agentsclimarketplace

The catalog

610,677 rows, by stacks then stars

  • Regression diagnostics

    sshtomar/claude-code-skills-social-science/skills/regression-diagnostics Skill

    19★ repo

    Comprehensive regression model diagnostics and assumption checking. Use when validating regression models, checking assumptions (linearity, homoskedasticity, normality, independence), detecting outliers/influence, testing multicollinearity, or when user mentions residuals, heteroskedasticity, VIF, Cook's distance, or diagnostic plots.

  • Visualization

    sshtomar/claude-code-skills-social-science/skills/visualization Skill

    19★ repo

    Publication-quality statistical visualization with mandatory best practices. Use when creating plots, charts, figures, or any data visualization. Enforces accessibility, uncertainty display, proper labeling, and statistical accuracy.

  • Concise

    o4f6bgpac3/concise/plugins/concise/skills/concise Skill

    19★ repo

    Concise communication mode. Cuts ~60-70% of output tokens while keeping natural, readable English. Drops filler, hedging, and pleasantries but maintains grammar and sentence flow. Elaborate on request -- ask for detail and get it, then auto-return to concise. Use when user says "concise mode", "be concise", "less verbose", or invokes /concise. Also triggers when user requests token efficiency with readability.

    The same file is in 2 other repositories

  • Threads hook extractor

    sergebulaev/threads-skills/.codex-marketplace/threads-skills/skills/threads-hook-extractor Skill

    19★ repo

    Reverse-engineer the hook from a viral Threads post or thread URL. Identifies which of the 10 canonical 2026 Threads formulas it uses (warm contrarian, data-point, build-in-public, quote-post, mini-list, relatable, listicle, story, curiosity-gap, how-I teardown), explains why it worked, and returns a blank template mapped to your topic with its primary goal (replies, reposts, likes, quotes). Use to learn from a post you admire. Not for writing your own (use threads-post-writer).

  • Threads humanizer

    sergebulaev/threads-skills/.codex-marketplace/threads-skills/skills/threads-humanizer Skill

    19★ repo

    Scrub AI tells from any Threads post or thread draft, or audit a finished draft against the 2026 Threads checklist. Strips em dashes, AI vocabulary (leverage, fundamentally, delve, harness), rule-of-three lists, and uniform post rhythm, then adds human fingerprints. Includes a --mode audit pre-publish check (500-char fit, hook, one-hashtag cap, link placement, warm tone). Triggers on humanize, de-AI Threads post, audit before posting. Not for writing from scratch (use threads-post-writer).

  • Threads post writer

    sergebulaev/threads-skills/.codex-marketplace/threads-skills/skills/threads-post-writer Skill

    19★ repo

    Draft a single Threads post or a multi-post thread using a 2026 Threads hook formula (warm contrarian, data-point, build-in-public, quote-post, mini-list, relatable, listicle, story, curiosity-gap, how-I teardown), picked by goal (replies, reposts, likes, quotes). Respects the 500-char limit and one-hashtag cap, runs the humanizer pass, and publishes via Publora, which auto-splits long content into a thread. Not for auditing a draft (use threads-humanizer) or hook teardown (use threads-hook-extractor).

  • Threads profile optimizer

    sergebulaev/threads-skills/.codex-marketplace/threads-skills/skills/threads-profile-optimizer Skill

    19★ repo

    Audit and rewrite a Threads (Meta) profile end-to-end for 2026: profile photo, name with a searchable keyword, @handle, bio (150 chars, warm and specific), link, pinned post, and the connected-Instagram cross-pull that feeds Threads discovery. Triggers on "review my Threads profile", "fix my Threads bio", "what to pin on Threads", and "profile audit". Turns a default profile into one that converts visitors into followers. Not for writing posts (use threads-post-writer).

  • Threads reply drafter

    sergebulaev/threads-skills/.codex-marketplace/threads-skills/skills/threads-reply-drafter Skill

    19★ repo

    Threads marketing skills for Claude Code and Codex: posts, multi-post threads, hooks, replies, and a weekly plan in your voice. Publish via Publora. Open source, MIT. Content engineering by Creative Content Crafts.

