codebase-design

Review a branch, PR, worktree, or implementation handoff against both repository standards and feature intent. Use for implementer self-review or independent review when the target repo may contain Spec Kit artifacts and repo-kit files; preserves separate Standards and Spec axes, fans Standards review out by changed layer, checks cross-layer dependency direction, and reports cited findings without editing code.

1 skill

对任意主题做深度、多来源、经交叉核查的调研,产出带引用、按置信度分级的报告。五阶段流水线:把问题分解成 4-8 个子问题 → 跨渠道(web/github/news/academic)并行 fan-out 调研 → 对每个发现做对抗式核查(证伪而非确认,发现者≠核查者)→ 交叉验证+圆桌综合、标注分歧 → 输出 HIGH/MEDIUM/LOW/CONTESTED 分级的引用报告。Provider-agnostic:同一份 skill 在 Claude Code、Kimi(kimi -p)、Codex(codex exec)三端都成立;fan-out 与核查阶段可跨模型互查(claude 的发现让 codex/kimi 证伪,反之亦然),对方模型作独立第二视角。当用户想「深度调研 / deep research / 全面调研 / 多角度调研 / research roundtable / 帮我把某主题查透并给带引用的报告」时使用。调用前:若问题欠具体(如「买什么车」却无预算/用途/地区),先问 2-3 个澄清问题收窄范围,再把澄清结果织进 args。

1 skill

Entry A of the Dual-Entry Design Flow: ingest, classify, and stockpile design inspirations, measured palettes, interaction/motion patterns, and video assets.

1 skill

howto skill

1 skill

面向日常学习、知识获取与好内容拆解沉淀的通用技能：支持「通道 A 主动求知（问题/概念 -> 快速多维检索四要素）」与「通道 B 素材拆解（视频总结/脚本/文章/URL -> 知识卡 + 制作技巧）」双通道输入，统一以「极简 TL;DR + 核心痛点问答（3–5 问）+ 立即可用清单 + 可选脚本/表达技巧拆解」直击痛点，并分类沉淀到 ~/Development/Personal/knowledge-vault/。

1 skill

TIA Idea Inbox 与 Global Goal Status Board：收集想法、提升 Goal、同步状态与 Task checklist。

1 skill

Use the JFrog Platform from Claude Code: Artifactory repos and artifacts, security findings and exposures, Catalog package safety and downloads, workflows across the SDLC, and platform administration.

7 skills · 1 MCP server · hooks

Drive the Superself `self` CLI: version control for a project's state (goals, decisions, work units, reports) kept outside the code repo, so a session reads context at start, reports with evidence, and the next session picks up where this one left off

1 skill

Gives Claude access to your real Git and project context: commits, branches, pull requests, and issues across every repo you work in. Works with GitHub, GitLab, Azure DevOps, Bitbucket, and Jira.

14 bundled product skills with 19 Python tools: product-skills fork-orchestrator with continuous-discovery loop (deterministic 16-lane router, Torres cadence tracker, OST linter, /cs-product + /cs-grill-product + /cs-product-loop), product manager toolkit (RICE, PRDs), product strategist, UX researcher, UI design system, competitive teardown, landing page generator, SaaS scaffolder, product analytics, experiment designer, product discovery, roadmap communicator, spec-to-repo, design-qa (UI finish gate: inert controls, missing states, rendered WCAG 2.2 checks). Companion standalone plugins: agile-product-owner, code-to-prd, apple-hig-expert, research-summarizer, design-qa.

14 skills · 3 commands · 1 agent · hooks

Agent-Native Research Artifact (ARA) tooling: compile any research input (paper, repo, notes) into a structured artifact, record session provenance as a post-task epilogue, and run Seal Level 2 epistemic review. Use when ingesting research into a falsifiable, agent-traversable artifact, capturing how a research project actually evolved, or auditing an ARA for evidence-claim alignment.

98 skills

Execute Hugging Face Hub operations using the hf CLI. Install additional Hugging Face skills, discover agent resources, download models/datasets, upload files, manage repos, and run cloud compute jobs.

1 skill