Skip to main content
Jeden Skill in Manus ausführen
mit einem Klick
liush2yuxjtu
GitHub-Creator-Profil

liush2yuxjtu

Repository-Ansicht von 79 gesammelten Skills in 25 GitHub-Repositories.

gesammelte Skills
79
Repositories
25
aktualisiert
2026-07-15
Hier werden die Top 8 Repositories angezeigt; die vollständige Repository-Liste folgt darunter.
Repository-Explorer

Repositories und repräsentative Skills

explore-data
Datenwissenschaftler

Profile and explore a dataset to understand its shape, quality, and patterns. Use when encountering a new table or file, checking null rates and column distributions, spotting data quality issues like duplicates or suspicious values, or deciding which dimensions and metrics to analyze.

2026-07-11
validate-data
Softwareentwickler

QA an analysis before sharing -- methodology, accuracy, and bias checks. Use when reviewing an analysis before a stakeholder presentation, spot-checking calculations and aggregation logic, verifying a SQL query's results look right, or assessing whether conclusions are actually supported by the data.

2026-07-11
write-query
Softwareentwickler

Write optimized SQL for your dialect with best practices. Use when translating a natural-language data need into SQL, building a multi-CTE query with joins and aggregations, optimizing a query against a large partitioned table, or getting dialect-specific syntax for Snowflake, BigQuery, Postgres, etc.

2026-07-11
statistical-analysis
Datenwissenschaftler

Apply statistical methods including descriptive stats, trend analysis, outlier detection, and hypothesis testing. Use when analyzing distributions, testing for significance, detecting anomalies, computing correlations, or interpreting statistical results.

2026-07-11
data-context-extractor
Softwareentwickler

Generate or improve a company-specific data analysis skill by extracting tribal knowledge from analysts. BOOTSTRAP MODE - Triggers: "Create a data context skill", "Set up data analysis for our warehouse", "Help me create a skill for our database", "Generate a data skill for [company]" → Discovers schemas, asks key questions, generates initial skill with reference files ITERATION MODE - Triggers: "Add context about [domain]", "The skill needs more info about [topic]", "Update the data skill with [metrics/tables/terminology]", "Improve the [domain] reference" → Loads existing skill, asks targeted questions, appends/updates reference files Use when data analysts want Claude to understand their company's specific data warehouse, terminology, metrics definitions, and common query patterns.

2026-07-11
build-dashboard
Webentwickler

Build an interactive HTML dashboard with charts, filters, and tables. Use when creating an executive overview with KPI cards, turning query results into a shareable self-contained report, building a team monitoring snapshot, or needing multiple charts with filters in one browser-openable file.

2026-07-11
sql-queries
Softwareentwickler

Write correct, performant SQL across all major data warehouse dialects (Snowflake, BigQuery, Databricks, PostgreSQL, etc.). Use when writing queries, optimizing slow SQL, translating between dialects, or building complex analytical queries with CTEs, window functions, or aggregations.

2026-07-11
html-artifacts
Softwareentwickler

Produce a self-contained HTML artifact instead of a markdown document when the request is for content that benefits from spatial layout, color, real diagrams, interactivity, or a round-trip editor. Use this skill aggressively whenever the user asks for a "doc," "writeup," "plan," "spec," "report," "explainer," "summary," "comparison," "review," "PR description," "mockup," "diagram," "flowchart," "deck," "slides," "status update," "post-mortem," "incident report," "playground," or a one-off "editor" or "tool" for triaging/reordering/tuning anything — even if they don't explicitly say "HTML" or "artifact." Also trigger when the user asks Claude to "explain," "summarize," "compare," "explore options for," "brainstorm directions for," or "walk through" a non-trivial topic. Stay in markdown only for short conversational replies, code-only outputs, terminal-style command answers, and content that's genuinely just a few sentences.