  • Threads repurposer

    sergebulaev/threads-skills/.codex-marketplace/threads-skills/skills/threads-repurposer Skill

    19★ repo

    Repurpose existing content into a native Threads post or thread. Take a LinkedIn post, X thread, blog, YouTube script, or newsletter and rewrite it for Threads: warm the tone, de-corporate it, refit to a short post or light thread, rebuild the hook to clear the soft fold, strip off-platform artifacts, run the humanizer, publish via Publora on approval. Not for writing from scratch (use threads-post-writer), auditing a draft (use threads-humanizer), or a hook teardown (use threads-hook-extractor).

  • Threads audience insights

    sergebulaev/threads-skills/skills/threads-audience-insights Skill

    19★ repo

    Read your Threads (Meta) audience and niche from real data. Scan a niche query or hashtag for the top posts right now with likes, replies, reposts, and quotes, and pull a profile (yours or a competitor) for follower count, bio, verified status, and recent posts with engagement. Powered by Apify, no login. Triggers on "analyze Threads", "what is working on Threads", "top posts for", "competitor Threads profile", "niche scan", "follower count". Not for writing posts (use threads-post-writer).

  • Threads content planner

    sergebulaev/threads-skills/skills/threads-content-planner Skill

    19★ repo

    Generate a weekly Threads (Meta) content plan from a theme, audience, and content pillars. Produces per-day recommendations (single post vs thread, Threads hook formula, angle, posting time, primary goal), a single-to-thread mix, daily reply and quote-post targets, and a goal-mix balance check across replies, reposts, likes, and quotes. Use when the user wants to plan a week of Threads content instead of ad-hoc posting. Not for drafting one post or thread (use threads-post-writer).

  • Threads hook extractor

    sergebulaev/threads-skills/skills/threads-hook-extractor Skill

    19★ repo

    Reverse-engineer the hook from a viral Threads post or thread URL. Identifies which of the 10 canonical 2026 Threads formulas it uses (warm contrarian, data-point, build-in-public, quote-post, mini-list, relatable, listicle, story, curiosity-gap, how-I teardown), explains why it worked, and returns a blank template mapped to your topic with its primary goal (replies, reposts, likes, quotes). Use to learn from a post you admire. Not for writing your own (use threads-post-writer).

  • Threads humanizer

    sergebulaev/threads-skills/skills/threads-humanizer Skill

    19★ repo

    Scrub AI tells from any Threads post or thread draft, or audit a finished draft against the 2026 Threads checklist. Strips em dashes, AI vocabulary (leverage, fundamentally, delve, harness), rule-of-three lists, and uniform post rhythm, then adds human fingerprints. Includes a --mode audit pre-publish check (500-char fit, hook, one-hashtag cap, link placement, warm tone). Triggers on humanize, de-AI Threads post, audit before posting. Not for writing from scratch (use threads-post-writer).

  • Threads post writer

    sergebulaev/threads-skills/skills/threads-post-writer Skill

    19★ repo

    Draft a single Threads post or a multi-post thread using a 2026 Threads hook formula (warm contrarian, data-point, build-in-public, quote-post, mini-list, relatable, listicle, story, curiosity-gap, how-I teardown), picked by goal (replies, reposts, likes, quotes). Respects the 500-char limit and one-hashtag cap, runs the humanizer pass, and publishes via Publora, which auto-splits long content into a thread. Not for auditing a draft (use threads-humanizer) or hook teardown (use threads-hook-extractor).

  • Threads profile optimizer

    sergebulaev/threads-skills/skills/threads-profile-optimizer Skill

    19★ repo

    Audit and rewrite a Threads (Meta) profile end-to-end for 2026: profile photo, name with a searchable keyword, @handle, bio (150 chars, warm and specific), link, pinned post, and the connected-Instagram cross-pull that feeds Threads discovery. Triggers on "review my Threads profile", "fix my Threads bio", "what to pin on Threads", and "profile audit". Turns a default profile into one that converts visitors into followers. Not for writing posts (use threads-post-writer).

  • Threads reply drafter

    sergebulaev/threads-skills/skills/threads-reply-drafter Skill

    19★ repo

    Threads marketing skills for Claude Code and Codex: posts, multi-post threads, hooks, replies, and a weekly plan in your voice. Publish via Publora. Open source, MIT. Content engineering by Creative Content Crafts.

