2K skills · sorted by relevance
Turn five collected UI references into five original landing pages with distinct brands, copy, and imagery. Each page gets its own Codex task and workspace, with build checks, a source commit, and private deployment through Sites.
Build and maintain Mintlify documentation sites by writing pages, organizing navigation, and creating API references. The skill guides edits to site settings, use of built-in components, consistency with existing content, and checks for broken links and build errors.
Establish reusable design guidelines by reviewing project files and asking about unresolved preferences. The skill records the audience, brand personality, visual direction, and design principles in a project file for future sessions.
Create reusable slash commands, prompts invoked by typing a slash, for Claude Code. The skill explains Markdown structure, arguments, file references, tool permissions, and plugin integration so recurring tasks can follow a defined workflow.
Search saved Zotero papers by keywords or meaning, read selected PDF pages, and organize references. Use shell commands to update bibliographic details, tags, notes, and annotations, add items by identifier, and export bibliographies.
Find academic papers through Google Scholar and PubMed, retrieve publication details from identifiers, and build BibTeX reference files. Check author and publication information, detect duplicates, and standardize formatting before using references in a manuscript.
Create and maintain Mintlify documentation sites with pages, navigation, built-in components, and API references. Follow the existing site’s structure and writing style, then check internal links and validate the documentation build before submitting changes.
Convert LaTeX papers and reports into Typst documents, including structure, formatting, equations, figures, tables, citations, and cross-references. Reference guides and symbol mappings help translate individual commands or migrate an entire article.
Guides an end-to-end data-warehouse migration to Amazon Redshift — discovery, schema/SQL/stored-procedure/macro/script conversion, data migration, validation, performance comparison, and reporting. Source-routed via `references/<source>/`; Teradata (Vantage) is the supported source; additional sources are added as their own `references/<source>/` sets. Text-only knowledge (no executable code) — the AI generates all execution at runtime. Applies when a user wants to migrate Teradata to Amazon Redshift, convert Teradata DDL/SQL/stored procedures/macros/BTEQ to Redshift/RSQL, or assess Teradata-to-Redshift migration complexity. Applies only to migrations targeting Amazon Redshift; migrations to other platforms (Snowflake, BigQuery, Databricks, etc.) are out of scope regardless of source. Does not cover general Redshift administration, performance tuning, or troubleshooting of existing Redshift clusters (no migration involved), or sources not listed under references/.
The English summary is being prepared. Showing the original description.
Reference for paired-reversal handling on GL batch tapes: an RV row whose ref-trace points at an earlier row cancels BOTH legs (the RV and the row it references) — but ONLY when the two value-dates fall within the shop's reversal settlement window; an RV that references a too-old posting is NOT a cancellation and posts one-sided. Useful when the posting tape carries a reference-trace column alongside reversal codes and the running balance is off by twice the reversal magnitude, or by a whole leg on stale references.
The English summary is being prepared. Showing the original description.
Tabular Editor documentation search and configuration file guidance (.tmuo, Preferences.json, UiPreferences.json, Layouts.json). Automatically invoke when the user asks about "TE docs", "Tabular Editor features", "TE3 preferences", ".tmuo files", "workspace database settings", "DAX editor settings", "per-model TE3 configuration", or needs to search Tabular Editor documentation for how-to guidance.
The English summary is being prepared. Showing the original description.
Guide for interpreting ResolveProjectReferences time in MSBuild performance summaries. Activate when ResolveProjectReferences appears as the most expensive target and developers are trying to optimize it directly. Explains that the reported time includes wait time for dependent project builds and is misleading. Guides users to focus on task self-time instead. Do not activate for general build performance -- use build-perf-diagnostics instead.
The English summary is being prepared. Showing the original description.
Citation-integrity forensics: is every reference real, correctly attributed, and used in a context the cited work actually supports? Catches hallucinated references (no paper at the claimed arXiv id/DOI/venue, fabricated authors/year), metadata drift (wrong year/venue/version), and wrong-context citations (a real paper cited for a claim it never makes — or argues against). A hot zone for machine-generated papers. Decidable at L0 (text + canonical sources). Span-anchored to the evidence ledger (claims.json); the executor gathers canonical facts (DBLP / arXiv / DOI), then one FRESH cross-model thread per cited key proposes findings; reviewer != adjudicator. Emits citation-forensics.findings.json; NEVER computes the verdict. Triggers: "citation forensics", "check the references", "hallucinated citations", "wrong-context citation", "verify references", "引用核对".
The English summary is being prepared. Showing the original description.
