yourpovv

@yourpovv source repo

13 skills
0 followers
6 hours ago last updated

▌
Apple Design · yourpovv
Use this skill whenever the user wants UI built in Apple's aesthetic language: glassmorphism, liquid glass, spring physics, Dynamic Island patterns, SF Pro typography, Control Center widgets, iOS/macOS system chrome, vibrancy, or any explicit "Apple style / iOS style / macOS style" request. Also trigger when the user says "clean and minimal with blur", "frosted glass UI", or references visionOS, watchOS, or iOS 26's new liquid glass system. Do NOT use for generic material design, flat design without glass, or designs where the user has specified a non-Apple aesthetic.

0 installs
▌
Audit · yourpovv
Universal operational harness for any review, security pass, or audit prompt. Always load before running prompts/reviews/* or prompts/domains/* or a full PR review. Defines scope, mode (report vs fix), exclusions, severity, verification, and output shape. Stack-agnostic. Project-specific threat models live in prompts; this file is the safety contract that keeps agents from thrashing an entire monorepo.

0 installs
▌
Commits · yourpovv
Commit discipline for agent-assisted work: one commit per completed task, staging only that task's files, conventional message types, and never pushing without being asked. Use when an agent is about to commit, when a session has produced a pile of unstaged changes across several tasks, or when deciding who owns commits between a parent session and its sub-agents. Trigger on "commit this", "should I commit", "write a commit message", "squash these", "git add", or any task finishing with changes on disk. Harness-agnostic.

0 installs
▌
Prose · yourpovv
Prose quality for engineering writing: READMEs, docs, PR descriptions, commit messages, changelogs, release notes, and comment text. Use when writing or editing any of those, or when someone says a doc reads like AI wrote it, sounds generic, is too wordy, needs tightening, or asks to remove AI tells, slop, or filler. Single source of truth for prose rules in this pack. Does not score output against AI detectors and does not add fake inconsistency to look human.

0 installs
▌
Sub Agents · yourpovv
Use when delegating work to sub-agents, or deciding whether to delegate at all. Covers the model tier table (which class of model gets which class of work), the rule that every delegated call sets its model explicitly, cheapest-first escalation, and the cases where delegation costs more than it saves. Also covers how to write a brief an agent can act on, who owns commits, and verifying delegated work before accepting it. Trigger on "spawn an agent", "delegate this", "run these in parallel", "use a subagent", "fan this out", "which model should this run on", "brief a subagent", "should the agent commit", or any plan that hands work to more than one agent. Harness-agnostic.

0 installs
▌
Craft · yourpovv
Code and prose craft for maintainability and clarity. Use when reviewing naming, comments, structure, or written docs. Optimizes for humans who must debug and extend the system. Does not score "AI detection" and does not encourage fake inconsistency. Language-agnostic.

0 installs
▌
Errors · yourpovv
Use this skill for anything about failure, both how code should fail and how failures should read to a human. Part A covers Robert C. Martin's ("Uncle Bob") error-handling principles from Clean Code: exceptions over return codes, try-catch-finally first, providing context, defining exceptions by the caller's needs, the Special Case pattern, and never returning or passing null. Part B covers user-facing error messages: the three laws (what / why / action), severity levels, copy rules, and accessibility. Trigger on "handle this error", "this exception is useless", "should I return null", "improve this error message", "write an error state", or any review of failure code or copy. Language- and framework-agnostic.

0 installs
▌
Claude Folder · yourpovv
Use when setting up or changing a project's Claude Code configuration: what belongs in CLAUDE.md versus CLAUDE.local.md, what each directory under .claude/ actually does, how hooks get registered, and what a minimal new project needs. Trigger on "set up .claude", "add a hook", "what goes in settings.json", "make a slash command", "add a project skill", "why isn't my hook firing", "CLAUDE.md vs CLAUDE.local.md", or scaffolding agent config for a new repo. Tooling reference, not a code standard.

0 installs
▌
Context Budget · yourpovv
Where an agent session's tokens actually go, and which levers move the number. Covers the startup floor (everything always-loaded is billed on every single call), prompt caching as a prefix match and what silently invalidates it, why switching models mid-session is the most expensive habit there is, and why output is the costliest token you can spend. Use when a session feels expensive, when usage limits keep getting hit, when cache hit rate is low, or when deciding what belongs in always-loaded context. Trigger on "reduce token usage", "why is this so expensive", "hitting my limits", "prompt caching", "cache hit rate", "context is full", "should I compact", "trim CLAUDE.md". Harness-agnostic.

0 installs
▌
Uncle Bob · yourpovv
Robert C. Martin's craft and professionalism applied as methodology, not as a report about any one repository. Use when reviewing structure, naming, comments, architecture seams, TDD discipline, or professional scope decisions. Pair with standards/Clean-Code/ for mandatory lesson standards (01–41), standards/Principles.md for the broader handbook, and skills/engineering/errors/SKILL.md for failure handling. Language- and framework-agnostic. Never treat paths or product names in other project notes as facts about the current tree.

0 installs
▌
Create Readme · yourpovv
Write or rewrite a project README from the actual tree, never from a generic template. Stack-agnostic discovery process. Trigger when asked to create, rewrite, or fix onboarding docs. Verify every claim against opened files.

0 installs
▌
Necessary Comments · yourpovv
Robert C. Martin's "Necessary Comments" rule: comments are a last resort, not a default. Use when writing, reviewing, or stripping comments; when deciding whether an explanation belongs in prose or in a rename/extraction; or when a reviewer flags a comment as narration, noise, or non-local information. Pairs with skills/engineering/craft/SKILL.md (comment quality) and skills/engineering/uncle-bob/SKILL.md (Clean Code methodology). Language-agnostic.

0 installs
▌
Web SEO · yourpovv
Use this skill when making a website discoverable and shareable: meta tags, Open Graph and Twitter cards, canonical URLs, robots.txt, sitemap.xml, JSON-LD structured data, per-route metadata in a single-page app, and soft-404 handling. Covers the traps that silently break sharing (relative og:image, duplicated meta tags, SPA catch-all rewrites returning 200, CSP and inline JSON-LD) and the rule that every URL-bearing artifact must derive from one build-time constant. Trigger on "add SEO", "SEO audit", "og:image not showing", "link preview is broken", "add structured data", "rich results", "sitemap", "robots.txt", "canonical", "meta description", "share preview", or any pre-launch checklist for a public site. Framework-agnostic; build-tool notes for Vite, Next.js, and static hosts.

0 installs

13 published skills