  • Threads repurposer

    sergebulaev/threads-skills/skills/threads-repurposer Skill

    19★ repo

    Repurpose existing content into a native Threads post or thread. Take a LinkedIn post, X thread, blog, YouTube script, or newsletter and rewrite it for Threads: warm the tone, de-corporate it, refit to a short post or light thread, rebuild the hook to clear the soft fold, strip off-platform artifacts, run the humanizer, publish via Publora on approval. Not for writing from scratch (use threads-post-writer), auditing a draft (use threads-humanizer), or a hook teardown (use threads-hook-extractor).

  • Facebook skills

    sergebulaev/facebook-skills/.codex-marketplace/facebook-skills Skill

    19★ repo

    Plan, draft, audit, and publish posts for a Facebook Page. Use when the user wants to write a short punchy Page post or a longer story post, remove AI tells from a draft, reverse-engineer the hook from a high-share Page post, draft replies to comments on their Page, or plan a week of Facebook Page content. Page posts publish via the Publora API. User provides notes or a Facebook Page post URL, the skill drafts, the user approves, then it publishes.

  • Facebook skills

    sergebulaev/facebook-skills Skill

    19★

    Plan, draft, audit, and publish posts for a Facebook Page. Use when the user wants to write a short punchy Page post or a longer story post, remove AI tells from a draft, reverse-engineer the hook from a high-share Page post, draft replies to comments on their Page, or plan a week of Facebook Page content. Page posts publish via the Publora API. User provides notes or a Facebook Page post URL, the skill drafts, the user approves, then it publishes.

  • Fetch investments

    ya5huk/findash/skills/fetch-investments Skill

    no license19★ repo

    Use when the user says "fetch investments", "fetch ibkr", "fetch interactive brokers", "pull portfolio", "fetch brokerage", "snapshot ibkr", or any portfolio-snapshot equivalent — and as the best-effort IBKR step inside `daily-run`. The connector authenticates only in interactive sessions, so unattended runs typically skip it with a warning. Ingests the IBKR connector's trade history into the `trades` ledger on a user-mapped account (so it stops needing trade screenshots), plus a positions snapshot used for reconciliation + new-user bootstrap. Skips gracefully — best-effort, like a failed bank source — when the connector isn't connected.

  • Findash doctor

    ya5huk/findash/skills/findash-doctor Skill

    no license19★ repo

    Use when the user says "doctor", "finance doctor", "check finance setup", "what's missing", or any "is everything set up?" equivalent. Audits binaries, configs, secrets, npm deps, vendor assets, DB, live Drive connectivity, and Chromium profiles. Auto-fixes safe local gaps and prints exact commands for everything that needs human action.

  • Render finance dashboard

    ya5huk/findash/skills/render-finance-dashboard Skill

    no license19★ repo

    Use when the user says "render dashboard", "show my finances", "build the dashboard", or any morning-summary equivalent. Reads SQLite, fetches live prices/FX from Yahoo Finance, fills the HTML template, and writes a self-contained dashboard to `output/dashboard.html`.

  • Setup

    ya5huk/findash/skills/setup Skill

    no license19★ repo

    Use when the user says "set up findash", "onboard", "first-time setup", "get findash running", "configure findash", or is installing the plugin for the first time. Runs findash-doctor's safe auto-fixes, then guides the human through the steps only they can do — creating `.secrets/findash`, the rclone Google Drive OAuth, the Telegram bot, and the one-time bank-scraper browser seeding.

  • Sync finance data

    ya5huk/findash/skills/sync-finance-data Skill

    no license19★ repo

    Use when the user says "sync finance", "sync my finance", "ingest new docs", or any morning-update equivalent. Gathers new Drive drops into local staging (best-effort), ingests everything staged — bank fetch pairs + manual drops — into the SQLite database, sorts `dump/` drops into their archetype folders on Drive, and backs the database up to Drive weekly.

  • Executing plans

    CodingCossack/agent-skills-library/skills/executing-plans Skill

    no license19★ repo

    Disciplined plan execution for implementation tasks. Use when executing a saved implementation plan, following step-by-step instructions from a plan document.

    The same file is in 7 other repositories

  • Finishing a development branch

    CodingCossack/agent-skills-library/skills/finishing-a-development-branch Skill

    no license19★ repo

    Git branch completion workflow. Use when implementation is complete, tests pass, and a feature branch needs to be integrated via merge, pull request, or cleanup.

