Loading...
Loading...
Found 53 Skills
Software architecture and UI/UX principles for building genuinely new solutions, not derivative work. Use when designing features, architecting software, brainstorming apps, reviewing designs, or during strategy discussions. Focuses on first-principles thinking, simplicity where it matters, and creating rather than commenting.
Make dense or complex information easier to understand, navigate, remember, and act on through clear layers, concrete examples, and visible progress. Use when the user explicitly invokes Focus Friendly; requests focus-oriented simplification, chunking, pacing, mapping, or reorientation; reports overwhelm, trouble reading or focusing, task-initiation difficulty, or losing their place in the current task; asks whether those difficulties prove ADHD; or asks for help navigating long, structurally complex material that genuinely needs a map. Do not invoke merely because a request mentions ADHD or asks for summarization, teaching, planning, research, or routine coding; those tasks need an explicit focus or navigation signal.
Apply principles of good design taste when creating, reviewing, or critiquing any creative or technical work. Use this skill whenever the user asks you to design something, review a design, create UI/UX, architect a system, write something with aesthetic intent, evaluate the quality of code or creative work, or asks for feedback on whether something is "good." Also trigger when users mention taste, aesthetics, beauty in design, elegance, simplicity, or when they want help making something not just functional but genuinely well-crafted. This skill applies across domains: software, writing, visual design, architecture, presentations, APIs, data models, and more. Even if the user doesn't explicitly mention "design," use this skill when the underlying task is about making something better, more elegant, or more refined.
Root-cause-driven solution decision framework for the hardest problems across any domain. This is the nuclear option — it consumes significant tokens through exhaustive multi-branch root cause analysis, MECE solution enumeration, and domain-adaptive external validation. Use ONLY for genuinely difficult problems: recurring failures that resist repeated fix attempts, complex systemic issues with no clear solution path, decisions where multiple approaches exist and the wrong choice has high cost, problems with multiple interacting causes spanning components or teams. Trigger when: the user says 'what's the best way to fix X', 'why does this keep happening', 'how should we approach this', 'find the root cause', 'what are my options for fixing X', 'analyze this problem systematically', 'evaluate our options for X', 'what's the right approach and why', or expresses frustration that previous solutions didn't stick. Do NOT use for: problems where the answer is already obvious or requires no analysis, straightforward issues with clear solutions, or routine investigation. If the problem can be solved in 5 minutes of investigation, this skill is overkill.
Makes AI-generated content sound genuinely human — not just cleaned up, but alive. Use when content feels robotic, uses too many AI clichés, lacks personality, or reads like it was written by committee. Triggers: 'this sounds like AI', 'make it more human', 'add personality', 'it feels generic', 'sounds robotic', 'fix AI writing', 'inject our voice'. NOT for initial content creation (use content-production). NOT for SEO optimization (use content-production Mode 3).
Detects AI-written text, scores it against a detection rubric, provides line-by-line edit recommendations, and rewrites content to sound genuinely human. Use when the user asks to 'humanize' text, detect AI writing, remove 'AI voice,' make copy 'less robotic,' pass AI detection tools, or rewrite content to 'sound human.'
NEVER escalate without investigation first. This is the Iron Law. Use when evaluating whether to escalate models, facing genuine complexity requiring deeper reasoning, novel patterns with no existing solutions, high-stakes decisions requiring capability investment. Do not use when thrashing without investigation - investigate root cause first. DO NOT use when: time pressure alone - urgency doesn't change task complexity. DO NOT use when: "just to be safe" - assess actual complexity instead.
Captures and organizes chaotic brain dumps into a structured, actionable system with zero information loss. Use this skill whenever the user says 'capture this', 'brain dump', 'let me dump some ideas', 'I've got a bunch of thoughts', 'here's everything on my mind', 'idea dump', 'let me get this out of my head', 'I need to organize my thoughts', 'here's what I'm thinking', or any variation where someone is unloading a messy stream of ideas, tasks, thoughts, and plans wanting them turned into something coherent. Also trigger when the user pastes or dictates a long, unstructured block of mixed ideas — even without the exact phrase — the intent is the same. Fast-to-action by design: no upfront intake. Output is four sections (Projects/Ideas, Tasks, Connections, How I Can Help) ending with a directive question. Asks at most one mid-organization clarifying question when a single item is genuinely ambiguous between task and project.
Log genuine, recurring repository friction to .agents/PAPERCUTS.md — confusing setup, a flaky repo command or script, a misleading in-repo error, stale generated files, or a non-obvious gotcha that will cost the next contributor time. Also use to review, deduplicate, and resolve existing entries. Gate hard before logging: only friction the repository itself can fix counts. Never log the agent's own sandbox/permission errors, shell-scripting mistakes, transient flakiness, or third-party tool quirks the repo can't change.
Use when creating product recommendation content on Xiaohongshu, writing posts that naturally lead to purchases, developing authentic product reviews, building trust through genuine product experiences, or planning content that converts readers to buyers
Use when a task fails, an approach does not work, when encountering errors during implementation, or when tempted to say "I cannot do this" - ensures retry with at least 3 genuinely different approaches before escalating
Orchestrate multiple code-writing agents in parallel when the work contains 3 or more genuinely independent build tasks. Use for execution lanes with disjoint write scope, clear task boundaries, and no dependency edges that would force sequencing.