发现 Skills

Writing technical blog posts about tldraw features and implementation details. Use when creating blog content about how tldraw solves interesting problems.

Creates and maintains project context artifacts (product.md, tech-stack.md, workflow.md, tracks.md) in a conductor/ directory. Scaffolds new projects from scratch, extracts context from existing codebases, validates artifact consistency before implementation, and synchronizes documents as the project evolves. Use when setting up a project, creating or updating product docs, managing a tech stack file, defining development workflows, tracking work units, onboarding to an existing codebase, or running project scaffolding.

Create and manage production Grafana dashboards for real-time visualization of system and application metrics. Use when building monitoring dashboards, visualizing metrics, or creating operational observability interfaces.

Python resilience patterns including automatic retries, exponential backoff, timeouts, and fault-tolerant decorators. Use when adding retry logic, implementing timeouts, building fault-tolerant services, or handling transient failures.

Builds an evidence-based ECC installation plan for a specific repository by performing repository-aware, parallel reviews of skills, commands, rules, hooks, and additional assets, dividing them into DAILY and LIBRARY categories. Use when ECC should be trimmed to what the project actually needs rather than loading the full package.

An engineering operating model for teams where AI agents generate large volumes of implementation output.

name: blueprint description: Transform a single-line objective into a step-by-step construction plan for a multi-session, multi-agent engineering project. Each step contains a self-contained context brief so a newly started agent can execute it directly. Includes adversarial review gates, a dependency graph, parallel-step detection, an antipattern catalog, and a plan-mutation protocol. Trigger conditions: when the user requests a plan, blueprint, or roadmap for a complex multi-PR task, or describes work that requires multiple sessions. Non-trigger conditions: when the task can be completed in a single PR or with fewer than three tool calls, or when the user says "execute directly." ...

Coordinate multi-agent coding tasks through Claude DevFleet—plan projects, schedule agents in parallel in isolated git worktrees, monitor progress, and read structured reports.

Convenes a council of four voices for ambiguous decisions, trade-offs, and go/no-go judgments. Use when multiple valid paths exist and structured objections are needed before choosing.

Use connected billing tools like Stripe to operate customer billing workflows such as subscriptions, refunds, churn triage, recovery via the billing portal, plan analysis, and more. Use this when you need to help a customer, inspect a subscription state, or manage billing operations that affect revenue.

An evidence-first revenue, pricing, refunds, team-billing and billing-model truth workflow for ECC. Use when users need sales snapshots, pricing comparisons, duplicate-charge diagnostics, or a code-grounded billing reality instead of generic payment advice.

F# test frameworks, property-based testing, and a functional approach.

Japanese translation: this file requires a Japanese translation for the motion-patterns collection.

Use this skill when adding authentication, handling user input, managing secrets, creating API endpoints, or implementing payment or other sensitive features. Provides a comprehensive security checklist and patterns.

Use AgentShield to scan Claude Code settings (the .claude/ directory) for security vulnerabilities, misconfigurations, and injection risks. Checks CLAUDE.md, settings.json, the MCP server, hooks, and agent definitions.

An evidence-first repository execution workflow for ECC. Used when a user needs to run commands, inspect a repository, debug CI failures, or push a narrow fix with precise execution and verification proof.

A regression testing strategy for AI-assisted development. It includes sandbox-mode API tests that do not depend on a database, an automated bug-check workflow, and patterns to catch blind spots that occur when the same model both writes and reviews code.

Build monitoring dashboards for Grafana, SigNoz, and similar platforms that answer real operator questions. Use this to turn metrics into actionable dashboards rather than vanity displays.

HIPAA-compliant implementation, security controls, audit logging, and data protection strategies.

Outreach to investors, relationship building, fundraising strategy, and pipeline management.

Weighted social-graph ranking for discovering warm introductions, bridge scoring, and network-gap analysis on X and LinkedIn. Intended for use when a user needs the ranking engine itself (not the broader promotion or network-maintenance workflow).

Verification loop for Spring Boot projects: build, static analysis, tests with coverage, security scans, and diff review before release or PR.

Automate Apiverve tasks via Rube MCP (Composio). Always search tools first for current schemas.

Automate Blackbaud tasks via Rube MCP (Composio). Always search tools first for current schemas.