    The same file is in 8 other repositories

  • Receiving code review

    CodingCossack/agent-skills-library/skills/receiving-code-review Skill

    no license19★ repo

    Assesses and responds to incoming code review feedback on PRs (reviewer comments, requested changes), especially when suggestions are unclear, technically questionable, or scope-expanding. Use before implementing review suggestions to align on intent and keep changes minimal.

    The same file is in 8 other repositories

  • Requesting code review

    CodingCossack/agent-skills-library/skills/requesting-code-review Skill

    no license19★ repo

    Use when you need to request a code review for a PR/MR and want a consistent review brief (context, scope, risk areas, test instructions, acceptance criteria) before merge.

    The same file is in 8 other repositories

  • Subagent driven development

    CodingCossack/agent-skills-library/skills/subagent-driven-development Skill

    no license19★ repo

    Sequential subagent execution with two-stage review gates for implementation plans. Use when executing multi-task plans in current session, when tasks need fresh subagent context to avoid pollution, when formal review cycles (spec compliance then code quality) are required between tasks, or when you need diff-based validation of each task before proceeding.

    The same file is in 8 other repositories

  • Systematic debugging

    CodingCossack/agent-skills-library/skills/systematic-debugging Skill

    no license19★ repo

    Root cause analysis for debugging. Use when bugs, test failures, or unexpected behavior have non-obvious causes, or after multiple fix attempts have failed.

    The same file is in 8 other repositories

  • Test driven development

    CodingCossack/agent-skills-library/skills/test-driven-development Skill

    no license19★ repo

    Red-green-refactor development methodology requiring verified test coverage. Use for feature implementation, bugfixes, refactoring, or any behavior changes where tests must prove correctness.

    The same file is in 8 other repositories

  • Using git worktrees

    CodingCossack/agent-skills-library/skills/using-git-worktrees Skill

    no license19★ repo

    Git worktree–based workspace isolation for parallel or non-disruptive development. Use when work must occur without modifying or interfering with the current working tree.

    The same file is in 8 other repositories

  • Using superpowers

    CodingCossack/agent-skills-library/skills/using-superpowers Skill

    no license19★ repo

    Meta-skill enforcing skill discovery and invocation discipline through mandatory workflows. Use when starting any conversation to check for relevant skills before any response, ensuring skill-first workflow before proceeding.

    The same file is in 8 other repositories

  • Verification before completion

    CodingCossack/agent-skills-library/skills/verification-before-completion Skill

    no license19★ repo

    Verification discipline for completion claims. Use when about to assert success, claim a fix is complete, report tests passing, or before commits and PRs. Enforces evidence-first workflow.

    The same file is in 8 other repositories

  • Writing plans

    CodingCossack/agent-skills-library/skills/writing-plans Skill

    no license19★ repo

    Structured implementation planning for multi-step development tasks. Use when you have a spec or requirements and need to break work into executable steps.

    The same file is in 8 other repositories

  • Writing skills

    CodingCossack/agent-skills-library/skills/writing-skills Skill

    no license19★ repo

    Use when creating new skills, editing existing skills, or verifying skills work before deployment

    The same file is in 42 other repositories

  • Coverage report

    livlign/claude-skills/plugins/dotnet-coverage-kit/skills/coverage-report Skill

    19★ repo

    A Claude Code plugin marketplace for open-source maintainers — README heroes, README audits, and .NET test-coverage backfills.

  • Generate tests

    livlign/claude-skills/plugins/dotnet-coverage-kit/skills/generate-tests Skill

    19★ repo

    A Claude Code plugin marketplace for open-source maintainers — README heroes, README audits, and .NET test-coverage backfills.

  • Readme doctor

    livlign/claude-skills/plugins/repo-doctor/skills/readme-doctor Skill

    19★ repo

    Audit a GitHub repo's README against best-practice patterns and produce a prioritized punch list of fixes. Runs a structured review covering hero presence, install-to-first-success length, "what is this in one sentence" clarity, audience-jargon match, scannability, and drift signals (stale versions, dead links, badge sprawl). Read-only diagnostic; opens a PR only when the user explicitly asks.

