Scan a codebase for missing, janky, or inconsistent UI motion and fix it with transitions.dev recipes. ALWAYS use this skill when the user's message is or contains a transitions-agent command (npx transitions-agent, npx transitions-agent fix, any variant) - the command is a request for the full guided flow, not just command execution. Also use when the user asks about UI transitions, animations, motion quality, a motion score, janky or missing transitions, "polish the motion", "fix the animations", or whether the motion is good after UI changes.

General-purpose desktop web prototype. Single self-contained HTML file built by copying the seed `assets/template.html` and pasting section layouts from `references/layouts.md`. Default for any landing / marketing / docs / SaaS page when no more specific skill matches.

Dogfoods Compozy through an autonomous startup scenario with live providers, cross-surface observation, and strict evidence audit. Use for release or complex-integration QA. Do not use for smoke, static, mock-only, or unit-test work.

Expert guidance for systematic backtesting of trading strategies. Use when developing, testing, stress-testing, or validating quantitative trading strategies. Covers "beating ideas to death" methodology, parameter robustness testing, slippage modeling, bias prevention, and interpreting backtest results. Applicable when user asks about backtesting, strategy validation, robustness testing, avoiding overfitting, or systematic trading development.

Use when the user asks about Liran Tal's talk at AI Native DevCon on skills security — including questions about the lethal trifecta / toxic flows, the Snyk research finding ~30% of ~4,000 Glow skills had security issues, malicious skill examples (SkillGuard, fake Vercel deployment skill, "buy anything", invisible-character Trojan Source skills), the confused-deputy problem, acceptance fatigue, parallels to NPM supply-chain attacks, or how to think about reviewing and sandboxing AI agent skills.

Use when the user asks about the "Welcome to AI Native DevCon" talk introducing Slick (slick.com) — a browser-native agent that controls the browser it runs in. Covers Slick's architecture (sprinkles, scoops, licks, the cone), how it uses HTTP / Chrome Debug Protocol / WebRTC, pyagent as the agentic loop, skills as "step zero of agent enablement", MCP and webMCP support, remote-controlling Electron apps (Slack, Teams, Claude desktop) via Slick Star, ad hoc generative UI, OAuth token handling, and verbatim quotes from the talk. Also use when the user wants to apply this browser-native agent approach to their own work.

Improve the quality, outcome orientation, and derisking of ONE initiative's artifacts in the portfolio PDLC — rewrite activity-framed cards into outcome hypotheses with leading indicators, sharpen riskiest assumptions with evidence/opinion tags, fix derisking-approach mismatches, and capture at most one durable learning. Use on cards flagged activity-oriented, thin on evidence, missing indicators, or carrying committed money with open risks. The loop-2 skill of the portfolio-pdlc family.

The sensing pass of the portfolio-pdlc operating system. Use when asking "where is everything really, and is it outcome-oriented or activity-oriented?" — full portfolio reads, review/investment-council prep, stale-status sweeps, or restoring board integrity after contract violations. Verifies stages against evidence, classifies every card on the input→impact ladder, reads flow and risk balance, and outputs a review brief with ranked candidate moves. Composes the sniff-test and sniff-test-portfolio skills included in this repo.

Turn any value stream — a PDLC, an SDLC, a content pipeline, an AI use-case pipeline, an operational request stream — into a flow-driven agentic loop that runs on plain files. Use when choosing where to apply agentic workflow, defining or ingesting a definition of workflow (steps, graph, exit evidence, delegate model per step, run model per step, measures), scaffolding it as markdown, orchestrating it agentically one move per cycle, integrating it with GitHub or a Kanban board, or inspecting and adapting the loop itself. Entry point and operating loop for the flow-driven-* skill family; for portfolio-level investment management use portfolio-pdlc instead.

Authors Cursor Plans for the OctoBot git repo that run on Cursor Cloud Agents. Automatically applies whenever CreatePlan is used and the plan title or overview/description contains "roadmap" (case-insensitive). Also applies when the user asks for a cloud roadmap, cloud-safe multi-step plan, or names cloud-roadmap. Requires repo-relative paths only, package/module responsibility maps, clarify-before-assume, validation milestones with unit tests (pytest or npm test/vitest) and functional tests when relevant, package ownership, and clarification before guessing.

Verify a Mem0 integration produced by /mem0-integrate. Runs in the same workspace on the same branch (loose coupling) — installs dependencies, runs the repo's native test suite, then exercises a real end-to-end smoke flow against the user's API key. Produces a scorecard. TRIGGER when: user has just run /mem0-integrate and says "verify", "test the integration", "run /mem0-test-integration", or when a .mem0-integration/ directory exists and tests have not been run yet on the current branch. DO NOT TRIGGER when: the user wants to run general project tests (defer to the repo's native test command), or when no prior /mem0-integrate run exists in the current branch (ask them to run /mem0-integrate first). This skill ONLY catches compile and runtime bugs by design. Logical integration errors — wrong data stored, wrong time retrieved, wrong user scoping — are on the human reviewer.

Search memories from earlier Kimi sessions in this repository. Use it when earlier work may already explain the code, error, decision, or command you need, so you can avoid repeating file reads, searches, or experiments.

Audit Fallow for unnecessary code, misleading tests, redundant abstractions, avoidable copying, and stale maintenance guidance. Use for a requested slop audit or deep cleanup pass.

Review Rust code changes in fallow for correctness, performance, cache-friendly design, and project conventions. Use when changes touch Rust crates such as config, types, extract, graph, core, cli, lsp, or mcp.

Use before modifying, refactoring, or deleting files in a codebase that has Repowise indexed (indicated by a .repowise/ directory). Activates when Claude is about to edit code, especially shared utilities, core modules, or files the user didn't explicitly mention. Helps assess impact and avoid breaking things.

Analyze Agent Host debug log exports. Use when given an ah-logs or ahp-logs zip/folder, an Export Agent Host Debug Logs bundle, events.jsonl, AHP JSONL transport logs, Agent Host.log, remote-agenthost.log, or copilot-logs.

Delegate a bounded implementation, prototype, benchmark, or file artifact to Claude Code, then verify and integrate its completed work. Use when the user explicitly authorizes Claude to own execution. Read-only advice belongs to consult-claude.

Imperative guidance for the System.Text.Json APIs added in .NET 11: the built-in `JsonNamingPolicy.PascalCase` naming policy, and the strongly-typed generic `JsonSerializerOptions.GetTypeInfo` and `JsonSerializerOptions.TryGetTypeInfo` metadata accessors (generic overloads that return a typed `JsonTypeInfo`). USE ONLY when the user is targeting net11.0 or later and needs PascalCase JSON property or dictionary-key names without writing a custom naming policy, a strongly-typed generic `JsonTypeInfo` instead of the non-generic `JsonTypeInfo`, or a no-throw way to probe whether a type's serialization metadata is resolved. DO NOT USE when the target is earlier than net11.0, the requested behavior uses an established pre-net11 naming policy, or the user explicitly selected another JSON library.

Look up Stripe customers, subscriptions, charges, and payment methods. Cancel subscriptions and issue refunds. Use when investigating billing issues, subscription cancellations, or payment disputes.

Port an existing form (a data-graph graph, or a bespoke RHF+zod form like model training) to the form-graph library. Use when asked to move a form's field logic, branching, persistence, or server validation onto form-graph. Encodes the method proven by the generation-form port — oracle-first differential testing, scope mapping, staged cutover.