caffeinity

Plugin caffeinity from marketplace caffeinity-skills in arm-pz/caffeinity-skills. Commands read from the repo's manifest — yesterday.

Skills (60)

• ai-team-blueprint

  Guide a solo operator or small business from "I want an AI team" to a ready-to-run v1 blueprint for a team of 3 to 5 Claude agents. Asks five sharp questions, recommends one starting use case, then delivers the team structure, a production prompt per agent, the handoff workflow, a lean tool stack, a

• applicant-kit

  Produces tailored job-application material from a resume and a job description: a decoded JD table with must-have versus nice-to-have, resume bullets rewritten as action-task-result-impact, a keyword-gap placement map, five drafted resume summaries, a full LinkedIn rewrite, and twenty likely intervi

• application-pilot

  Runs the job search around the applications: turns role criteria into a live shortlist, scores each role for fit with evidence, keeps a reviewable tracker (status, submission and follow-up dates, dedupe), flags roles gone quiet past an aging threshold, drafts follow-ups and interview briefings, and

• caffeinity-routing

  Picks which caffeinity skills to run, in what order, for a goal that spans more than one of them, and says what each step hands the next: build and publish a skill, get a project found, pass a release gate, grow organic search traffic, run a job search, make a decision, learn a skill, run cold outbo

• career-track

  Career positioning and the moves around it: personal brand and function-level visibility, promotion and performance-review narratives, executive presence, salary negotiation scripts, career pivots, networking that reaches opportunities before they are posted, interview preparation for the rooms you

• choose-effort

  Asks the user how much effort a Claude Code task deserves before heavy work starts, then recommends an effort level, whether to fan out to subagents, goal mode, workflows or agent teams, how to set it, and when to check /usage. Use when the user is about to start a large, long or unattended Claude C

• cold-email-list-gate

  Gate a cold-email lead list before it loads: sample ten rows, check company, title, size, and mailbox against the ICP, compare data providers on the same criteria, and return a GO or HOLD decision with the fail pattern and the re-run condition. Use when someone wants a list QA'd, checked, sampled, o

• cold-email-ops

  Plan and audit a cold-email program at volume and keep it from degrading: computes inbox and domain capacity from a monthly send target, sets per-domain reply-rate floors, burn-replacement cadence, shadow-ban tests, and automation error budgets, and reports prospects-to-lead with per-client averages

• consistent-code-review

  Perform a deterministic, evidence-backed code review that produces the same findings on re-runs of unchanged code, reconciled against a previous report when one is supplied. Use whenever the user asks to review code, a diff, a PR or a file, says "check for bugs" or "find bugs", complains that earlie

• course-builder

  Designs a course for a group of learners (a class, cohort, workshop series, bootcamp or internal training): measurable outcomes, a module sequence with prerequisites, activities and assessments aligned to each outcome, a time budget that fits the hours available, and a rubric, then checks the plan w

• crash-test

  Crash-tests a decision before you build it. Four sub-agents (Pragmatist, Skeptic, Specialist, Contrarian) draft the same task in separate contexts, attack each other's drafts anonymously, and a chair merges what survived, logs unresolved dissent, and checks the winner's claims about existing files a

• data-readout

  Raw numbers turned into a decision: dataset interpretation, statistics with the business implication of each finding, chart specifications, pattern and anomaly detection, forecasts built on stated assumptions, segmentation, A/B test significance, dashboard metric selection and report templates, outp

• diagnose-usage

  Diagnoses why a Claude Code session or day burned through usage limits faster than expected, and says what to change. Reads the user's own /usage breakdown, checks the known heavy-session causes (high effort levels, subagents inheriting effort, goal mode, workflows, agent teams, long SDK jobs), and

• do-better

  Make 100 versions of the assistant fight to the death over one task. Spins up N sub-agents (default 100, --quick for 16), gives every one the exact same task plus a different strategy card (reasoning mode, workflow, strategy), then runs a single-elimination bracket: they attack each other's solution