  • Repo visuals retro

    livlign/claude-skills/plugins/repo-visuals/skills/repo-visuals-retro Skill

    19★ repo

    Retrospective meta-skill for the `repo-visuals` skill. Reads accumulated evaluation logs from past runs, spots patterns (recurring low-score criteria, repeated iteration failures, unsatisfied requests), consults other expert skills (skill-creator, frontend-design, etc.) where relevant, and proposes concrete edits to `repo-visuals/SKILL.md` as a reviewable diff. Runs on-demand, not per run.

  • Repo visuals

    livlign/claude-skills/plugins/repo-visuals/skills/repo-visuals Skill

    19★ repo

    Create hero visuals — animated GIF, static PNG, or animated SVG — for GitHub repositories. Runs a structured discovery conversation (scan repo → recommend format → propose creative scenarios → agree on a brief), then designs bespoke HTML/SVG, previews it in the browser, and exports. Use when the user asks for a README hero, repo banner, README image, GitHub header, social preview card, repo demo GIF, hero image, OG image, project screenshot, repository showcase, or any "image at the top of the README".

  • Abrevia

    iamursky/sokrati/skills/abrevia Skill

    19★ repo

    Edita y mejora textos profesionales en español aplicando los principios del estilo informativo (infoestilo) — un enfoque editorial centrado en el lector desarrollado por Maxim Iliajov. Se activa cuando el usuario pide editar, revisar, depurar o mejorar cualquier texto profesional: correos, landing pages, páginas «Quiénes somos», notas de prensa, currículums, cartas de presentación, informes, presentaciones, correos en frío, publicaciones en redes o copy corporativo. También se activa con menciones de «estilo informativo», «infoestilo», «Iliajov», «Ilyahov», «Glavred», «palabras de relleno», «muletillas», «lenguaje administrativo», «lenguaje burocrático», o cuando se pide quitar la «paja», eliminar clichés, hacer el texto «más fuerte» o reescribirlo en «lenguaje llano» o «lenguaje claro». Funciona tanto para edición completa como para retroalimentación puntual. Sirve para las variantes peninsular y latinoamericana, priorizando la versión panhispánica neutra.

  • Escurca

    iamursky/sokrati/skills/escurca Skill

    19★ repo

    Edita i millora textos professionals i de negoci en català fent servir els principis de l'estil informatiu —una manera d'editar centrada en el lector desenvolupada per Maxim Ilyahov. L'habilitat s'activa quan l'usuari demana editar, revisar, netejar, escurçar o millorar qualsevol text professional: correus electrònics, pàgines de destinació («landing pages»), pàgines «Qui som», notes de premsa, currículums, cartes de presentació, informes, presentacions, missatges en fred, publicacions a xarxes socials o qualsevol mena de text corporatiu. També s'activa quan es mencionen «estil informatiu», «infostyle», «Ilyahov», «Glavred», «paraules buides», «paraules mosca», «llenguatge burocràtic», «cremarcanvi», «cul de sac lingüístic», o quan es demana treure la palla, eliminar tòpics, fer el text «més fort» o reescriure'l en «llenguatge planer». Funciona tant per a una reedició completa com per a una crítica puntual. Es pot aplicar a textos en castellà, anglès o rus si l'usuari ho demana explícitament.

  • Kuerzen

    iamursky/sokrati/skills/kuerzen Skill

    19★ repo

    Redigiert und verbessert deutschsprachige Geschäfts- und Fachtexte nach den Prinzipien des Informationsstils — einem leserzentrierten Redaktionsansatz von Maxim Iljachow. Aktiviert sich, wenn der Nutzer einen Geschäftstext bearbeiten, prüfen, kürzen oder verbessern lassen möchte: E-Mails, Landingpages, Unternehmensbeschreibungen, Pressemitteilungen, Lebensläufe, Anschreiben, Berichte, Präsentationen, Kaltakquise-Mails, Social-Media-Texte. Wird ebenfalls ausgelöst durch Stichworte wie „Informationsstil", „Iljachow", „Ilyahov", „Glavred", „Füllwörter", „Floskeln", „Behördendeutsch", „Nominalstil", „Denglisch", oder bei Bitten wie „mach den Text knackiger", „bring das auf den Punkt", „in einfache Sprache übersetzen", „Marketing-Sprech rausnehmen". Funktioniert sowohl für komplette Überarbeitungen als auch für gezieltes Feedback ohne Umschreiben. Kann auf russische oder englische Texte angewandt werden, wenn der Nutzer das ausdrücklich wünscht.

