搜索

PythonReactSEOPDF

数据与 AI AI 技能

发现 数据与 AI 相关 Skills,比较来源仓库和用途,查看适合你工作流的技能说明。

分类目录: 数据与 AI

显示第 23,689–23,712 个,共 83,104 个

数据与 AI 清除筛选

全部技能

GitHub

everyrow-sdk

futuresearch

Helps write Python code using the everyrow SDK for AI-powered data processing - transforming, deduping, merging, ranking, and screening dataframes with natural language instructions

GitHub

zig-expert

srdjan

Write idiomatic Zig code following the Zen of Zig philosophy. Use for systems programming with Zig (.zig files), covering manual memory management with allocators, error unions and explicit error handling, comp...

GitHub

assemblyscript

sablier-labs

This skill should be used when working with AssemblyScript code in the graph/ directory, writing subgraph mappings, event handlers, or store operations. Triggers: "AssemblyScript", "subgraph", "graph/", mapping...

GitHub

researching

desplega-ai

Comprehensive codebase research skill. Documents codebase as-is by spawning parallel sub-agents and synthesizing findings into research documents.

GitHub

implementing

desplega-ai

Plan implementation skill. Executes approved technical plans phase by phase with verification checkpoints.

GitHub

file-review-install

desplega-ai

Install the file-review tool. Use when user needs to install file-review on a new machine or asks how to set it up.

GitHub

wts-expert

desplega-ai

Git worktree management expert for @desplega.ai/wts. Use when the user asks about git worktrees, wts commands, worktree workflows, or wants help managing multiple branches simultaneously.

GitHub

process-review

desplega-ai

Process review comments in a file after user finishes reviewing in file-review GUI. Extracts HTML comment markers, guides Claude through addressing each comment interactively, and removes resolved markers.

GitHub

planning

desplega-ai

Implementation planning skill. Creates detailed technical plans through interactive research and iteration.

GitHub

swarm-expert

desplega-ai

Multi-agent coordination expert for agent-swarm MCP. Use when the user asks about swarm coordination, delegating tasks to agents, checking swarm status, agent messaging, or managing multi-agent workflows.

GitHub

spar

bdsqqq

adversarial review via spawned antithesis agent. use to prune false positives from EXISTING findings. NOT for discovery or when claim is verifiable against single source.

GitHub

document

bdsqqq

apply documentation philosophy — explain why, not what. use for jsdocs, READMEs, inline comments.

GitHub

tmux

bdsqqq

manage background processes in tmux windows. use when running dev servers, build watchers, or any long-running process that shouldn't block the agent. check window before spawning.

GitHub

rounds

bdsqqq

iterate with spawned agents until stable. use for verification with BOUNDED scope and explicit exit criteria. NOT for generating opinions to reconcile.

GitHub

dig

bdsqqq

systematic investigation and debugging methodology. hypothesis-driven analysis with verification agents. use for incident response, codebase archaeology, dependency mapping, root cause analysis, or any investig...

GitHub

report

bdsqqq

message coordinator as a spawned agent. use when you were spawned by coordinate/spawn and need to report progress, completion, or blockers back to the coordinator.

GitHub

write

bdsqqq

prose style guide. use when your output includes ANYTHING other than a code snippet. use during conversation, and every time you write to a file, commit, PR. enforces academish voice: supported claims, precise...

GitHub

coordinate

bdsqqq

orchestrate multiple amp agents with bidirectional tmux communication. use for multi-hour autonomous runs with INDEPENDENT parallel tasks. NOT for review courts or generating opinions to reconcile.

GitHub

review

bdsqqq

epistemic standards for evaluation and analysis. load before reviewing code, debugging, reporting findings, or any task where claims must be defensible. enforces trace-or-delete, confidence labeling, falsificat...

GitHub

shepherd

bdsqqq

watchdog for autonomous runs that will exhaust context and need handoffs. supervises tmux agents, respawns on death, orchestrates handoffs. NOT for single-session tasks.

GitHub

remember

bdsqqq

record context that would help in future sessions. use after learning something, discovering a gotcha, or making a decision worth preserving. test: would a future agent starting fresh benefit from knowing this?

GitHub

amp-voice

bdsqqq

write in amp's voice — direct, technical, opinionated, honest. use for technical writing that should feel authoritative without being academic. derived from analysis of amp's content patterns.

GitHub

spawn

bdsqqq

spawn parallel amp agents in tmux with thread linkage. use for INDEPENDENT side-quests discovered during main work. NOT for spawning multiple agents to review/evaluate the same thing.

GitHub

rust-quality

reown-com

Writes high-quality Rust code following yttrium project standards. Use when working on Rust codebases, creating new modules, or reviewing Rust code quality.

默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库,同一仓库的多个技能可能共享相同数值;它反映仓库关注度,不代表单个技能的安装量或质量评分。

更多筛选

热度筛选

热门标签