Minimal MDA source demonstrating relationship-graph footnotes and metadata.mda.* MDA-extended fields. Use as a reference fixture when learning the MDA source format.
// Auto-stub for source build
Move records from an external source (CSV, JSON, SQL dump, or API response) into a live FileMaker solution via OData. Reads the source data, maps source columns to FM fields with type coercion, gets developer approval on the mapping, then executes the migration with error tracking. Use when the developer asks to "migrate data", "import records", "move data into FileMaker", "load CSV", or "import JSON".
CLI to download npm packages, PyPI packages, crates, or GitHub repo source code into node_modules/.gitchamber/ for analysis. Use when you need to read a package's inner workings, documentation, examples, or source code. Alternative to opensrc that stores in node_modules/ for zero-config gitignore/vitest/tsc compatibility. After fetching, analyze files with grep, read, and other tools.
Publishes and updates remote Canvas pages on Acquia Source via Source MCP — images, props, layout; page JSON does not CLI-sync to Source. --- # Acquia Source — Canvas pages via Source MCP ## When this applies Use this skill when **all** of the following hold: 1. The target is an **Acquia Source** Drupal/Canvas site (see hostname signal and **`CANVAS_SITE_URL`** in [`AGENTS.md`](../../../AGENTS.md)). 2. The work is **Canvas pages** on the **remote** site (create page, place components, update layout/props, publish)—not local-only Workbench preview. ## Do not use Canvas CLI for remote pages **`canvas push` / `canvas pull` do not support syncing page JSON to/from the remote Acquia Source environment today.** Do not instruct users to rely on CLI page sync for that tenant. - **Components:** Continue to use the Canvas CLI (`npx canvas push`) and [`canvas-component-push`](../canvas-component-push/SKILL.md) for pushing **JavaScript components** when the user asks to push component source. - **Pages:** Use **Source MCP tools** on the configured server. ## Images and media (pages do not CLI-sync) Because **`canvas push` / `canvas pull` do not sync page JSON** to Acquia Source, **nothing in repo `pages/*.json` automatically provisions files or image props on the remote site.** Local page specs may use HTTPS placeholders, `placehold.co`, or example paths so **Workbench** renders; those values are not reliable as the remote source of truth. Treat image handling as a **remote-only** concern: ### What to do instead 1. **Discover the prop shape** — Each component’s `component.yml` defines how image fields are modeled (`image`, `heroImage`, nested objects, etc.). Keep that shape when updating instances on the server. 2. **Obtain Drupal-hosted media** — Prefer assets that live on the Source site: - **Upload** — Use Source MCP (`create_media` + signed upload URL pattern, etc.—read the live tool schema). See **Phase A5** in [`acquia-source-site-build`](../acquia-source-site-build/SKILL
Fetch, scrape, or download football data from any source. Also handles API key setup and credential management. Use when the user wants to get data from StatsBomb, Opta, FBref, Understat, SportMonks, Wyscout, Kaggle, or any football data source. Also use when they ask about API keys, authentication, setting up access to a provider, or what data is available free vs paid.
Register a git URL as a team-profile source so nyann can periodically sync and expose its profiles under a namespace. TRIGGER when the user says "add a team profile source", "register a team profile source", "set up team profiles from <url>", "wire up our team's shared profiles at <repo>", "add profile source named X at <url>", "install team profiles from <git repo>", "/nyann:add-team-source". Do NOT trigger on "sync team profiles now" (that's `sync-team-profiles` — the pull operation). Do NOT trigger on "save my setup as a profile" (that's `learn-profile` — writes to user root, not a team source). Do NOT trigger on generic "add a repo" or "add a remote" — those are git operations unrelated to profile distribution. --- # add-team-source Wraps `bin/add-team-source.sh`. Updates `~/.claude/nyann/config.json` to declare a new team-profile source. Idempotent — passing the same `--name` updates the entry in place. ## 1. Collect inputs - **`--name <id>`** — required. Short slug, `^[a-z0-9][a-z0-9-]*$`. Will also become the namespace prefix for team profiles (e.g. `platform-team/base` when name is `platform-team`). When the user gives a name with spaces or caps, propose a slug and confirm. - **`--url <git-url>`** — required. Any URL git can clone (https://, git@, file:// for testing). - **`--ref <branch-or-tag>`** — default `main`. Override when the team pins a specific branch or tag. - **`--interval <hours>`** — default `24`. How often `sync-team-profiles` will re-pull from this source without `--force`. Decrease only when the user says "we update these often" or similar. ## 2. Pre-flight - Config path defaults to `~/.claude/nyann/config.json`. Override only when the user explicitly names a different user root. - The backend upserts on `--name` collision. Warn the user if they're replacing an existing source with a different URL — that's usually unintentional. Read current config first if unsure. ## 3. Invoke ``` bin/add-team-source.sh \ --name <id> \ --url <git-url> \ [--