• draft-skill

  Create a new agent skill from a plain idea, with no prompt list to work from. Confirms intent before writing anything, decides what belongs in scripts versus references versus assets, writes a description that actually triggers, validates with tune-skill's check_skill.py, then hands off for boundari

• findable-polish

  Audit content for discoverability gaps with the Findable skill, then generate improved alternatives with Wordsmith. Use when the user wants to improve SEO, search visibility, or findability of a repo README, skill page, landing page, article, or marketing copy — and wants both the diagnosis and conc

• findable

  Sets up discovery for a GitHub repo, agent skill, Claude Code plugin or MCP server so people and agents can find it by what it does, not only by its name: audits current visibility and same-name collisions, derives the queries people actually search, drafts the GitHub About text, topics, README open

• get-indexed

  Tells search engines about a site's new and changed pages through every channel that has an API, and lists the few steps that still need a person. Sends live pages that are new since the last run to IndexNow (Bing, Yandex, Seznam, Naver), resubmits the sitemap to Google Search Console, reads Google'

• harness-audit

  Audits an existing coding-agent harness (CLAUDE.md, AGENTS.md, rules files, hooks, MCP and tool config, skills) against the project's past Claude Code sessions, then returns a ranked findings report plus proposed diffs applied only after approval. Flags bloated instruction files, rules with no evide

• insights-to-prompts

  Turn a Claude Code /insights report into before/after rewrites of the prompts that caused friction — both the prompts you type in sessions and the prompt text inside your own skills. Reads ~/.claude/usage-data (report.html, cached facets) plus session transcripts with a bundled script, ranks frictio

• keyword-guard

  Plan SEO topic clusters and eliminate keyword cannibalization so exactly one page wins each query. Use when mapping pillar and satellite pages, deciding which page should rank for a keyword, resolving internal competition between pages, writing title/H1/meta to avoid primary-keyword overlap, assigni

• keyword-resolver

  Resolve keyword cannibalization with Keyword-Guard, then generate alternative titles/H1/meta descriptions with Wordsmith. Use when the user wants to eliminate internal competition between pages, assign query ownership from Search Console or sitemap, de-conflict mixed-language pages with hreflang, or

• paper-trail

  Drafts the policy pages a small product needs before it takes money or data (privacy policy, terms of service, refund policy, cookie notice) from a fact sheet about what the product actually collects, stores, shares and charges, then checks the drafts for placeholders, missing sections and facts nob

• platform-content

  Platform-native content packs: Twitter/X threads, LinkedIn posts, YouTube and TikTok scripts, Instagram captions, newsletter issues, blog articles, podcast outlines, 30-day calendars and repurposing chains, each with hook, body and call to action, built from a brief about your platform, niche, audie

• portable-harness

  Set up a repo so any coding agent (Claude Code, Codex, Cursor) behaves the same wherever it runs - writes 12 working rules at the top of CLAUDE.md or AGENTS.md, adds map sections only where the agent keeps getting things wrong, and installs guardrails it cannot talk past - a type check that fails on

• pre-ship-performance-audit

  Audit and fix real-world web app performance before launch using four independent read-only subagent audits covering images and fonts, frontend bundles and rendering, database queries and APIs, and server, network and user-flow measurement. Use when asked to find and fix slow pages, heavy bundles, N

• pre-ship-security-red-team

  Authorized, evidence-driven security red-team pass over a web app you own before launch, run by three parallel read-only subagents with synthetic test accounts. Covers anonymous data access, IDOR cross-user object access, self-service role escalation, password-reset token reuse, UI-disabled request

• production-code

  Production-ready code delivered as a complete artifact: scripts, bug fixes with the root cause, API integrations, SQL of any complexity, automation jobs, scrapers, data analysis in pandas or R, technical documentation and architecture write-ups, each with setup steps, error handling and a plain-Engl

• prompts-to-skill-release

  Release a skill built from prompts. Use after prompts-to-skill has drafted and tuned a skill, to package it as a zip, run its test cases and record real results, check install and discovery in a fresh session, write the repo README and version, and hand the user an install checklist. Use whenever th

