kellymears
- 21 skills
- 0 followers
- 11 hours ago last updated
- ▌ Sprint Worker · kellymearsBatch-process GitHub issues using parallel agents. Use when the user wants to automate implementation of a set of issues.
- ▌ Version · kellymearsBump plugin versions in this repo's .claude-plugin/marketplace.json after making changes. Detects which plugins were modified, determines the appropriate semver bump (major, minor, or patch) from commit history, updates the manifest, and syncs project documentation (README plugin table, site homepage) with the manifest. Use when the user wants to bump versions, update plugin versions, or says "version bump". Also trigger when the user says "bump changed plugins", "update versions", "bump versions", or anything about versioning plugins after making changes — even just "version" or "bump".
- ▌ CLI · kellymears bundleCLI design best practices based on clig.dev — covers argument/flag design, help text, output formatting, error handling, configuration, signals, and robustness. Use this skill when building CLI tools, adding commands or flags, designing help output, formatting terminal output, handling CLI errors, reviewing CLI UX, or making any decisions about how a command-line program interacts with its users. Also trigger when working with argument parsers (yargs, commander, clap, cobra, click, argparse), exit codes, stdin/stdout patterns, progress indicators, or interactive prompts. If the user is building anything that runs in a terminal, this skill probably applies.
- ▌ Ink · kellymears bundleBest practices for building terminal UIs with Ink (React for CLIs). Use this skill when writing Ink components, laying out terminal interfaces with Box/Text, handling keyboard input, building animations, or setting up a new Ink project. Triggers on: Ink components (Box, Text, Transform, Static, Newline), ink imports, terminal UI layout, CLI component architecture, useInput/useApp hooks, or any React-in-the-terminal work. Also use when the user mentions building a CLI with React, terminal rendering, or references the ink npm package.
- ▌ Gist · kellymearsManage GitHub gists — create, list, view, edit, and delete. Use this skill when the user wants to create a gist, share a snippet, save code to a gist, list their gists, view or read a gist, edit/update a gist, or delete one. Also triggers when the user pastes code and asks to "gist this", "share this snippet", or "save this somewhere". Gists are created as **private** (secret) by default — only made public when the user explicitly asks.
- ▌ Git Pr · kellymearsOpen a pull request against the main branch with a conventional commit title and structured body. Use when the user wants to open a PR, create a pull request, submit changes for review, or share a branch with their team. Triggers on phrases like "open a PR", "create a pull request", "submit this for review", "PR this", "send a PR", or any request to open a pull request on GitHub. Also triggers when the user invokes /git:commits or asks to push and open a PR after committing.
- ▌ Comms · kellymears bundleDraft human-facing communications — emails, Slack messages, blog posts, and general markdown — in the user's authentic voice. Use this skill whenever the user asks to write, draft, or compose any message intended for other people: emails, Slack messages, blog posts, announcements, PR descriptions, issue writeups, documentation prose, or any text where voice and tone matter. Also trigger when the user asks to "write something up", "send a message", "draft a response", "put together an email", or any variation of composing human-readable text that isn't pure code.
- ▌ Git Work · kellymearsStart working on an issue, PR, or idea — handles branch creation, context switching, and uncommitted changes. Use when the user wants to work on something, pick up an issue, switch to a PR, resume work, start a task, or context switch. Triggers on phrases like "work on", "pick up", "start", "switch to", "resume", "grab that issue", "context switch", "let me work on #N", "check out PR #N", or any request to begin or resume work on a specific item.
- ▌ Git Issue · kellymearsCreate a GitHub issue from a PR, Slack message, or ad-hoc description. Use when the user wants to file an issue, track a bug, request a feature, or turn a conversation into a trackable work item. Triggers on phrases like "create an issue", "file a bug", "open an issue for this", "track this", "make a ticket", "turn this into an issue", or any request to create a GitHub issue. Also triggers when the user pastes a Slack message, PR URL, or describes a problem and wants it tracked.
- ▌ Git Commits · kellymearsOrganize messy git changes into clean, well-scoped conventional commits. Use when the user wants to clean up their commit history, organize uncommitted changes into logical commits, squash or reorganize recent commits, or curate a changeset before pushing. Triggers on phrases like "clean up my commits", "organize these changes", "split this into commits", "curate history", "make my commits cleaner", or any request to restructure git history into atomic, meaningful units.