2026-07-11
Zeigt die Top 8 von 34 gesammelten Skills in diesem Repository.
insight-flush
Softwareentwickler

Use this skill when the user wants to force-finalize the in-flight session buffer immediately, instead of waiting for the 30-min idle threshold. Triggered by "/insight-flush", "flush insights", "push my insight buffer now", "publish lessons now", "force-sync the mirror". Reads the local buffer, runs the two-layer PII filter, and pushes any surviving lessons to the mirror repo.

2026-04-25
insight-rate
Softwareentwickler

Use this skill when the user (or another Claude instance) wants to rate a previously injected insight as good / bad / irrelevant for the current task. Triggered by "/insight-rate", "rate this insight", "this lesson saved me time", "this lesson was wrong", "thumbs up the insight", or similar phrasings. Writes a single rating record to the per-repo ratings.jsonl. Used at Gate 1 to compute "≥1 cross-engineer relevant retrieval / week" and detect drift in topic-tag inference.

2026-04-25
insight-help
Softwareentwickler

Use this skill when the user has just installed the insights-share plugin and asks any onboarding question — "what next", "where is the README", "how do I use this plugin", "/insight-help", "show me the insights-share quickstart", "what does this plugin do for me". The skill prints a compact onboarding card pointing to the README on disk, the four slash commands, statusline wiring, and the optional self-host stub server.

2026-04-25
insight-add
Softwareentwickler

Use this skill when a Claude instance has just hit, fixed, or learned about a non-obvious trap that another teammate (or another Claude instance) would benefit from knowing. Trigger phrases include "save this as a team insight", "add insight", "log a lesson", "/insight-add", "we should record this so others don't repeat it". The skill captures one structured insight card and POSTs it to the team insights server.

2026-04-25
insight-install
Softwareentwickler

Use this skill when a Claude instance is bootstrapping a new repository or onboarding a project that is not yet wired into the team insights system. Trigger phrases include "install insights into this repo", "wire insights-share here", "/insight-install", "wire this repo so teammates inherit insights". The skill idempotently appends a force-install block to the project CLAUDE.md (append-only) and verifies hook registration so any future Claude instance entering this repo is guided to install the plugin.

2026-04-25
insight-search
Softwareentwickler

Use this skill when a Claude instance wants to manually look up team insights before acting on a non-trivial task — e.g. before changing build configuration, touching auth, writing a migration, or wiring a hook. Trigger phrases include "search insights", "any team lesson on X", "/insight-search", "have we hit this before". The skill performs a keyword search against the team insights server and renders the top hits as a compact briefing.

2026-04-25
insight-server
Softwareentwickler

Use this skill when a Claude instance needs to start, stop, ping, or run the nightly automation cycle of the self-host insights server. Trigger phrases include "start insights server", "ping the insights server", "run nightly insights sync", "/insight-server start|stop|ping|nightly", "is the team insights backend up". The skill is a thin operator over the self-host server stub documented in references/self-host.md; the production backend is intentionally deferred.

2026-04-25
insights-share-server
Netzwerk- und Computersystemadministratoren

管理员专用:启动 LAN insightsd 守护进程(--start 默认)或打开 control dashboard kanban 做在线 CRUD(--ui)。触发词:启动 wiki 服务器 / 开 wiki / 打开 wiki 管理面板 / wiki kanban。仅分配给管理员。

2026-04-22
insights-share-server
Netzwerk- und Computersystemadministratoren

管理员专用:启动 LAN insightsd 守护进程(--start 默认)或打开 control dashboard kanban 做在线 CRUD(--ui)。触发词:启动 wiki 服务器 / 开 wiki / 打开 wiki 管理面板 / wiki kanban。仅分配给管理员。

2026-04-22
insights-share
Softwareentwickler

局域网 insights-share 静默回灌技能。当 Bob 在 Claude Code 里写代码、提问或排障时,自动从 LAN insightsd 守护进程拉取相关 insight 卡片,缓存到 ~/.cache/insights-share/,并通过 Stop hook 把命中卡片以 additionalContext 形式悄悄注入下一轮回复。仅在用户无感的前提下工作,不打断对话流。触发场景:任何技术问题、生产事故、配置调优、性能 debug。

