Loading...
Loading...
Found 598 Skills
Create subtasks in Jira from a previously generated task plan. Reads the plan from docs/<TICKET_KEY>-tasks.md and creates one Jira subtask per task under the parent ticket. Use when the user says "create subtasks", "push tasks to Jira", "sync plan to Jira", "create Jira tickets", "make subtasks for PROJECT-1234", or anything about turning a plan into Jira issues. Also triggered by the orchestrating-jira-workflow skill as Phase 4. Requires the task plan to already exist (run planning-jira-tasks first if it does not). Use this skill even if the user just says "push to Jira" or "create the tickets" after a planning phase — those are subtask creation requests.
Full project soul alignment in one command. Scans every frontend file in the project, builds a prioritized plan, then systematically aligns all components and styles to .marrow.md. Smart enough to detect if .marrow.md was updated since the last run and only reprocess files affected by what changed — not a full rewrite every time. Use this skill when the user wants to align the entire project to the design soul at once, just installed marrow mid-project and wants to catch everything up, or updated .marrow.md via /marrow-update and wants to propagate only the changed rules across the project. Triggers on: /marrow-redesign, or prompts like "align the whole project", "redesign everything to match marrow", "apply marrow to all files", "full soul alignment", "catch everything up to marrow", "propagate the marrow update", "marrow everything". Requires .marrow.md to exist. If not found, instructs user to run /marrow first. This is a multi-step agentic command — it will take multiple turns to complete large projects. It creates a .marrow-state.json file to track progress and enable smart diff on future runs.
Use this skill when a user asks to review a pull request for bugs, wants AI code review focused on correctness issues, or runs /bug-review. Trigger on PR review, bug finding, code review, "review this PR", "check for bugs", "find issues in this PR". This is a multi-pass review workflow with 5 parallel passes, majority voting, independent Opus validation, and resolution rate tracking. Also trigger on /bug-review:resolve to classify whether findings were fixed at merge time, and /bug-review:report for resolution rate stats. Even if the user just says "review this" while on a PR branch, trigger this skill.
Capture the current session's repeatable process into a reusable SKILL.md skill file. Use when the user wants to create a skill, save a workflow as a skill, turn a process into a reusable skill, or mentions "skillify", "create skill", "make a skill", "save as skill", "capture workflow", "turn this into a skill", "new skill", or wants to automate a repeatable process they just performed.
Sets up or repairs the AGENTS.md source-of-truth pattern for any project. Creates a well-structured AGENTS.md with real stack info auto-detected from the project, then wires all AI config satellites (.claude/CLAUDE.md, .github/copilot-instructions.md, .agents/rules/, MEMORY.md) to point to it. Eliminates duplication. Always runs in plan mode — asks before acting. Use this skill whenever the user mentions AGENTS.md, agent config, source of truth for AI rules, setting up Claude/Copilot/Cursor for a project, fixing duplicate AI instructions, or wants to consolidate AI configuration files. Trigger even if the user just says "set up agents" or "fix my AI config".
Ultra-lightweight channel for feature workflows: No need to write design docs, checklists, or conduct phased reviews. Let AI write code directly as it normally would, but before it starts, tell it where the CodeStable knowledge base in the project is and how to search it. This way, the code it writes will have fewer pitfalls and be more consistent with project conventions. Trigger scenarios: Users say "fast mode", "fastforward", "skip all those steps", "just start coding", "help me make xxx" and the requirement is too small to go through the design process.
Behavior Guidelines for Information Visualization Presentation. Automatically activated when the model's response contains structured information such as comparisons, steps, configurations, architectures, etc., ensuring priority use of visual formats like tables, code blocks, lists, tree structures, instead of pure text accumulation. Trigger words: "Use a table", "Draw a diagram", "Make a list", "Structure it", "Don't just use text", "Visualize", "Compare". Even without trigger words, the rules of this Skill should take effect as long as the response contains structured information suitable for visualization. It also applies to scenarios such as "Too much text to read", "Can it be more intuitive?", "Organize into a table".
Startup diagnostic router. Use FIRST when a founder doesn't know where to start, has multiple overlapping problems, or asks a vague question like 'what's wrong with my startup', 'why aren't people buying', 'what should I focus on', 'where do I even begin', 'nothing is working'. Routes to the right framework from the 14 available skills — or tells you when no framework fits and you just need to go talk to people. This is the entry point. Use it before reaching for any specific skill.
Format a final summary message for Linear. Your output is automatically streamed to the Linear agent session — just format it well, do not post it yourself.
Map, analyze, and redesign the systems behind product experiences. Part of the Intent design strategy system. Creates service blueprints, ecosystem maps, process architecture, and dependency diagrams. Understands how services, teams, tools, and data flows connect to produce (or fail to produce) user outcomes. Proposes structural changes to how products and services are organized. Trigger on: service blueprints, system maps, process architecture, actor/role mapping, dependency analysis, cross-functional workflows, operational design, "how does this system work?", "what breaks when X happens?", "map out the service", "where are the dependencies?", or any question about the structural machinery behind a product experience. Use this skill broadly — whenever someone needs to understand or redesign how a system works, not just what a user sees.
Candlestick / OHLCV data and intraday minute series for stocks listed in HK / US / A-share / Singapore via Longbridge Securities. Supports 1m / 5m / 15m / 30m / 1h / day / week / month / year periods, history by date range, and today's intraday curve. Triggers: "K线", "K 线", "走势", "历史价格", "日K", "月K", "周K", "分时图", "近一周走势", "K線", "走勢", "歷史價格", "日K", "月K", "週K", "分時圖", "candlestick", "candles", "OHLCV", "intraday chart", "price history", "weekly chart", "monthly chart", "1-year chart", "前复权", "前復權", "forward adjusted".
Analyze source code and produce an enterprise-quality, domain-organized Wiki under `.nium-wiki/`. Trigger on: "generate wiki", "create docs", "update wiki", "rebuild wiki", or any documentation generation request. Capabilities: - Semantic code analysis — understands logic, not just structure - Auto-generated Mermaid diagrams (architecture, data flow, class, dependency) - Bidirectional cross-linking across all documents - SHA256-based change detection for incremental rebuilds - Every section traces back to source via relative path links - Multi-language output (zh/en/ja/ko/fr/de and more)