  • Shorten

    iamursky/sokrati/skills/shorten Skill

    19★ repo

    Edits and improves English business and professional writing using principles of information style — a reader-first editing approach developed by Maxim Ilyahov. The skill activates when the user asks to edit, review, clean up, tighten, or improve any business text: emails, landing pages, about pages, press releases, resumes, reports, slide decks, cold emails, social posts, or any professional copy. Also triggers on mentions of "information style", "infostyle", "Ilyahov", "Glavred", "red-flag words", "filler words", "bureaucratese", or on requests to cut the fluff, kill the clichés, make text "stronger", or rewrite in "plain language". Works for full editing passes and for targeted feedback. Can be applied to Russian text if the user explicitly asks.

  • Sokrati

    iamursky/sokrati/skills/sokrati Skill

    19★ repo

    Редактирует и улучшает русский деловой и профессиональный текст, опираясь на идеи информационного стиля Максима Ильяхова. Навык срабатывает, когда пользователь просит отредактировать, проверить, почистить или улучшить любой деловой текст на русском — письма, лендинги, описания компаний, пресс-релизы, резюме, отчёты, презентации, холодные письма, тексты для соцсетей и любые профессиональные тексты. Также срабатывает при упоминании «информационный стиль», «инфостиль», «Ильяхов», «Главред», «стоп-слова», «канцелярит», или при просьбе убрать «воду», сделать текст «сильнее», переписать на «человеческий язык». Работает и с полной переработкой, и с точечной обратной связью. Может применяться к английскому тексту, если пользователь явно просит использовать подход Ильяхова.

  • Add

    pilotspace/ADD/add-method/skill/add Skill

    19★ repo

    ADD (AI-Driven Development) — a minimal, state-tracked workflow: the AI writes the code, the human owns direction and verification. Drives every feature through one lean PLAN.md: Specify → Plan → Tests & Scenarios → Build → Verify → Observe, red/green TDD built in. Use whenever a repo has `.add/`, or the user says "add", "start a task", "next phase", "specify this feature", "ADD method", "AI-driven development", or wants spec/tests-first discipline over vague-prompt coding. Also resumes work across sessions via `.add/state.json` (never re-read the whole repo).

  • Persona author

    pilotspace/ADD/add-method/skill/add/persona-author Skill

    19★ repo

    Author or improve an ADD-method persona file (a .add/personas/ slug.md) — the project-fit requirements LENS the ADD engine validates and the design/build/verify/advisor surfaces load. Use when adding a domain expert to the ADD roster, when the add-worker persona mode must DRAFT a persona because none fits the task kind, or when folding a retrospective into an existing persona. Produces a schema-valid persona (Identity, Critical Rules, Default Requirement, Success Metrics, plus recommended frontmatter and Abilities/Anti-patterns/Playbook) that carries the judgment layer of strong agent design: earned-perspective identity, bold-lead rules, the qualification gate, read-before-you-assert, failure-mode-aware metrics, defended budgets, and per-flow stances. Seeds a first draft from the teacher library or a sample subagent when a near-fit source exists, instead of a blank page.

  • Add

    pilotspace/ADD/add-method/src/add_method/_bundled/skill/add Skill

    19★ repo

    ADD (AI-Driven Development) — a minimal, state-tracked workflow: the AI writes the code, the human owns direction and verification. Drives every feature through one lean PLAN.md: Specify → Plan → Tests & Scenarios → Build → Verify → Observe, red/green TDD built in. Use whenever a repo has `.add/`, or the user says "add", "start a task", "next phase", "specify this feature", "ADD method", "AI-driven development", or wants spec/tests-first discipline over vague-prompt coding. Also resumes work across sessions via `.add/state.json` (never re-read the whole repo).

