security issues", "audit this codebase", or "check for vulnerabilities". Covers injection flaws, authentication and access control bugs, secrets exposure, weak cryptography, insecure dependencies, and business logic issues across JavaScript, TypeScript, Python, Java, PHP, Go, Ruby, and Rust.
python-dev
Guide Python development using the user's preferred stack and conventions. Use this skill whenever writing, reviewing, refactoring, testing, or designing Python code, especially when choosing libraries for logging, terminal output, environment config, notifications, dates/times, HTTP clients, dataframes, CLIs, validation, or tests.
playwright-cli
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
plan-task
Plan complex tasks and write structured plan documents to the project's plans/ directory. Use this skill whenever the user asks to plan a task, create a plan, design a solution, make a plan, analyze a requirement before implementation, or says "先规划一下", "先出个方案", "帮我设计", "分析一下怎么做". Also trigger proactively when the user describes a large, ambiguous, or multi-step task that would benefit from upfront planning before any code is written. This skill operates in planning-only mode — it reads code, runs verification commands, and produces plan documents, but MUST NOT write or modify any production code or configuration files.
obsidian-markdown
Create and edit Obsidian Flavored Markdown with wikilinks, embeds, callouts, properties, and other Obsidian-specific syntax. Use when working with .md files in Obsidian, or when the user mentions wikilinks, callouts, frontmatter, tags, embeds, or Obsidian notes.
obsidian-cli
Interact with Obsidian vaults using the Obsidian CLI to read, create, search, and manage notes, tasks, properties, and more. Also supports plugin and theme development with commands to reload plugins, run JavaScript, capture errors, take screenshots, and inspect the DOM. Use when the user asks to interact with their Obsidian vault, manage notes, search vault content, perform vault operations from the command line, or develop and debug Obsidian plugins and themes.
image-bg-transparent
Make solid or pastel image backgrounds transparent using ImageMagick corner flood fill. Use this skill whenever the user asks to remove an image background, make a background transparent,去背景,抠图,背景变透明, or needs to post-process a generated image that has a solid/pastel background into a transparent PNG.
grill-me
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
gpt-image-2
面向 GPT Image 2 的图像生成 / 编辑技能。作为 Host-Native 或 Advisor 提示词工程 Skill 使用：宿主有图像工具时，把渲染好的 prompt 交给宿主 Agent 自带工具出图；宿主无图像工具时，退化为高质量 prompt 顾问。涵盖 18 大类、80+ 个结构化模板，覆盖海报 / UI / 产品 / 信息图 / 学术图 / 技术架构图 / 漫画 / 头像 / 流程板 / 电影分镜 / IP 周边 / 编辑工作流等场景。
code-review
Review code changes for correctness, maintainability, integration risk, tests, dependencies, and security-relevant regressions. Use this skill whenever the user asks for a code review, PR review, diff review, commit review, staged/working-tree review, or asks "review this", "check my changes", "look over this branch", or "before I merge". Produces evidence-cited findings with verification and concrete fixes.
commit
Generate a Conventional Commits message and create a git commit
redaction-tool
|
court-record-transcriber
|
software-architect
Architecture review using "A Philosophy of Software Design" principles. Modes: red-flags, depth, complexity, fcis, performance, split, comments, naming, consistency, tactical, review.
naming-reviewer
Expert code naming review and refactoring. Reviews variables, functions, and classes to improve readability and maintainability using master-level naming principles. Use when: (1) User asks to review naming/variable names in code, (2) User wants to improve code readability, (3) User requests naming suggestions or refactoring, (4) User mentions code quality or maintainability concerns related to naming, (5) User asks to apply best practices to naming
code-commenter
Add detailed comments explaining WHY code works, its context, edge cases, and performance implications. Use when user mentions "add comments", "document", "explain code", "improve readability", or "maintainability". Supports C++, Python, Java, JavaScript, Go, Rust, SQL.
pr-description
Generate comprehensive pull request descriptions that help reviewers understand code changes. Use when the user asks to "generate PR description", "create PR summary", "write PR intro", or needs help documenting their code changes for review. Analyzes git diffs or specified files to create structured descriptions covering why changes were made and what was implemented.
generate-feature-spec
Generates features_spec.txt files for use with auto-code extension mode. Analyzes existing codebase and creates structured feature specifications based on user requirements.
generate-spec
Generates app_spec.txt specification files from codebases. Use when you need to create specification documents, analyze code structure, document project architecture, or generate comprehensive project overviews in XML format.
update-pi
Update Pi to the latest release, only applying changes when versions drift (global CLI + ~/dotfiles/pi/agent deps).
websearch
Search the public web using the Exa-backed websearch tool. Use this when the user asks for up-to-date facts, external docs, release notes, APIs, or anything not reliably present in the local repo.
build-skill
Create effective skills for OpenCode agents. Load FIRST before writing any SKILL.md. Provides required format, naming conventions, progressive disclosure patterns, and validation. Use when building, reviewing, or debugging skills.
adr
Manage Architecture Decision Records and ADR-aligned development. Use when user says "we should use", "let's go with", asks "why did we choose X?", implements a feature that may have an ADR, updates ADR status, or needs to check alignment with existing decisions.
agents-md
How to write, audit and edit AGENTS.md files.
write-discoverable-code
|
writing-for-agents
Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.
prd-to-todos
Break a PRD into independently-grabbable file-backed todos using tracer-bullet vertical slices. Use when the user wants to convert a PRD into implementation tasks, create vertical-slice todos, or break down a PRD into work items.
to-tickets
Break a plan, spec, or the current conversation into a set of tracer-bullet tickets, each declaring its blocking edges, published to the configured tracker — edges as text in one file per ticket locally, or native blocking links on a real tracker.
wayfinder
Plan a huge chunk of work — more than one agent session can hold — as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.
to-spec
Turn the current conversation into a spec and publish it to the project issue tracker — no interview, just synthesis of what you've already discussed.
thermo-nuclear-code-quality-review
Run an extremely strict maintainability review for abstraction quality, giant files, and spaghetti-condition growth. Use for a thermo-nuclear code quality review, thermonuclear review, deep code quality audit, or especially harsh maintainability review.
terminal-control
Control and test terminal applications with the termctrl CLI by reading visible screen state, driving named live sessions, sending typed keyboard input, waiting for text, collecting explicit evidence, recording timelines, marking important moments, and exporting edited videos. Use when an agent must operate or verify a TUI, REPL, interactive CLI, shell process, OpenTUI application, or other terminal-backed workflow.
where
Locates where a feature, behavior, symbol, or concept is implemented in the codebase.
Page 1525 of 1708 · 85365 results
