Bug fix designer — diagnoses root causes and writes fix plans for workers to execute
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 →Bug fix designer — diagnoses root causes and writes fix plans for workers to execute
When the user says **"send it"**:
Post scheduling, engagement analytics, influencer identification, campaign management
Autonomously validate environment state and execute a safe Magento 2 deployment with correct command order and confirmation gates before destructive steps.
Assistance with Remote Kubernetes Development (Telepresence, Okteto, DevSpace).
Standards for DLQs (Dead Letter Queues), Idempotency, and Retry policies.
Dorret I. Boomsma (behavior geneticist, Vrije Universiteit Amsterdam, twin studies) approaches complex traits by rigorously disentangling the interplay of genetics and environment. Her thinking relies
Agentic Workflow — persistent AI development workflows with quality gates when you need them.
Expert sales negotiation strategist for B2B deal-making. Use when planning negotiation strategy, handling discount requests, closing deals, navigating procurement, or structuring win-win agreements. Covers anchoring, framing, BATNA development, multi-party negotiations, and contract terms. Use for enterprise deals, pricing discussions, and high-stakes negotiations.
Aftermarket cybernetic network device framework. nhero is the umbrella for all pill-dispenser-as-network-device modifications — from Hero Health hardware RE to PyHole DNS-style medication routing to killdispenser supply chain primitives. One lowercase word. Append-only reference architecture.
Agent execution engine that composes prompts, routes models, and writes run artifacts. Use when launching subagent runs.
- "Is it safe to change this function?"
Git worktree–based workspace isolation for parallel or non-disruptive development. Use when work must occur without modifying or interfering with the current working tree.
Fundraising strategy, investor targeting, term sheet analysis, and SAFE/convertible note structures.
Investor pitch deck structure, narrative arc, and slide-by-slide content.
Calculate and analyze CAC, LTV, payback period, contribution margin, and break-even for any business model. Turn raw numbers into decisions.
Structured decision-making for founders using reversibility analysis, weighted scoring, pre-mortems, and second-order thinking.
Welcome sequences, launch campaigns, re-engagement flows, and segmentation strategy.
Competitor teardowns, SWOT analysis, positioning maps, and differentiation strategy.
High-converting landing page wireframes, copy, and CRO recommendations.
Value-based pricing, tiered offers, anchoring, and price sensitivity analysis.
Use to browse or verify external info—run web searches, open pages, drive Chrome via CDP tools, and cite sources when facts may be outdated, niche, or user-requested.
>
Research-first workflow: 리서치 → 분석 → 실행/수정 → 검증 → 커밋 (상황에 맞게 PHASE 자동 조절)
Add new capabilities or modify NanoGemClaw 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.
Draft professional, empathetic customer-facing responses adapted to the situation, urgency, and channel. Use when responding to customer tickets, escalations, outage notifications, bug reports, feature requests, or any customer-facing communication.
Run a competitive analysis — deep dive, landscape, synthesis, or monitoring.
Write a status update for a project or initiative. Matches the style to the audience.
Synthesize customer interview notes into themes, findings, and recommendations.
Initiate or respond to sibling contract sync — advisory only, non-blocking. Both sides update local peer topology copies.
Multi-chain wallet balance monitoring with threshold alerts. Tracks ETH and token balances across Base and Ethereum networks, comparing against historical snapshots to detect suspicious activity.
Aggregate, score, and prioritize social mentions across X/Twitter. Outputs a ranked inbox with engagement scores and draft context for efficient reply batching.
Scan project dependencies for outdated packages, security vulnerabilities, and maintenance issues across multiple languages and package managers.
Verify blockchain transactions before announcing success. Use to avoid premature celebration and trust issues. Learned from getting a basename sniped.
Track bugs, QA, and fixes in .galdr/. For bug reports, issues, quality, fixes, QA workflows.
Competitive insights are often locked in deal notes, lost opportunity records, and anecdotal rep knowledge. This skill mines Dataverse to surface structured competitive intelligence: which competitors
Consistent lead qualification is critical for sales efficiency. This skill provides a structured playbook that helps SDRs qualify leads effectively, ensures all qualification criteria are captured in
Regulatory compliance auditing across GDPR, HIPAA, PCI DSS, SOC 2, and ISO frameworks with automated evidence collection and gap analysis. Use when conducting compliance assessments, preparing for certifications, or implementing regulatory controls.
Drives the cortex skills recommend-feedback-rate loop. Use when a context change occurs (new file types, domain shift, task pivot) or when a task completes and skill effectiveness should be recorded.
>-
>-
>-
>-
Synthesizes input from nursing, pharmacy, PT/OT, social work, and case management into unified care plans. Use when conducting interdisciplinary rounds, coordinating care teams, or documenting team-based decisions.
Delegate code tasks and analysis to Codex CLI agents
Use this skill to identify, score, and prioritize Salesforce AI use cases before any implementation begins — covering opportunity identification, Impact-Effort matrix scoring, feasibility evaluation across Technical/Operational/Data/Risk dimensions, and ROI framing. NOT for implementation, enablement, feature configuration, or data architecture design.
Use this skill to configure a Salesforce B2B Commerce storefront: creating the WebStore, linking BuyerGroups, assigning CommerceEntitlementPolicies, and granting buyer contacts transactional access. Trigger keywords: B2B Commerce, WebStore, BuyerGroup, entitlement policy, buyer account, storefront access. NOT for B2C Commerce (LWR storefronts using Individual/Person Account models), CPQ quote configuration, or Order Management fulfillment flows.
Use when monitoring, diagnosing, or managing Batch Apex, Scheduled Apex, Queueable, and Flow scheduled jobs: Setup > Apex Jobs, AsyncApexJob queries, concurrent limits, failure detection, and notification patterns. NOT for writing batch Apex code (use batch-apex-patterns) or writing Schedulable implementations (use apex-scheduled-jobs).
Use this skill to configure Salesforce Billing billing schedules, invoice plans, billing policies, and billing treatments on activated Orders. Triggers: 'billing schedule not generating invoices', 'blng__BillingSchedule__c records missing after order activation', 'how to set up in-advance vs in-arrears billing', 'configure milestone billing in Salesforce Billing', 'invoice run not picking up order products', 'evergreen billing setup', 'billing treatment configuration'. NOT for CPQ quoting, not for standard revenue schedules (OpportunityLineItem revenue schedule splits), not for Salesforce Revenue Cloud (Revenue Lifecycle Management), not for native Salesforce subscription billing without the Salesforce Billing managed package.
Use this skill when designing Campaign Hierarchy structures for program-level ROI tracking, configuring Customizable Campaign Influence (CCI) attribution models, or interpreting multi-touch attribution data from MCAE B2B Marketing Analytics. Trigger keywords: campaign ROI, attribution model, campaign hierarchy, first-touch, last-touch, multi-touch, CCI, campaign influence, revenue attribution, campaign member status. NOT for campaign record creation, campaign member import, email send execution, or MCAE connector provisioning (use mcae-pardot-setup instead).