Give an agent durable, cross-session long-term memory using Databricks MANAGED memory (the Unity Catalog memory-store REST APIs) as tools — governed by UC with no infra the customer needs to run. This works for either OpenAI Agents SDK or LangGraph templates. Use when: the agent should remember a user's (or a team/org's shared) preferences/facts/decisions across conversations; keywords 'long-term memory', 'managed memory', 'memory store', 'agentic memory'. This is separate from the self-hosted Lakebase memory solution with skills in (agent-openai-memory / agent-langgraph-memory).

Give an agent durable, cross-session long-term memory using Databricks MANAGED memory (the Unity Catalog memory-store REST APIs) as tools — governed by UC with no infra the customer needs to run. This works for either OpenAI Agents SDK or LangGraph templates. Use when: the agent should remember a user's (or a team/org's shared) preferences/facts/decisions across conversations; keywords 'long-term memory', 'managed memory', 'memory store', 'agentic memory'. This is separate from the self-hosted Lakebase memory solution with skills in (agent-openai-memory / agent-langgraph-memory).

Detect and capture technical preferences, naming conventions, and architectural practices from user messages into Packmind standards. Trigger when user prescribes HOW to code through direct statements (e.g., "Use snake_case for columns", "Always use async/await") or suggestive patterns like questions ("Could we use X instead?"), code review feedback ("This would be clearer with X"), and comparative statements ("Use X instead of Y"). Does NOT trigger for feature requests, bug reports, or general implementation tasks without coding preferences.

Guide for creating coding standards via the Packmind CLI. This skill should be used when users want to create a new coding standard (or add rules to an existing standard) that captures team conventions, best practices, or coding guidelines for distribution to CoPilot.

Bidirectional bridge between ClickUp and spec-kitty feature specs. Use when the user mentions ClickUp tasks, CU- IDs, spec-kitty features, creating tasks in ClickUp, importing ClickUp context into specs, or exporting spec-kitty specs to ClickUp. Provides /specup.setup, /specup.new, /specup.import, and /specup.export commands.

Code review — yours or someone else's. Self-review before pushing, structured PR review against the story and the codebase, and feedback processing once reviewers respond. Reads the diff in surrounding context, not the patch alone.

Browser automation via Playwright for web testing, screenshots, form filling, scraping, and verification. Use when tasks require navigating websites, interacting with web pages, or testing web applications.

Guidelines for making .NET libraries and applications trimming-safe and Native AOT compatible. Covers the trimming/AOT model, the MSBuild properties that enable analysis (IsTrimmable, IsAotCompatible, PublishTrimmed, PublishAot), the trimming attributes (RequiresUnreferencedCode, RequiresDynamicCode, DynamicallyAccessedMembers, UnconditionalSuppressMessage), IL2xxx/IL3xxx warning codes, and a pattern playbook: source generators and UnsafeAccessor, generated-interception diagnostic suppressors, intentional runtime scanning boundaries, trimming-safe islands and feature switches, migration analyzers, and temporary warning-approval baselines. Use when introducing trimming/AOT support, resolving IL2xxx/IL3xxx warnings, or making reflection-heavy code trimming-safe in C# / .NET codebases. For System.Text.Json AOT scenarios, see also the serialization skill.

Guide an Amplitude user through building a custom agent by suggesting use cases grounded in their role and data, shaping the idea into a well-formed spec, and generating a ready-to-run Global Agent deeplink that creates it. Use to create, build, or set up a custom agent, automate a recurring analysis, or put a repeated report on a schedule.

**WORKFLOW SKILL** - Execute the end-to-end WingtipToys migration benchmark: clear samples\AfterWingtipToys, run the migration-toolkit against samples\WingtipToys, repair the generated app until Playwright acceptance tests pass, and write a numbered run report with embedded screenshots under dev-docs\migration-tests\wingtiptoys. WHEN: "run Wingtip migration", "test WingtipToys migration", "Wingtip benchmark", "migrate WingtipToys", "rerun Wingtip migration". INVOKES: migration-toolkit (scripts + skills), dotnet CLI, Playwright tests.

Domain-agnostic metric-driven improvement loop, generalizing Karpathy's autoresearch. Use when you want an agent to discover what to measure for a project/goal, then run a keep-or-revert experiment loop that proposes changes, measures them against an objective, keeps wins, discards regressions, and records implemented improvements. Adapts to code perf-auditing, codegen, bug-finding, ad optimization, or any artifact + measurable objective + trial. Trigger: 'autoresearch this', 'find and implement improvements to X', 'discover metrics and optimize'.

Commit changes and create a Merge/Pull Request following project conventions. Use when the user asks to commit, push, create an MR/PR, or ship/land their work. Handles staging, committing (with conventional commit format), pushing, and MR/PR creation with proper descriptions. Single commit per MR/PR; amends if one already has a commit.

Break down an epic into well-refined subtasks. Use when the user wants to groom a backlog, create subtasks from an epic, break down an epic into tickets, or refine tasks from user stories. Triggers on "groom", "backlog grooming", "break down epic", "create subtasks from epic", or any request to turn an epic's user stories into individual tickets.

Create and iterate on Slidev presentation decks using a customizable brand theme. Use when the user asks to create a new presentation, slide deck, or slides, or wants to modify/add slides to an existing deck. Triggers on: 'new deck', 'new presentation', 'new slides', 'slide deck', 'make a presentation', or any request involving Slidev markdown slides in the presentations/ directory.

Use when creating or iterating staged planning artifacts for a complex feature: design discussion, structure outline, final executor plan, or supporting research/research questions. Also use when designing before coding, breaking work into vertical slices, or deepening a high-value roadmap item, NNN improve plan, architecture candidate, or HumanLayer-style task.

General prose doctrine for anything a human will read — clear, concrete, free of ready-made phrases. Use when writing or editing documentation, explanations, summaries, commit messages, reports, or any other prose.

Snapshot of a single wallet's token holdings on a specific chain — list of every token currently held with name, symbol, current price, 24h price change, and holding quantity. Use when the user provides an explicit wallet address (or says "my wallet") and wants the current portfolio: "what does 0x... hold", "wallet balance breakdown", "list positions for this address", "what tokens are in this wallet", "show me the holdings of <address>".

Interact with ClawDirect, a directory of social web experiences for AI agents. Use this skill to browse the directory, like entries, or add new sites. Requires ATXP authentication for MCP tool calls. Triggers: browsing agent-oriented websites, discovering social platforms for agents, liking/voting on directory entries, or submitting new agent-facing sites to ClawDirect.

Audit an LLM eval pipeline and surface problems: missing error analysis, unvalidated judges, vanity metrics, etc. Use when inheriting an eval system, when unsure whether evals are trustworthy, or as a starting point when no eval infrastructure exists. Do NOT use when the goal is to build a new evaluator from scratch (use error-analysis, write-judge-prompt, or validate-evaluator instead).

Claude Code extensibility: agents, skills, output styles. Capabilities: create/update/delete agents and skills, YAML frontmatter, system prompts, tool/model selection, resumable agents, CLI-defined agents. Actions: create, edit, delete, optimize, test extensions. Keywords: agent, skill, output-style, SKILL.md, subagent, Task tool, progressive disclosure. Use when: creating agents/skills, editing extensions, configuring tool access, choosing models, testing activation.