YuukiFST
@YuukiFST
Public Skills
ai-copywriter
by YuukiFST
"Write copy that converts and doesn't sound like a robot: clickbait titles, headlines, short descriptions, microcopy, CTAs, error messages, subject lines, viral LinkedIn posts, and category-defining strategic blog posts. Asks for the ICP, the category, and the story before writing, and audits every draft against Wikipedia's Signs of AI writing before delivering it. Use when writing or punching up marketing copy, UI text, titles, LinkedIn posts, or strategic blog posts. Rewriting existing prose to sound less AI belongs to ai-tells."
ai-tells
by YuukiFST
"Find and remove AI tells in prose: rewrite a draft so it reads like its writer, or audit text for tells without rewriting. Use when text should sound less AI-written or more human, when asked whether writing reads as AI, or when polishing a PR body, commit message, doc, post, or file before it ships. Writing new marketing copy belongs to ai-copywriter."
git-workflow
by YuukiFST
"Use when shipping a change through GitHub end to end — before the first commit, not at merge time. Covers opening the issue, naming the branch, sequencing commits, opening a PR that closes the issue, recording a review before merge, choosing merge vs rebase vs squash, and cleaning up after. Also covers reverting a merged mistake, forks vs standalone repos, and contributing to someone else's repo."
ui-polish
by YuukiFST
Build or improve a web UI (page, screen, component, flow) to a design-engineer craft bar on any stack, with no package required, routing to the jakubkrehel and emilkowalski reference skills. Use when asked to create a screen or component from scratch, improve/polish/redesign an existing page ("improve the UI", "make the UI look better.", "feels off"), review UI or motion quality of a screen or of a diff/branch/PR, add or fix animations, pick a UI library, show variants, or stress-test a component. Skip for pure logic, data or backend work.
test-audit
by YuukiFST
"Invoke whenever writing, changing, reviewing, or sweeping tests. Authoring gate for new tests plus audit workflow for low-value, implementation-coupled, or duplicative tests and the test-only production seams they demand."
code-simplifier
by YuukiFST
Simplify and refine recently modified code for clarity, consistency and maintainability while preserving all functionality. Use when asked to simplify, clean up or refine code just written, or after finishing a change.
security-review
by YuukiFST
Use this skill when adding authentication, handling user input, working with secrets, creating API endpoints, or implementing payment/sensitive features. Provides comprehensive security checklist and patterns.
security-bounty-hunter
by YuukiFST
Hunt for exploitable, bounty-worthy security issues in repositories. Focuses on remotely reachable vulnerabilities that qualify for real reports instead of noisy local-only findings.
helmsman
by YuukiFST
Plan a huge chunk of work — more than one agent session can hold — as a shared map where the human answers only what the system should do, and the agent decides how it gets built, resolving the technical tickets alone and in cascade.
chrome-devtools-axi
by YuukiFST
"Control a Chrome browser session through the chrome-devtools-axi CLI - navigate, snapshot, click, fill forms, run JavaScript, inspect console and network, take screenshots, audit performance. Use whenever a task needs a real browser: opening or testing a web page, clicking through a flow, extracting page content, or debugging a website."
optimizing-startup
by YuukiFST
Use when a desktop app's launch or startup feels slow, when asked to hit a "bounce" or half-bounce startup target, or when a splash, spinner, skeleton, or blank window shows on launch. Windows and Linux desktop apps (Tauri, Electron, native).
helmsman-explain
by YuukiFST
Build a visual, self-contained HTML explainer of how the /helmsman skill works — the division of labour, the map, the three modes — drawn from the current SKILL.md and rendered against the user's live map when one exists. Use when the user asks how helmsman works, what it does, whether to use it, or invokes /helmsman-explain.
backpass
by YuukiFST
Train a project CLAUDE.md on its own session transcripts — one evidence-backed gradient step per run.
systematic-debugging
by YuukiFST
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
writing-plans
by YuukiFST
Use when you have a spec or requirements for a multi-step task, before touching code
verification-before-completion
by YuukiFST
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
brainstorming
by YuukiFST
"You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation."
executing-plans
by YuukiFST
Use when you have a written implementation plan to execute in a separate session with review checkpoints
prototype
by YuukiFST
Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.
setup-matt-pocock-skills
by YuukiFST
Configure this repo for the engineering skills — set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.
writing-for-agents
by YuukiFST
Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.
grilling
by YuukiFST
Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.
improve-codebase-architecture
by YuukiFST
Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
research
by YuukiFST
Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to a background agent.