• prompts-to-skill

  Turn a set of user-supplied prompts into a finished, tested agent skill. Runs an intent interview and overlap check, drafts with draft-skill, writes test cases, tunes with tune-skill, and optionally names and lists the repo with findable. Use whenever the user has a list of prompts, instructions, or

• prompts-to-workflow

  Turns a pasted batch of prompts that together do one multi-step job into a workflow, then decides how to split it into skills. Maps the prompts to ordered steps with inputs, outputs and gates, checks every step against the live skillsmith.tech catalog and its brews, reuses existing skills such as tu

• publish-pipeline

  Sets up, audits and repairs a manifest-driven CI/CD pipeline that publishes a collection of agent skills to a Cloudflare Pages site, with a generated page per skill. Use when someone asks for CI/CD or automation for a skills site, wants a new skill repo to appear on the site with its own page, asks

• recruiter-lens

  Review resumes, CVs, cover letters and LinkedIn profiles the way recruiters commonly screen them, and prepare candidates for interviews. Use when the user shares or asks about job-search materials: why a resume is not getting interviews, a quick first-impression scan, ATS compatibility or keyword fi

• release-gate-chair

  Runs the three pre-launch passes in order — web-preflight for external exposure, pre-ship-security-red-team for application behaviour in an isolated environment, pre-ship-performance-audit for measured speed — records each lane's own verdict and findings into one ledger, and computes a single releas

• release-gate-ledger

  Runs the three pre-launch passes in order and has each lane write its own rows into one release-gate ledger through a validating recorder, instead of a chair copying tables after the fact. Produces three separate verdicts and one release posture (HOLD or ready) computed by script. Use when the three

• release-gate-validator

  Turns three pre-launch reports that already exist into one release posture (HOLD or ready) without running any of them. Ingests the security red team's on-disk results table mechanically, takes the preflight and performance tables as verbatim pastes, and computes the posture with a script. Use when

• research-brief

  Decision-grade research: topic overviews, competitor and industry analysis, literature reviews, fact checks with conflicting sources flagged, synthesis of expert positions, trend scans, due diligence on a partner or investment, interpretation of numbers found in public sources and one-page executive

• sales-copy

  Direct-response conversion assets: long-form sales pages, launch and abandoned-cart email sequences, Facebook, Google and LinkedIn ad variations, landing pages, product descriptions, video sales letter and webinar scripts, upsell flows and testimonial frameworks, each with headline, subheadline, bod

• seo-crawl

  Use when you need evidence about the technical SEO state of a site you own or are authorized to crawl, covering HTTP statuses and redirects, indexability (meta and header robots), robots.txt, canonical tags, titles, meta descriptions, H1s, internal links, sitemap coverage, and static JSON-LD. Runs a

• seo-polish

  Audit SEO health with seo-crawl (and seo-audit when installed), then generate optimized alternatives with Wordsmith. Use when the user wants a full technical + on-page SEO diagnosis followed by concrete rewrite alternatives for titles, meta descriptions, headings, content gaps, and internal linking

• seo-sweep

  Runs the Skillsmith by Caffeinity SEO skills on a site you own, in order, fixes what they find in the site's code, proves each fix with a re-crawl, and turns every defect a skill shows along the way into a tested fix to that skill, chaining seo-crawl, findable, keyword-guard, wordsmith and get-index

• session-retrace

  Find a past AI coding conversation from a fuzzy memory — "the session where we fixed the redirect" — across Qoder, Claude Code, Codex and Gemini CLI. Searches the transcript files those tools already keep on disk, ranks sessions with verbatim evidence and a session ID, then prints the chosen chat. U

• setup-claude-advisor

  Configure Claude Code for quota-optimised model tiering: Sonnet as the main session model, Opus as the on-call advisor, Haiku for read-only subagents, and Sonnet for code-editing subagents. Audits existing subagents, environment variables, and CLI version before proposing changes; writes settings, s

• ship-second-brain

  Builds and maintains a team second brain in one markdown folder: raw issues, PRs, specs and call notes saved first, cut into one-idea notes with a source and confidence (seen, verified, opinion), linked, verified against the source, summed up in today.md, and checked by an answer test, with misses i