  • Persona author

    pilotspace/ADD/add-method/src/add_method/_bundled/skill/add/persona-author Skill

    19★ repo

    Author or improve an ADD-method persona file (a .add/personas/ slug.md) — the project-fit requirements LENS the ADD engine validates and the design/build/verify/advisor surfaces load. Use when adding a domain expert to the ADD roster, when the add-worker persona mode must DRAFT a persona because none fits the task kind, or when folding a retrospective into an existing persona. Produces a schema-valid persona (Identity, Critical Rules, Default Requirement, Success Metrics, plus recommended frontmatter and Abilities/Anti-patterns/Playbook) that carries the judgment layer of strong agent design: earned-perspective identity, bold-lead rules, the qualification gate, read-before-you-assert, failure-mode-aware metrics, defended budgets, and per-flow stances. Seeds a first draft from the teacher library or a sample subagent when a near-fit source exists, instead of a blank page.

  • Context diet

    Neeeophytee/ai-cost-cutter-skills/skills/context-diet Skill

    no license19★ repo

    Cut agent token spend by shrinking what enters the context window. Index the repo or corpus once and query it instead of re-reading files on every question. Use when the user complains their coding agent burns tokens, the context fills up fast, the same files get read repeatedly, or the bill scales with conversation length.

  • Free model triage

    Neeeophytee/ai-cost-cutter-skills/skills/free-model-triage Skill

    no license19★ repo

    Route high-volume, low-stakes triage (reading piles, inbox summaries, needs-reply flags) to a free model with a strict output schema. Use when the user wants one-line summaries of many items cheaply, asks to triage email, articles, or reports with AI, or wants to decide what's worth reading without paying premium rates for it.

  • Free tier batch plan

    Neeeophytee/ai-cost-cutter-skills/skills/free-tier-batch-plan Skill

    no license19★ repo

    Size a big one-time batch job against a free tier's rate limit and token budget BEFORE starting it, with a proven wall-clock ETA. Use when the user wants to label a dataset, summarize an archive, or process a large backlog for free (or on a tiny rate limit), or asks "will this finish overnight?"

  • Model bakeoff

    Neeeophytee/ai-cost-cutter-skills/skills/model-bakeoff Skill

    no license19★ repo

    Choose a model with evidence by running the few prompts that actually matter across candidate models inside a free tier's caps, picking by a stated criterion. Use when the user asks "which model should I use", wants to evaluate a newly launched model, or is choosing between models for a specific task.

  • Reasoning effort throttle

    Neeeophytee/ai-cost-cutter-skills/skills/reasoning-effort-throttle Skill

    no license19★ repo

    Stop paying for deep reasoning on easy turns by setting a modest default reasoning effort and escalating per task. Use when the user runs a reasoning model in an agent and the bill is dominated by output or thinking tokens, or asks about reasoning_effort, thinking budgets, or why a cheap model is still expensive to run.

  • Route cheap escalate hard

    Neeeophytee/ai-cost-cutter-skills/skills/route-cheap-escalate-hard Skill

    no license19★ repo

    Cut LLM spend by routing bulk work to a cheap model and escalating only the hard turns to a premium one. Use when the user says their AI bill is too high, asks to "use a cheaper model", or wants two-tier model routing without losing quality on the hard tasks.

  • Tested fallback

    Neeeophytee/ai-cost-cutter-skills/skills/tested-fallback Skill

    no license19★ repo

    Pin an open-weights fallback model with a tested-on date and real smoke prompts, so a pulled or deprecated model is a two-minute config swap instead of a lost week. Use when the user worries a model could vanish or be deprecated, builds anything important on one model, or asks about model failover and resilience.

  • Token receipts audit

    Neeeophytee/ai-cost-cutter-skills/skills/token-receipts-audit Skill

    no license19★ repo

    Attribute AI usage by tokens AND dollars so a high-volume cheap model is never mistaken for the expensive one. Use when the user asks where their AI spend actually goes, why the bill is high, which model is costing the most, or wants a usage audit across agents and models.

  • Ai product teardown

    aroyburman-codes/pm-skills/skills/ai-product-teardown Skill

    19★ repo

    Structured teardown of AI products (ChatGPT, Claude, Gemini, Perplexity, Copilot, etc.). Analyzes product decisions, UX patterns, technical architecture, business model, and competitive positioning.

  • Analytical pm

    aroyburman-codes/pm-skills/skills/analytical-pm Skill

    19★ repo

    Structured analytical and metrics framework for AI product roles. Covers: metrics, goal-setting, root-cause analysis, trade-offs, A/B tests.