Send feedback or bug reports to the Deepline team, including session transcript and environment info. Use when the user asks to report a bug, send product feedback, or share the current Claude/Cowork session with Deepline support.

This skill should be used when the user asks to "merge dependabot PRs", "review dependabot", "auto-merge dependencies", "handle dependabot", "merge dependency updates", "check dependabot PRs", or wants to automatically review and merge open Dependabot pull requests. Also triggered by the /auto-merge-dependabot command.

Enforces the Airbnb iOS Swift Style Guide on Swift code. Use this skill any time the user wants to: review Swift code for style compliance, lint or audit an iOS codebase, apply Airbnb Swift conventions to new or existing code, understand why code violates Airbnb style rules, or get corrected rewrites of Swift snippets. Triggers on any request mentioning Swift code quality, iOS code review, Airbnb style, linting Swift files, or when the user pastes Swift code and asks for feedback, fixes, or a review. Also use when the user asks to "clean up" or "format" Swift code, or asks "is this good Swift?" — even if they don't mention Airbnb by name.

Handle errors as values instead of throwing exceptions. Result/Either pattern, railway-oriented programming, and validation with error accumulation. Activate when: writing error handling, try/catch blocks, validation logic, operations that can fail, chaining fallible operations, form validation, API input validation, or when the user mentions Result, Either, error handling, or validation patterns. Works in any language (TypeScript, Python, Go, Rust, Java).

Write and refactor code using functional programming principles for fewer bugs and less code. Language-agnostic (TypeScript, Python, Go, Rust, Java, etc.). Activate when writing new functions, refactoring existing code, reviewing code quality, fixing bugs caused by state mutation, building data pipelines, or when the user mentions functional programming, pure functions, immutability, composition, or side effects. Also activate when generating any non-trivial business logic to default to FP patterns.

Build complex behavior by composing small, reusable functions. Covers currying, partial application, pipe/flow, data-last design, and building utility libraries from tiny pieces. Activate when: creating utility functions, building data processing pipelines, chaining transformations, refactoring large functions into smaller ones, or when the user mentions pipe, compose, curry, partial application, point-free, data-last, or function composition. Works in any language (TypeScript, Python, Go, Rust, Java).

Never mutate data — create new values instead. Covers immutable update patterns (spread, copy, freeze), nested updates without mutation, readonly enforcement, and performance trade-offs. Activate when: updating objects or arrays, working with state management (React, Redux), fixing bugs caused by unintended mutation, deeply nested data updates, or when the user mentions immutability, spread, readonly, frozen, copy-on-write, or structural sharing. Works in any language (TypeScript, Python, Go, Rust, Java).

Migrate Terraform/OpenTofu projects to Pulumi, including translating HCL source code and/or importing Terraform state into a Pulumi stack. Use when a user wants to convert Terraform to Pulumi, migrate from HCL, or import tfstate into Pulumi. Do NOT trigger for general Terraform-vs-Pulumi comparisons or questions about using both tools side-by-side.

Kubernetes cluster, pod, node, and workload monitoring. Use when analyzing K8s health, resource optimization, pod failures, OOMKills, scheduling, or security posture. Also use for Kubernetes operational events like pod restarts, OOM events, evictions, and cluster event history. Trigger: "Kubernetes pods", "K8s cluster health", "OOMKill", "pod restarts", "container CPU", "namespace resource usage", "over-provisioned pods", "privileged containers", "pod placement", "K8s node capacity", "running containers by cluster", "workload scheduling", "pod evictions", "K8s labels and annotations", "kubernetes events", "pod restart events", "OOM events", "K8s event history". Do NOT use for explaining existing queries, product documentation questions, AWS-specific resource queries, service-level RED metrics, distributed tracing, or log analysis — use the relevant skill instead.

Research a documentation topic — locate affected files, understand the problem, identify what to change. Use when investigating an issue, a question, or a topic before writing a fix. Triggers on: "research issue 1234", "investigate what needs changing for #500", "what files are affected by #200", "where is X documented", "is our docs page about Y accurate", "look into how we document Z".

libutil - General utilities. countTokens and estimateTokens for GPT-style token counting. generateHash creates SHA256 hashes. generateUuid creates unique IDs findProjectRoot locates repository root. updateEnvFile modifies environment files. exec runs child processes. createBundler downloads code bundles. Use for token counting, hashing, and project utilities.

Draft cold emails, warm intro blurbs, follow-ups, update emails, and investor communications for fundraising. Use when the user wants outreach to angels, VCs, strategic investors, or accelerators and needs concise, personalized, investor-facing messaging.

Create platform-native content systems for X, LinkedIn, TikTok, YouTube, newsletters, and repurposed multi-platform campaigns. Use when the user wants social posts, threads, scripts, content calendars, or one source asset adapted cleanly across platforms.

libanalysis - Code analysis and formatting utilities. formatForAnalysis function prepares markdown documents with Prettier formatting and line numbers for LLM code review tasks. Use for document preparation, code analysis, and creating numbered reference documents for AI processing.

Interview the user and produce issues/prd.md from a client brief, feature idea, or rough request. Step 1 of the build pipeline (write-a-prd → prd-to-issues → work-issues). Use when no PRD exists yet and one is needed. NOT for breaking an existing PRD into tasks (use prd-to-issues), and NOT for tracker-coupled output (this writes local markdown only). Triggers: /write-a-prd, "write a PRD", "draft a spec", "turn this brief into a PRD".

Instrument a LaunchDarkly metric event in a codebase by adding a track() call. Use when the user wants to wire up an event, instrument an action for a metric, add tracking to a feature, or confirm that an event is flowing to LaunchDarkly.

Update, archive, and delete LaunchDarkly configs and their variations. Use when you need to modify config properties, change model parameters, update instructions or messages, archive unused configs, or permanently remove them.

Create and manage agent graphs — directed graphs of configs connected by edges with handoff logic. Use when building multi-agent workflows where configs route to each other.

Design a loss function and harness for a long-running /goal optimization run (loss-function development, LFD). Use when the user wants to set up an autonomous optimization loop, distill a product from public artifacts, turn a spec into an optimization target, or asks to design a /goal. Observes the existing environment, interrogates the task, ingests or generates the spec, builds a blinded eval, generates and verifies the harness, red-teams the target for cheats, and emits goal.md ready to launch. Re-invoke in patch mode when a running loop cheated and the loss function needs patching.

Use this skill whenever the user asks you to write, edit, review, refactor, debug, or design TypeScript or TSX code. It is especially relevant for application code, backend routes, React/UI work, schemas, runtime boundaries, persistence, async workflows, API contracts, tests, lint/typecheck fixes, and code review. Apply it even when the user does not explicitly mention "TypeScript" if the files or project are TypeScript-based.