First-run conversational setup wizard for marketing-cli. Use when /cmo detects no populated brand files and no cmo-preferences.md, when the user just installed marketing-cli for the first time, or when they say things like "set up marketing", "start marketing", "marketing wizard", "I just installed marketing-cli", "onboard me", "first time", "initial setup". Asks 3 sharp questions (identity, posture, distribution preferences), records the answers to brand/cmo-preferences.md, then hands off to /cmo's foundation flow which spawns 3 research agents in parallel. The user never has to type /mktg-setup directly — /cmo auto-routes here on first run.
The English summary is being prepared. Showing the original description.
Dev-only check that a drafted spec for THIS baseline repo won't ship dev-tree references to consumer installs. Catches three failure modes — shipped SKILL.md prose that references paths under `src/`, `tests/`, `scripts/`, `obj/` as runtime invocations (in ```bash fences``` OR `inline backticks`, plus shipped `.mjs`/`.js`/`.sh`/`.py` helper-file imports); new Python helpers added under `.claude/skills/<slug>/` (shipped helpers must be `.sh` or `.mjs`/`.js` going forward); and imports of modules that aren't in `obj/template/.claude/manifest.json` (consumer won't have the file). The aggregate scanner (`scan-shipped-skills.mjs`) walks only baseline-owned skill dirs (via `owner: baseline` frontmatter) at top level — `references/` and other subdirs are documentation, not runtime. BLOCKER findings hard-block implementation entry; ADVISORY surfaces but doesn't block. Read-only — surfaces a punch list; maintainer edits the spec and re-runs until CLEAN.
The English summary is being prepared. Showing the original description.
當使用者要為新客戶規劃或撰寫全新的 Brand Guideline、品牌手冊、視覺識別規範時使用。互動教練模式：一次只問一題完成 intake，全部問完後產出由知識圖譜推理驅動的 Plan 供確認，使用者確認後才 Build 並寫入 clients/ 下的 blueprint、index.yaml 與 note.md 初稿。Plan 階段以 Design Strategy 推理鏈（產業 → 品牌類型 → 商業問題 → 匹配決策卡 → 架構）運作，並引用 references/research/decision_patterns.yaml、contexts、modules、archetypes、module_graph 與 references/docs/*.profile.yaml 的證據。本 skill 亦涵蓋兩個延伸能力（見 references/）：分析既有 guideline PDF（design-guideline-researcher）、把分析升級成決策卡（design-strategy-extractor）。
The English summary is being prepared. Showing the original description.
Guide for interpreting ResolveProjectReferences time in MSBuild performance summaries. Only activate in MSBuild/.NET build context. Activate when ResolveProjectReferences appears as the most expensive target and developers are trying to optimize it directly. Explains that the reported time includes wait time for dependent project builds and is misleading. Guides users to focus on task self-time instead. Do not activate for general build performance -- use build-perf-diagnostics instead.
The English summary is being prepared. Showing the original description.
Requires OFOX_API_KEY — create one at https://app.ofox.ai, plus a publicly reachable reference video the user is authorized to use. Use when a user has a rough 3D white-model, clay, wireframe, blockout, previs, or animatic clip and wants a finished visual treatment that preserves its shot order, cut timing, camera framing, spatial layout, and motion directions. Distinguishes that structure-preserving job from a continuation beginning at the reference's final state. Do not use for two still endpoints (keyframe-animation), for appending and locally joining a new ending (video-extend-edit), or when still-image references must be combined with the video in one request — first/last-frame anchors conflict with video references in the shipped core, while mixed image/video references are untested.
The English summary is being prepared. Showing the original description.
Rebuild OpenClaw release changelogs from Git history, the recorded code changes. Group changes by user impact, preserve issue and pull request references and contributor credits, and verify the notes against the release history and published GitHub release text.
Guides multi-step web tasks with the OpenClaw browser tool, including login checks, tab reuse, and page inspection before actions. It also covers recovery when element references expire or browser operations time out.
Add a model provider to OpenClaw and verify it with a real response. The skill validates configuration, keeps credentials in environment or file references, and reports test results and any default model changes.
Create or revise agent skills by defining when they run, what they produce, and how their files are organized. Validate SKILL.md settings, resource links, and changed helper scripts before completing the work.
Summarize an ongoing conversation and launch a fresh background agent to continue the work. The handoff includes the next focus, references to existing documents, and suggested skills, with sensitive information removed.
Build a project-specific ECC installation plan from evidence in its code and configuration. Sort skills, rules, commands, and hooks into everyday components and references available when needed, then verify that the applied setup matches the project.