- ▌ Sim Problem · kellymears bundleLive coding challenge simulator — 55-minute pair programming sessions with TypeScript. Trigger on: 'coding challenge', 'pair programming sim', 'mock interview', 'live coding practice', 'problem sim', 'challenge me', or anything about simulating a live coding interview or pair programming exercise. Also trigger on: 'done', 'ready for next', 'finished' (to advance to next phase), 'status', 'timer', 'how much time' (to check progress), and 'abandon', 'cancel', 'end session' (to stop). Any trigger while a session is active resumes the session. Proactively use this skill when the user wants realistic coding interview practice that goes beyond algorithmic puzzles.
- ▌
- ▌ Grilling · kellymearsGrill 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.
- ▌ Obsidian · kellymearsCreate a document in an Obsidian vault. Supports all vaults synced via iCloud. Use this skill when the user asks to create a note, write to Obsidian, save to their vault, or any variation of composing a markdown note for Obsidian.
- ▌ Research · kellymears bundleDeep-dive research across any domain — science, history, law, medicine, policy, philosophy, finance, technology, or anything else. Use this skill when the user asks to research a topic, look into something, do a deep dive, fact check a claim, investigate a question, prepare a briefing, or wants to understand "what do we know about X." Also triggers on phrases like "what's the evidence for", "is it true that", "summarize the research on", "compare perspectives on", or any request for rigorous, multi-source analysis with cited evidence. Produces reports with multiple viewpoints, plausibility tiers, qualitative confidence assessment, and verification-tagged citations.
- ▌ Seniordev · kellymearsForces the laziest solution that actually works — simplest, shortest, most minimal. Channels a senior dev who has seen everything: question whether the task needs to exist at all (YAGNI), reach for the standard library before custom code, native platform features before dependencies, one line before fifty. Supports intensity levels: lite, full (default), ultra. Use whenever the user says "seniordev", "be lazy", "lazy mode", "simplest solution", "minimal solution", "yagni", "do less", or "shortest path" — and whenever they complain about over-engineering, bloat, boilerplate, or unnecessary dependencies.
- ▌ Sim Progressive · kellymears bundleInteractive test proctor for progressive coding assessments. Trigger on: 'new sim', 'generate a problem', 'practice problem', 'another simulation', or anything about creating timed coding exercises. Also trigger on: 'done', 'finished', 'next level', 'tests pass', 'I'm done' (to verify and advance), 'status', 'timer', 'how am I doing', 'where am I' (to check progress), and 'abandon', 'cancel sim', 'start over' (to end session). Any trigger while a session is active resumes the session. Generates progressive L1-L4 TypeScript projects incrementally, one level at a time, with vitest tests.
- ▌ Tailshare · kellymearsPublish static files (HTML pages, reports, demos, build output) to the tailnet with the `tailshare` CLI. Use when the user says "tailshare this", "host this on the tailnet", "put this on cachy", "share this page", "publish this html", or wants a shareable https URL for a local directory. Also covers listing and removing existing shares. Not for GitHub gists (use /gist) or Claude Artifacts.
- ▌ Remote Run · kellymearsExecute commands, builds, test suites, and long-running jobs headlessly on a remote dev box over SSH instead of the local machine. Use this skill when the user asks to run something "on the box", "on <hostname>", "remotely", "headlessly", to "offload" heavy work, or when a task is clearly better suited to a beefier remote machine (docker stacks, full test suites, asset builds, local LLM inference). Host details come from a per-user config file, so the skill works for any user with any remote machine.
- ▌ Seniordev Help · kellymearsQuick-reference card for all seniordev modes, skills, and commands. One-shot display, not a persistent mode. Trigger: /seniordev-help, "seniordev help", "what seniordev commands", "how do I use seniordev".
- ▌ Seniordev Review · kellymearsCode review focused exclusively on over-engineering. Finds what to delete: reinvented standard library, unneeded dependencies, speculative abstractions, dead flexibility. One line per finding: location, what to cut, what replaces it. Use when the user says "review for over-engineering", "what can we delete", "is this over-engineered", "simplify review", or invokes /seniordev-review. Complements correctness-focused review — this one only hunts complexity.