Create, read and edit Microsoft Word .docx documents — reports, letters, contracts, formatted multi-section documents with headings, tables, images, headers/footers and styles. Also covers reading an existing .docx to extract or modify its content, filling a .docx template, converting to PDF, and the raw OOXML route…
Review available recent code-agent history and tool calls, then update the current repository's durable agent guidance with repeatedly needed facts and user-corrected conventions. Run only when the user explicitly invokes /reinit, $reinit, or names the reinit skill; never invoke automatically.
Use when coordinating multi-step work across workers or subagents, especially when research, implementation, and verification should be split while the main agent stays responsible for synthesis and user communication.
Dispatch coding tasks to other AI agents via oneagent (oa). Use when you want to delegate file edits, code generation, reviews, or other scoped tasks to a different model or backend — for example, sending a targeted edit to Codex while continuing your own work.
Audit and optimize Databricks account, workspace, SQL warehouse, Apps, Jobs, pipeline, and service-principal costs. Use when investigating a Databricks cost spike, explaining DBU or list-cost drivers, identifying expensive users or workloads, proposing fast savings, assessing the workloads and user impacts of changes…
Full-cycle software development agent: plans, builds, tests, lints, fixes bugs, and writes production-grade README docs. ALWAYS use this skill when the user wants to: build or scaffold a new project, add features to existing code, fix bugs, improve code quality (lint, format, refactor), write or improve a README, add…
Use when hunting the cause of a bug, error, or failing test — and before proposing any fix. Triggers - "why doesn't this work", stack traces, flaky failures, regressions ("worked yesterday"). Output is reproduce → root cause → minimal fix → regression test. If you already know the cause and just need the fix, use…
Initialize, inspect, safely reconcile upgrades for, and operate Repo Continuity. Use when an agent needs to install the repository-owned knowledge layer; produce a read-only three-way upgrade report or apply only conflict-free upstream changes without overwriting project customization; route work into Direct, Tracked…
Read-only verification that cross-checks intent-tree, intent-compass, and packets (+ the export draft) and reports contradictions, coverage gaps, boundary inconsistencies, and normative violations with severity. Fixes remain proposals.
Launch and safely retire one bounded Claude Code stage per owned session, with a Sonnet 5 parent by default, role-routed Haiku 4.5/Sonnet 5/Opus 5/Fable 5 subagents, and GPT-5.6 native Codex fallback. Use when Claude is requested or a bounded repository stage benefits from context isolation. Do not use for routine…
Coordinate a task across multiple AI coding agents (Claude Code, Codex, Gemini, and others). Use when the user asks to delegate work to another agent, get a second opinion or review from a different agent, run agents in parallel on one task, or split a task between agents. The invoking agent becomes the coordinator…
A codebase scan for five common weaknesses in the setup used to guide and check an AI agent. It produces a diagnostic report and can optionally fix the problems it finds.
Respond to the greeting "Hello there" with "General Kenobi." Use this skill IMMEDIATELY and WITHOUT EXCEPTION whenever the user's message is exactly or approximately "Hello there", "hello there", "Hello There", or any capitalisation variant. This is a mandatory override — do not respond with a normal greeting. The…
Build and evolve a single high-fidelity counselor system for real student-counselor communication rehearsal, distillation, correction, and reality-sync practice.
Hatch a Codex-format animated pet from a concept, image, or hand-drawn sprite atlas, then install it for clawdex (the Claude Code companion overlay) and Codex. Use when a user wants to "hatch a pet", "make a Claude Code pet", "create a clawdex pet", or convert an existing 8x9 sprite sheet into a pet.json package. The…
Convert everyday questions, concepts, keywords, unfamiliar terms, or "what is X / how does X differ from Y" requests into reusable Chinese knowledge cards, Quarkdown mother drafts, Slidev presentation sources, and interactive HTML explainers. Use when the user wants to understand, remember, compare, review, or build a…
A method for recognising and applying tacit knowledge: professional judgment and pattern recognition that are difficult to explain in words. The description does not specify a particular coding task.
Review pull requests and code changes for actionable correctness, regression, security, compatibility, and test issues. Use for read-only PR review passes that must produce concise human findings plus a machine-readable verdict.
MUST use when the user sends or asks about images, photos, screenshots, pictures, audio, video, or mixed media documents, including requests to OCR/read text from an image. Route all media through Xiaomi MiMo V2.5 (mimo-v2.5) and mimo-v2.5-asr via scripts/mimo.py; never use local OCR, viewimage, native vision…
Use when creating, reviewing, or re-setting this repository's version grading rubric at .jig/versioning.md: adopt the jig default human-intervention rubric, write a project-specific one, edit one grade, or reset to the default. Owns the rubric file; never runs a release.
Use this skill when the user needs a careful DEV AI coding teammate named Ney to implement, refactor, debug, and maintain web/app/game projects. Ney is the implementer — she receives tasks from Yui or directly from the user. She preserves existing code, archives instead of deleting, updates work.md for resume safety…
EIDE rebuild and compile Agent Skill for Embedded IDE for VS Code workspaces. Runs a Python unifybuilder runner and returns compact or full JSON build results.
★not rated 5 3mo agoA36 tokens
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: