> Analyze a competitor's website, positioning, pricing, and weaknesses. Find the gaps.
Skills(SKILL.md)は、AIエージェント(Claude Code、Cursor、Codexなど)に特定の能力を追加するための設定ファイルです。
詳しく見る →> Analyze a competitor's website, positioning, pricing, and weaknesses. Find the gaps.
> The operating system for agent swarms.
Audit your business workflows and find automation opportunities
A collection of AI agent skills for small-business bookkeeping. Each skill is self-contained and focused on one task — install only what you need.
Match recorded transactions against bank and credit card statements to verify the books are accurate, complete, and audit-ready.
Assign every transaction to the correct expense category so it flows to the right line on a tax return, produces accurate financial statements, and survives an audit.
A repeatable month-end close process for small businesses that produces reliable financial statements and catches errors before they compound.
Organize financial records into tax-ready reports that an accountant can use directly or that the business owner can use to file accurately.
deal-screener
investment-summary
property-report
sop-writer
>
Insert handwritten electronic signatures into Word documents (.doc/.docx). Provides a canvas-based signature pad for hand-drawing, parses documents to locate signature fields, inserts signature images, and fills in dates/names. Use when the user mentions electronic signature, handwritten signature, sign a document, e-sign, digital signing, or filling signature fields in Word files.
Monitor and protect your email sender reputation. Use when deliverability drops, investigating spam placement, checking blocklists, or recovering from reputation damage.
Use when choosing between multi-agent architecture patterns. Five patterns compared.
Use when choosing between RAG, fine-tuning, and prompting approaches. Decision tree for the right technique.
Use when choosing between coordination patterns for multi-agent systems. Stigmergic vs centralised comparison.
Use this skill whenever a user asks for OSINT dorks, Google dorks, GHDB queries, Shodan filters, GitHub code search dorks, search operators, or exposed asset discovery. Prioritize this workflow even if the user does not explicitly mention GHDB.
Feed this agent a data file (appointment export, referral data, financial data) and it runs ALL relevant analyses automatically — no questions, pure insights. Produces a comprehensive operational intelligence report covering capacity, revenue, variation, demand patterns, workforce health, and anomalies. Use with 3+ months of appointment data for meaningful results.
Estimate immune and stromal cell composition from bulk RNA-seq using multiple algorithms. Wraps CIBERSORT, quanTIseq, EPIC, xCell, MCP-counter, TIMER, and ESTIMATE through the immunedeconv unified int
Use this skill when working with Iron Claw. Triggers when user mentions Iron Claw or imports from it.
Use this skill when working with n8n. Triggers when user mentions n8n or imports from it.
Strategic session-end preservation. Captures decisions, discoveries, and state that the automatic hooks miss.
Run the DesignVault `/execute` lane from one approved implementation plan. Use when Codex needs to read a plan, run preflight, execute phases in order, verify results with the narrowest valid evidence, write back changed wiki truth, and finish with one execution log.
Create and upgrade agent skills for distribution across Claude Code, Codex, Gemini CLI, and OpenClaw. Every decision accounts for end users who receive the skill package, not just the author.
Audit and repair GitHub repository health with Ceratops defaults, using scripted live checks first for machine-checkable GitHub settings.
Ship local repository changes through GitHub and any relevant artifact registry with Ceratops defaults, using scripted live repo and PR checks before merge decisions.
Drive substantial tasks through staged contingent execution with Ceratops defaults. Use when Codex should diagnose first, prefer the simplest standard fix, advance only to the next justified stage, ask before complex or high-maintenance solutions, and finish with a risk-based closure pass.
Create a minimal copy-paste prompt for spinning a newly discovered side task into another thread. Use when Codex should ignore most of the original task and capture only the side task's origin, conclusion, current objective, minimal refs, and next step.
Implement Linkerd service mesh patterns for lightweight, security-focused service mesh deployments. Use when setting up Linkerd, configuring traffic policies, or implementing zero-trust networking with minimal overhead.
Add Slack channel integration via Chat SDK.
Add Microsoft Teams channel integration via Chat SDK.
Add new capabilities or modify NanoClaw behavior. Use when user wants to add channels (Telegram, Slack, email input), change triggers, add integrations, modify the router, or make any other customizations. This is an interactive skill that asks questions to understand what the user wants.
Diffusion-based molecular docking. Predict protein-ligand binding poses from PDB/SMILES, confidence scores, virtual screening, for structure-based drug design. Not for affinity prediction.
Medicinal chemistry filters. Apply drug-likeness rules (Lipinski, Veber), PAINS filters, structural alerts, complexity metrics, for compound prioritization and library filtering.
RNA velocity analysis with scVelo. Estimate cell state transitions from unspliced/spliced mRNA dynamics, infer trajectory directions, compute latent time, and identify driver genes in single-cell RNA-seq data. Complements Scanpy/scVI-tools for trajectory inference.
trace-claude-code
Problem-solving strategies for numerical integration in numerical methods
Search Tool Hierarchy
Calculate SaaS revenue, retention, and growth metrics. Use when diagnosing momentum, churn, expansion, or product-market-fit signals.
Turn raw PM content into a compliant, publish-ready skill. Use when creating or updating a repo skill without breaking standards.
Break a large story or epic into smaller deliverable stories using proven split patterns. Use when backlog items are too big for estimation, sequencing, or independent release.
Automate Google Calendar events, scheduling, availability checks, and attendee management via Rube MCP (Composio). Create events, find free slots, manage attendees, and list calendars programmatically.
Batch-categorize uncategorized transactions by clustering similar ones and applying categories in bulk.
Ship parcels via any configured carrier — MyParcel, Sendcloud, DHL Parcel NL, PostNL, DPD, UPS, FedEx. Auto-selects the first carrier whose credentials are configured, or pass --carrier <name> to override. Verbs: ship, label, track, list, carriers.
Run all remaining phases autonomously — discuss→plan→execute per phase
Diagnose planning directory health and optionally repair issues
Insert urgent work as decimal phase (e.g., 72.1) between existing phases
Surface Claude's assumptions about a phase approach before planning