Progressive-disclosure instructions an agent loads on demand. Cheap until invoked, which is why the per-session figure on each card is usually two digits.
Retrieve and curate durable, project-aware knowledge through the Global Agent Memory MCP server. Use before substantial planning, implementation, refactoring, debugging, handoff preparation, or investigation when prior decisions, exact identifiers, recurring errors, verified solutions, preferences, or conventions may…
Before running a risky shell command, check it with Sigil's assess and refuse anything Sigil would block. Use whenever you are about to execute a destructive, privileged, or unfamiliar command.
★not rated 15 15d agoA✓ AI review46 tokens
originalApache-2.0
Run or resume the Sprint Loops Book v2 workflow when the user explicitly invokes $sprint-loops or directly asks to start, continue, resume, or run a sprint loop. Do not use it for ordinary documentation work or merely because a docs directory exists.
System diagnostics using osquery. Use when asked about CPU usage, memory consumption, network connections, running processes, disk I/O, fan speeds, temperatures, or system security. Triggers: "why is my computer slow", "what's using memory", "what's using CPU", "network connections", "suspicious processes", "system…
Transcribe multilingual audio/video meetings locally into speaker-labeled Markdown with word times and voice clips. Uses fast Russian GigaAM or multilingual WhisperX, Nemotron diarization across languages with pyannote fallback, and optional validated host-AI punctuation. Rename speakers after identification. Use for…
Use this skill whenever the user wants to work with FileMaker layout XML. This includes generating paste-ready layout object XML (fmxmlsnippet type LayoutObjectList) from descriptions, reviewing layout XML for silent paste-handler failures, or analysing Save as XML layout exports. Trigger any time the user mentions…
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
Expert Apache Airflow assistance covering DAG authoring, TaskFlow API (@task), operators, sensors, and Celery/Kubernetes executors. Use when orchestrating complex data engineering and ML pipelines.
Write and publish a new blog post for the skillfold site (site/blog/). Use whenever asked to write a blog post, cover a news story about the agent tooling ecosystem, announce a feature rollout, publish the next post from the queue, or when the weekly blog automation runs. Covers the full pipeline - finding the story…
Run the standard markdown review loop end-to-end with the mdxg-redline CLI: send a markdown document to a human reviewer, wait (via Bash polling) for the feedback.json they export, then apply their location-aware inline comments back into the markdown and revise it. Always use this skill when the user wants…
Modern Typst typesetting patterns for documents, slides, and academic writing. Use this skill when writing Typst markup (.typ files), creating document templates, building slide decks with Quarto, or debugging Typst compilation issues. Covers content blocks, styling, math typesetting, tables, figures, custom…
Monitor and control ProxyClawd MITM proxy for Claude Code. Inspect intercepted API requests, view conversation history, and send messages through the proxy.
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
Use this skill to generate well-branded interfaces and assets for Cogni Work (cogni-work.ai / insight-wave), either for production or throwaway prototypes, mocks, decks, and design artifacts. Contains the essential design guidelines, colors, type, fonts, assets, and UI kit components needed to prototype or ship…
Put an EU AI Act Article 14 human-oversight checkpoint and an Article 12 auditable record in front of a high-risk tool call. Use before an agent runs a consequential or irreversible action (writing to a clinical/genomic database, submitting a record to a regulator, moving money, deleting data, anything a human should…
Use this skill whenever the user wants to write hooks, headlines, ad openers, email subject lines, video titles, or attention-grabbing copy for selling digital products (PDF guides, templates, printables, mini-courses, ebooks priced $17-$47). Trigger when user says "write me a hook", "give me headlines", "grab…
Research Colosseum project histories, competitors, ideas, program questions, and tool choices backed by project use, and give feedback on the user's own Colosseum projects, drafts, submissions and team. Use it for any crypto or onchain startup or product idea, even when Colosseum isn't named, and whenever the user…
Query Garmin Connect fitness and health data including activities, athlete stats, sleep, heart rate, stress, and body battery. Use when the user asks about Garmin data, workouts, training, or health metrics.
Read and modify Twenty CRM data — people, companies, opportunities, tasks, notes, custom objects — on any Twenty deployment (self-hosted or cloud). Includes a one-time setup that connects the instance and stores the API token. Use when the user wants to look up, search, filter, count, create, update, or delete CRM…
CVE-oriented multi-agent code audit system. Use when user provides a git repository URL for vulnerability discovery with the goal of submitting CVEs. This skill orchestrates subagents to find exploitable vulnerabilities (RCE, SQLi, Auth Bypass, etc.), write weaponized POCs, and generate CVE-ready reports. ALWAYS use…
Create, review, and run typed TypeScript agents and workflows with Rig. Use when writing Rig programs, generating runnable rig markdown fences, defining agent schemas and prompt intents, or configuring Rig engines and addons.
Emit privacy-safe receipts for context selection, deferral, hydration, compaction, pruning, delegation, usage attribution, and boundary handoffs.
★not rated 15 3mo agoA33 tokens
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: