ryanportfolio
UserSTK (Session Token Killer) Claude Code hook that clamps oversized Read tool results into line-numbered outlines. RTK kills tokens per command, STK per session. 85% of my oversized agent context was file reads.
Categories
Indexed Skills (26)
purposeful-writing
Use when drafting or revising prose for a reader: application answers, emails, essays, bios, cover letters, proposals, memos, reports, product copy, speeches, or when a draft reads as machine-made or must match a writer's own voice.
writing-plans
Use when you have a spec or requirements for a multi-step task, before touching code
writing-skills
Use when creating new skills, editing existing skills, or verifying skills work before deployment
brainstorming
Use when brainstorming or designing a product, interface, workflow, architecture, or behavior change with unresolved goals or material tradeoffs; not for routine or fully specified work.
caveman
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy.
fable-mode
Use proactively for hard layered work with dependent steps, load-bearing unknowns, repeated failures, or verification-sensitive handoff; also when the user asks for Fable mode.
forge-repo-ui-skill
Use when the user wants a repository-specific UI or design skill synthesized from current agent skills; not for ordinary UI implementation or backend-only work.
humanizer
Use when the user asks to humanize, de-AI, de-slop, voice-match, or review prose for AI tells before publishing.
optimize-context
Use when the user asks to reduce per-turn context or token load, trim kernels, skills, or connectors, or propagate a generic context optimization to the starter.
arena
Spawn N parallel candidate attempts at one task, pick the strongest as base, graft the losers' best parts in. Use when the user says $arena, "arena this", or when one attempt at a non-trivial artifact would lock in the wrong shape.
automate-me
Use for "automate me", "$automate-me", "create/update my -mode skill", or "turn my preferences / working style into a skill". Mines the current project's transcripts plus direct questions, then drafts a personal <handle>-mode skill.
unslop
Always-on AI-tell stripper: apply its pattern check to everything written for humans (chat prose, commits, PR bodies, docs, UI text). Also use when the user says $unslop, "unslop this", or points at text or a file to clean.
verify-this
Verify a claim with fresh local evidence: restate it falsifiably, capture baseline and treatment, compare, return VERIFIED, NOT VERIFIED, or INCONCLUSIVE. Use for $verify-this, "prove it works", "did this fix it", "show me the evidence".
babysit-ci
Watch a PR's checks and iterate on failures until green. Use for /babysit-ci, "watch CI", "fix CI", "get the checks green", or when a PR is waiting on failing or pending checks.
advocate
Use only when the user explicitly invokes /advocate to challenge a change just made before it lands. Do not trigger from natural-language requests.
bro
Restate the assistant's last message in plain human language, no jargon. Use when the user says /bro, "in plain english", "dumb it down", or "what does that actually mean".
addskill
Use when the user asks to add, install, or create a repo-local skill that must work in future Claude Code and Codex sessions.
enhance-prompt
Use when the user asks to rewrite a rough request into a polished, copy/paste-ready prompt for another agent or a fresh session.
handoff-audit
Use when the user asks for a self-contained audit prompt to paste into a separate fresh session for independent verification.
impartial-review
Use when the user asks to review, audit, or stress-test recent code changes with fresh independent agents; requires exposed multi-agent tools or an authenticated Codex CLI.
init-project
Use once in a spawned starter repo when the user asks to initialize or configure it, or when FILL IN markers remain; never auto-run in a claude-starter template checkout.
lab
Use when the user explicitly asks to lab or prototype a visual, UI, motion, or game-feel element with live tuning before production implementation.
merge
Use only when the user explicitly asks to enable session-wide automatic commit, push, PR, and merge; not for one-shot shipping requests.
recall
Use before unfamiliar project-area edits, when the user asks what the project knows or its pitfalls, or when saving durable project-specific learning.
sync-starter
Use when the user asks to pull template improvements into a spawned repo, compare starter drift, or push a generic improvement back to the starter.
why
Use only when the user explicitly invokes /why to challenge the assistant's immediately prior recommendation; never trigger from ordinary why questions or paraphrases.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.