2026-04-21
register-session
Netzwerk- und Computersystemadministratoren

注册/创建一个 tmux 实机测试 session,建立固定日志镜像,让 agent 能直接读取用户实际操作终端的输出。当用户说 "/register-session"、"/new-session"、"注册一下 session"、"注册实机 session"、"建一个实机 tmux"、"让你能看到我这个终端"、"把我的终端绑上"、"register tmux session"、"pop out a new terminal window" 时触发。

2026-04-19
pre-mr
Softwareentwickler

MR 提交前 4 段式自检 + 默认就地修复:QA → e2e 默认改源码(不 defer 到 follow-up MR)→ diff 展示(代码全量 / 文档仅摘要)→ 冲突默认按 safe-category + intent 自动解(撞模糊才升用户)→ MR body 引用了未跟踪的视觉证据(mp4 / webm / PNG / 草稿 workflow)并对该证据做"能不能 让 reviewer 一眼接受"的质量复盘。**默认行为是动手修,不是报告遗留**。 Use this skill whenever the user says any of: "pre-mr", "/pre-mr", "pre-MR", "prepare merge request", "准备 MR", "MR 前检查", "开 MR 前", "ready to push", "ship MR", "合并前检查", "MR checklist", "push 前自检", "MR 提交流程", "before I push", "before opening MR", or asks to verify a branch is ready to merge into origin/main with diff, conflict, visual-evidence, and evidence-quality gates. Do NOT trigger for plain "diff" or "merge" requests — those are too broad and don't imply the full 4-gate pre-MR pipeline.

2026-06-11
submit-mr
Softwareentwickler

一条龙把"当前 git worktree → 远端分支 → 已开 MR"的最后一公里跑完: worktree 探测 → 委托 /pre-mr 4 段自检 → fetch + rebase(默认拉齐) → zh-CN/视觉证据补齐(默认 ≥ 0.30 安全垫) → push --force-with-lease → **GitLab 协议探活(HTTPS → HTTP → OAuth 三段退化)** → 创建 MR → 输出 web_url + 用户待办 + 把产物留在 .agent/pr-assets/ 便于 recall。 **默认行为是动手把 MR 开出来,不是报告剩余项**。 Use this skill whenever the user says any of: "/submit-mr", "submit mr", "open the MR", "ship it", "ship MR", "push my branch", "push 我这条分支", "提个 MR", "提 MR", "搞定 MR", "把这条分支提了", "准备合并", "合并准备", "把分支推上去", "开 MR", "发 MR", "push and open MR", "create the merge request", or asks to take a clean worktree all the way to an opened GitLab MR in one shot. Special-case for winchannel internal GitLab (gitlab008.its.winchannel.net) where HTTPS API often returns EOF and the skill silently falls back to HTTP + $GITLAB_TOKEN. Do NOT trigger for plain "pre-mr"/"准备 MR" — that's the 4-gate self-check sub-step, delegate to /pre-mr instead. Do NOT trigger for "commit"/"git push" with no MR intent.

2026-06-11
worktree-qa
Softwarequalitätssicherungsanalysten und -tester

Full QA loop for the current worktree: diff → host → test → handoff. Runs `git diff` to enumerate every new/changed feature, launches the per-worktree dev stack via `/worktree-self-host`, exercises all features (old + new) through `/playwright-cli`, generates a test report, and finally pops the app open in Chrome for manual inspection. Use this skill whenever the user says "QA this worktree", "test my changes", "smoke test the worktree", "run full QA", "test everything end-to-end", "playtest my app", or mentions wanting to both auto-test AND hand-test their current worktree changes — even if they don't say "worktree" explicitly. Also trigger when the user wants a diff-to-test pipeline, or says something like "diff → host → test → let me try it".

2026-06-11
12 von 25 Repositories angezeigt