文件操作
文件系统与批量文件任务
update-skills
microsoft
Create or update repository skills and instructions when major learnings are discovered during a session. Use when the user says "learn!", when a significant pattern or pitfall is identified, or when reusable domain knowledge should be captured for future sessions.
init
microsoft
Generate or update chat customization files for AI coding agents
feedback-learning
microsoft
Classify and record explicit corrective feedback without turning skills or instructions into append-only knowledge dumps.
customizations-in-the-agent-host
microsoft
Architecture and hard-won debugging lessons for customization enablement (plugins, MCP servers, agents, skills, instructions) in the agent host. Use when changing how customizations are discovered, published, enabled/disabled, or handed to a provider SDK; when a customization shows the wrong enabled state in the UI; or when a disabled MCP server or plugin is still reaching the model.
task-management
anthropics
Simple task management using a shared TASKS.md file. Reference this when the user asks about their tasks, wants to add/complete tasks, or needs help tracking commitments.
spa-routes
lobehub
'LobeHub SPA route architecture. Use when editing src/routes, src/features delegation, desktop/mobile/popup router configs, .desktop variants, route segments, redirects, or new pages.'
onboard
wesammustafa
Explains this repository's shared Claude Code setup to a new teammate, covering what is committed and shared, what stays personal, and what the team-kit plugin adds. Use when someone asks how the team's Claude Code setup works or what they get by cloning the repository.
CLAUDE.md Review
wesammustafa
Audit a CLAUDE.md file for the patterns that actually degrade Claude Code's output — vagueness, unnamed files, stale facts, and bloat. Use when asked to review, audit, improve, shrink, or fix a CLAUDE.md, and when a project's results feel inconsistent or Claude keeps rediscovering the same context.
sherpa-onnx-tts
openclaw
"Local text-to-speech via sherpa-onnx (offline, no cloud)"
lfg
brycewang-stanford
Full autonomous research workflow — brainstorm, plan, implement, review, and document
Getting Started with Research Superpowers
brycewang-stanford
Introduction to literature search & review skills - systematic paper finding, screening, extraction, and citation traversal
compile-latex
brycewang-stanford
Compile a Beamer LaTeX slide deck with XeLaTeX (3 passes + bibtex). Use when compiling lecture slides.
slide-excellence
brycewang-stanford
Multi-agent slide review (visual, pedagogy, proofreading). Use for comprehensive quality check before milestones.
techdebt
brycewang-stanford
Find and fix technical debt including duplicated code, dead code, outdated patterns, and code smells. Run at the end of sessions to clean up.
workflows:compound
brycewang-stanford
Document a recently solved research problem to compound methodological knowledge
stata-data-cleaning
brycewang-stanford
Clean and transform messy data in Stata with reproducible workflows
wacli
openclaw
"Send third-party WhatsApp messages or sync/search WhatsApp history via wacli, not normal active chats."
feishu-wiki
openclaw
Feishu knowledge-base navigation workflows. Activate when the user mentions a knowledge base, wiki, or wiki link.
plugin-write
oh-my-dsh
Use when creating a DeepSeek Harness plugin, choosing public names for a new external DSH plugin, validating a dsh-plugin.naming.json manifest, checking reviewed central registrations for known conflicts, or creating a workspace package inside the deepseek-harness repository. Covers the full workflow from repository-mode and plugin-form selection through separate offline naming validation, optional online registry lookup, and package validation. Routes tool, LLM adapter, hook, service, and configuration forms to their corresponding references while separating upstream-monorepo rules from external-package rules. For an existing plugin crossing Harness versions, use this Skill's built-in version-adaptation workflow before implementing against the exact target contract.
porting-another-repository
dyoshikawa
Plan how to port a feature, configuration, or implementation from this repository into another repository. Analyzes the source feature here and the target repo's conventions, then writes a multi-file porting plan (overview, source analysis, target analysis, plan, diff) to tmp/porting-another-repository-{YYYYMMDD-HHmm}/*.md for the user to review and apply manually.
hindsight-coding-agent
vectorize-io
How this machine's Hindsight coding-agent memory works — the plugin behind the 🧠 banner. Use when the user says "store/remember this in hindsight", asks what the memory/knowledge pages are, wants to configure per-repo memory (disable, rename banks, git depth), or something memory-related looks broken.
copywriting
supabase
Write or audit UI copy (buttons, labels, empty states, error messages, tooltips, form text) anywhere in the monorepo. Load it before shipping or reviewing any user-facing text — including when copy is incidental to the task, like a new feature that adds buttons, toasts, dialogs, or validation messages.
full-output-enforcement
Leonxlnx
Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.
studio-e2e-tests
supabase
Write and run Playwright E2E tests for Supabase Studio (e2e/studio).