Generate accurate BibTeX entries from authoritative sources (DBLP, ACL Anthology, PMLR, CrossRef, arXiv). Use this skill whenever the user needs a citation, BibTeX entry, bibliography fix, or wants to look up where/whether a paper was published — even if they don't explicitly say "BibTeX." Triggers on: paper titles, arXiv IDs, DOIs, DBLP keys, "cite this paper", "add to references", reference list verification, or any academic citation task. --- # make-bib `$ARGUMENTS` — accepts `arxiv:ID`, `doi:ID`, `dblp:KEY`, `openreview:ID`, a title in quotes, or an abbreviation. For background on how bibliographic sources work and their reliability characteristics, see `${CLAUDE_SKILL_DIR}/citation-guide.md`. ## Principles Each principle exists because a specific class of citation error is common and hard to catch after the fact. **Ask when uncertain.** Citations involve judgment calls — which of two similar titles is the right paper, whether something is workshop or main track, what venue a paper belongs to. Guessing wrong means the user silently gets a wrong citation in their manuscript. Use `AskUserQuestion` for any ambiguous case: multiple candidates, unclear venue, conflicting metadata across sources. **One source per entry.** Every field in a BibTeX entry (title, authors, year, venue) should come from the same source. Mixing metadata across sources — even "just the author order" from a different database — creates entries where no single source can verify the whole record. If sources disagree on a field, use the chosen source as-is or ask the user. **Discovery tools are not citation sources.** Semantic Scholar and Google Scholar optimize for finding papers, not for metadata accuracy. Their venue names, dates, and author formatting frequently contain errors. Use them to locate papers and collect external IDs, then get the actual BibTeX from authoritative sources downstream. **Honest representation.** Citing a preprint as a published paper (or vice versa) is academic misrep
skill-sample/ ├─ SKILL.md ⭐ Required: skill entry doc (purpose / usage / examples / deps) ├─ manifest.sample.json ⭐ Recommended: machine-readable metadata (index / validation / autofill) ├─ LICENSE.sample ⭐ Recommended: license & scope (open source / restriction / commercial) ├─ scripts/ │ └─ example-run.py ✅ Runnable example script for quick verification ├─ assets/ │ ├─ example-formatting-guide.md 🧩 Output conventions: layout / structure / style │ └─ example-template.tex 🧩 Templates: quickly generate standardized output └─ references/ 🧩 Knowledge base: methods / guides / best practices ├─ example-ref-structure.md 🧩 Structure reference ├─ example-ref-analysis.md 🧩 Analysis reference └─ example-ref-visuals.md 🧩 Visual reference
More Agent Skills specs Anthropic docs: https://agentskills.io/home
├─ ⭐ Required: YAML Frontmatter (must be at top) │ ├─ ⭐ name : unique skill name, follow naming convention │ └─ ⭐ description : include trigger keywords for matching │ ├─ ✅ Optional: Frontmatter extension fields │ ├─ ✅ license : license identifier │ ├─ ✅ compatibility : runtime constraints when needed │ ├─ ✅ metadata : key-value fields (author/version/source_url...) │ └─ 🧩 allowed-tools : tool whitelist (experimental) │ └─ ✅ Recommended: Markdown body (progressive disclosure) ├─ ✅ Overview / Purpose ├─ ✅ When to use ├─ ✅ Step-by-step ├─ ✅ Inputs / Outputs ├─ ✅ Examples ├─ 🧩 Files & References ├─ 🧩 Edge cases ├─ 🧩 Troubleshooting └─ 🧩 Safety notes
Skill files are scattered across GitHub and communities, difficult to search, and hard to evaluate. SkillWink organizes open-source skills into a searchable, filterable library you can directly download and use.
We provide keyword search, version updates, multi-metric ranking (downloads / likes / comments / updates), and open SKILL.md standards. You can also discuss usage and improvements on skill detail pages.
Quick Start:
Import/download skills (.zip/.skill), then place locally:
~/.claude/skills/ (Claude Code)
~/.codex/skills/ (Codex CLI)
One SKILL.md can be reused across tools.
Everything you need to know: what skills are, how they work, how to find/import them, and how to contribute.
A skill is a reusable capability package, usually including SKILL.md (purpose/IO/how-to) and optional scripts/templates/examples.
Think of it as a plugin playbook + resource bundle for AI assistants/toolchains.
Skills use progressive disclosure: load brief metadata first, load full docs only when needed, then execute by guidance.
This keeps agents lightweight while preserving enough context for complex tasks.
Use these three together:
Note: file size for all methods should be within 10MB.
Typical paths (may vary by local setup):
One SKILL.md can usually be reused across tools.
Yes. Most skills are standardized docs + assets, so they can be reused where format is supported.
Example: retrieval + writing + automation scripts as one workflow.
Some skills come from public GitHub repositories and some are uploaded by SkillWink creators. Always review code before installing and own your security decisions.
Most common reasons:
We try to avoid that. Use ranking + comments to surface better skills:
