All categories
Data & Analytics
Data analysis, BI, visualization, datasets, statistics, and ML workflows
- 12,625
- 527
Security grades appear on each card once the skill has been scanned. Newly imported skills may briefly show without a grade until the backfill job runs.
Open in full browserBrowse data & analytics skills
Showing 97–120 of 12,625 skills
- SongseeAudio spectrograms/features (mel, chroma, MFCC) via CLI.Votes: 0GitHub stars: 2
- StorageUse to persist key-value metadata in IDA databases via netnode_kv.Votes: 0GitHub stars: 2
- Headless Ghidra DiscoveryP3 phase skill for Headless Ghidra metadata discovery. Use after P2, or after a P4 batch exposes missing context, to enrich function names, signatures, types, constants, strings, and hotpath metadata in YAML before serialized CLI apply.Votes: 0GitHub stars: 2
- Ctf Ai MlCTF AI/ML 攻击技术。当挑战涉及 AI 模型攻击、对抗样本生成、模型提取、Prompt 注入/越狱、LoRA 权重操纵、LLM Token 走私、成员推理攻击、训练数据投毒、神经网络分析时使用。覆盖 FGSM/PGD/C&W 对抗攻击、模型反演、模型权重扰动还原、LLM 工具链劫持、上下文窗口操纵等 AI 安全全链路攻防技术Votes: 0GitHub stars: 2
- Build DashboardBuild a source-backed dashboard or monitoring view with clear metrics, filters, visual hierarchy, definitions, refresh context, and QA.Votes: 0GitHub stars: 2
- Bigquery GraphSkill for Graph Query Language (GQL) or SQL/PGQ queries against a property graph. Includes path finding, multi-hop traversal, topological connection, shortest path, node reachability, edge connectivity, and semantic graph queries.Votes: 0GitHub stars: 2
- Analyzing Insights Across TeamsAnalyze PostHog insights, dashboards, or teams beyond the current project by querying the prod Postgres replicas synced into the dogfood data warehouse (US project 2, "PostHog App + Website"). Use when asked to analyze insights across all teams or projects, another team's insights, or fleet-wide insight/dashboard usage — cases where `system.insights` only returns the current project's rows and the agent would otherwise report the data as inaccessible. Covers the synced table names for US and ...Votes: 0GitHub stars: 2
- Analyze Data QualityAssess whether structured data, query results, dashboards, or analytical evidence are trustworthy enough to use. Use when the task is to check data quality, reconcile conflicting sources or metric definitions, or decide whether evidence is safe to cite.Votes: 0GitHub stars: 2
- Tun VerifyProve a built dashboard actually renders and works before it is shared — opens it in a real browser from a file:// URL, checks it is self-contained, confirms charts and interactivity work, checks the size budget, and produces a screenshot for review. Use before publishing any dashboard, or when checking whether a dashboard file is broken or safe to share.Votes: 0GitHub stars: 2
- Tun PublishPublish a built standalone dashboard to SharePoint, OneDrive or Atlassian Artifacts, confirm who can see it, produce a shareable link or a Confluence embed, and draft the announcement. Use when someone wants to share, publish, distribute, or send out a dashboard, asks where to put it so colleagues can open it, or wants it in Artifacts or on a Confluence page.Votes: 0GitHub stars: 2
- Tun ProcessDraw a process as a swimlane diagram in one self-contained HTML file: who does what, in which order, where it branches, and where it goes wrong. Use when someone wants a process diagram, flowchart, swimlane or workflow drawn, wants to map how work really flows between people or teams, or wants to show where a process should improve.Votes: 0GitHub stars: 2
- Tun Powerbi EscapeGet a report out of Power BI and turn it into a standalone interactive dashboard that anyone can open — no licence, no workspace, no capacity. Use when someone wants to move, replace, retire or escape a Power BI report, is frustrated with licence or sharing friction, or asks whether a report could just be a file.Votes: 0GitHub stars: 2
- Tun NewBuild a new standalone interactive dashboard from a data file (Excel, CSV, JSON, or a query result). Produces a single self-contained HTML file that can be shared through SharePoint or OneDrive with no Power BI licence, no workspace, and no admin approval. Use when someone wants a dashboard, a report, charts from a spreadsheet, or to share data interactively.Votes: 0GitHub stars: 2
- Tun HelpFigure out which dashboard skill fits a situation, and what it will cost in approvals and effort. Use when someone wants to share data interactively but does not know where to start, asks whether this can replace a Power BI report, or asks what is possible with dashboards in SharePoint, OneDrive, Confluence or Atlassian Artifacts.Votes: 0GitHub stars: 2
- Tun For CommunicatorsExplain this project's vocabulary (self-contained file, paired mode, sidecar file, tenant, preview, row level, provenance) to a communications adviser, using analogies from communications work. Translate an incoming technical message before answering it, keep a running glossary, and ask which level is unclear. Use when writing to or for a communications adviser, a press officer or an editor, when someone says 'skip the explanation', or when a technical sender's message needs to be made answer...Votes: 0GitHub stars: 2
- Tun FeedbackRecord feedback (tilbakemelding) or an idea (forslag) about a Tún skill or a built dashboard to a local log, and offer to file it as an issue on the public Tún repository. Use when the user says "this was wrong", "feedback", "tilbakemelding", "det funket ikke", "the dashboard looks wrong", "I have an idea", "forslag", "it would be nice if", or when any tun-* skill finishes. Also covers the --feedback-to build flag that puts a "Gi tilbakemelding" link inside an artefact.Votes: 0GitHub stars: 2
- Tun DataRefresh the data in an existing standalone dashboard, or add a new data source to it. Converts Excel to a usable format, re-extracts from the source, and rebuilds the file in place so existing share links keep working. Use when dashboard numbers are stale, someone asks to update or refresh a dashboard, or wants to point it at different data.Votes: 0GitHub stars: 2
- Writing For AgentsWriting documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.Votes: 0GitHub stars: 2
- Magnus ReviewRun an adversarial review of a PR, branch, or large diff through two senior-engineer lenses — Magnus (correctness: falsify the author's story, trace every finding through the actual code with file:line evidence) and Linus Torvalds (code & architecture: data structures over code, wrong coupling, interfaces and surfaces, useless helpers, lying names, never break user space). Verdict-first, honest severity, verified strengths listed alongside findings, and a closing pattern note. Use when the us...Votes: 0GitHub stars: 2
- HotshotFull change-to-reviewable-PR pipeline under one name — 'use hotshot' or 'implement this with hotshot'. Drive a change the user described in chat (bug, feature, refactor, wording, tooling) end to end: understand, implement, verify with whatever gate the repo documents, run the magnus-review loop and fix until it relents, run simplify, commit to a typed branch, push, open the PR. Repo-agnostic: it discovers the build/test/verify commands, the base branch and the forge rather than assuming them....Votes: 0GitHub stars: 2
- Method WriteDrafts, revises, and audits evidence-bound manuscripts, sections, abstracts, and reviewer responses with claim provenance. Use when scientific prose must be written or revised (entry point).Votes: 0GitHub stars: 3
- Method WorktreeCreates an isolated git worktree for a new branch or an existing branch, PR, or commit, after checking for existing isolation. Use when analysis code needs isolated work.Votes: 0GitHub stars: 3
- Method WorkflowShows the methodsmith study lifecycle for the current project and recommends the next safe skill. Use when the user asks what to run next or wants lifecycle status.Votes: 0GitHub stars: 3
- Method WorkExecutes a data-science implementation or analysis plan with task tracking, tests, SAP traceability, and a real-data gate. Use when the user asks to execute a plan.Votes: 0GitHub stars: 3