Loading...
Loading...
Found 3,210 Skills
Skills retrospective and improvement. Use when: - User asks to "review", "retrospect", "summarize" or "复盘" skills - User wants to analyze skills issues from the conversation - User requests skills optimization or improvement - End of conversation or after significant skill usage
Explain code in detail - what it does, how it works, and why. Use when you need to understand unfamiliar code or explain code to others.
Open a new context session at the start of a leader agent workflow. Records agentName, storyId, and phase in wint.contextSessions, emitting a structured SESSION CREATED block for downstream workers to inherit.
Creates or updates the product marketing context document for a brand — the deep positioning reference that all marketing specialists read before any task. Use when the user wants to document product positioning, target audience, customer language, competitive differentiation, objections, personas, or proof points. Also use when marketing output feels generic and needs richer brand context, when starting a new brand without a full SOSTAC plan, or when SOSTAC is complete and the user wants a distilled reference for the whole team. Works with the multi-brand system — always asks which brand to work on first.
Deprecated: this skill has moved to l2s.
Reproduce and investigate a bug using logs, console inspection, and browser screenshots
Draft a knowledge base article from a resolved issue or common question. Use when a ticket resolution is worth documenting for self-service, the same question keeps coming up, a workaround needs to be published, or a known issue should be communicated to customers.
Assess and classify legal risks using a severity-by-likelihood framework with escalation criteria. Use when evaluating contract risk, assessing deal exposure, classifying issues by severity, or determining whether a matter needs senior counsel or outside legal review.
Structure a pattern library entry with problem context, solution pattern, usage examples, and related patterns.
Capture architectural decisions made during Claude Code sessions as structured ADRs. Auto-detects decision moments, records context, alternatives considered, and rationale. Maintains an ADR log so future developers understand why the codebase is shaped the way it is.
Generate an ethos/ folder that captures a project's vision, principles, personas, and non-goals — the 50k-foot "why behind the what." Use when the user wants to establish project philosophy, define guiding principles, document who the product is for, or create foundational context that agents and humans can reference for decision-making. Triggers: "create an ethos", "define project principles", "document our vision", "set up project philosophy", "who is this product for."
Use when you need to generate an AGENTS.md file for a Java repository — covering project conventions, tech stack, file structure, commands, Git workflow, and contributor boundaries — through a modular, step-based interactive process that adapts to your specific project needs. Part of the skills-for-java project