• site-prompt

  Writes one self-contained, paste-and-build prompt for a website from a topic. Narrows the topic to a concrete subject, derives the concept from that subject's world, builds and verifies the site in a scratch folder, then embeds every file verbatim with a pinned stack, final copy, code-native visuals

• skill-estate

  Takes a whole collection of agent skill repos from scattered to published, consistent and self-maintaining, in gated phases: inventory every repo, reconcile site, marketplace and README listings, test and tune the family, close workflow gaps, wire publishing so new skill repos go live on their own,

• skill-launch

  Launch a new skill end-to-end. Create it with draft-skill, validate and tune it with tune-skill, then audit its discoverability and polish it with findable-polish. Use when the user has an idea for a skill and wants to go from zero to published, with triggering, validation and discovery surfaces all

• skill-to-mod

  Decide whether an existing agent skill should become a Claude Code mod (code that runs inside Claude Code on events like tool calls, prompts, turns and compaction), and if it should, convert it into a validated mod plugin that keeps the original skill bundled. Use whenever the user wants to turn a s

• solo-income-blueprint

  Design a realistic one-person online income plan from the user's skills, time and budget: one recommended business model, one offer, a demand check, a content and sales path, automations, a minimal tool stack, and a 7-day launch plan. Use when someone asks how to make money online or with AI tools,

• straight-prose

  Writes and edits prose so it reads like a specific person wrote it and carries no stock AI patterns such as inflated significance, promotional wording, vague attribution, negative parallelisms, forced threes, em dashes, chatbot pleasantries and over-formatting. Applies the rules while drafting, edit

• strategy-memo

  Business strategy written as a decision document: competitive analysis, market and customer research, business model canvas, growth and pricing strategy, go-to-market plan, SWOT ranked by actionability, ninety-day, one-year and three-year roadmaps, board presentations and pivot assessments, structur

• study-system

  A personal system for acquiring a skill: decomposition into the minimum viable components, a beginner-to-practitioner roadmap, the mental models that unlock a subject, Feynman-level explanations, deliberate-practice routines, knowledge-gap audits that surface wrong assumptions, spaced-repetition sch

• topic-primer

  Use when the user names a topic and wants to be taught it — from absolute zero, step by step, concept by concept, through a full beginner-to-expert curriculum, with a personal tutor that diagnoses and adapts, in how experts think and which mental models to use, in avoiding common beginner mistakes,

• tune-and-polish

  Tune a skill's trigger and boundaries with Tune-Skill and then polish its discoverability with Findable-Polish, in one pass. Use when the user wants both halves at once, meaning a triggering or sibling-overlap fix AND polished repo description, topics, README or site page; chaining them means the li

• tune-and-ship

  Takes one published skill at a time from as-is to tuned, fact-checked, released and live, then moves to the next one in the catalog. Each run tunes the skill with tune-skill, checks every version number, flag, price and command it states against the primary source, re-reads its siblings' real SKILL.

• tune-skill

  Audit and fine-tune an existing agent skill so it triggers when it should and hands off cleanly to its siblings. Reads the real SKILL.md and references, checks the description, sibling overlaps, stale names and counts, handoffs and command routing, makes minimal evidenced edits, validates them with

• upstream-check

  Find local work that never reached its remote and push only what is safe, then check whether published listings agree with the repos. Fetches a folder of git clones, classifies every repo as push-ready, level, behind, diverged, no-upstream or no-remote, screens the outgoing diff for credential-shape

• upstream-polish

  Audit upstream drift and listing mismatches with upstream-check, then generate polished fixes with Wordsmith. Use when the user wants to reconcile repo state with published listings (marketplace, site index, README), fix descriptions or topics that drifted, or clean up skill boundaries after a push

• web-preflight

  Use when shipping, deploying, publishing, launching, reviewing, or pre-flighting a website or API and you want a lightweight check for accidental exposure of secrets, source or configuration files, admin and debug surfaces, unsafe redirects, missing security controls, and misleading 200 responses. T

• wordsmith

  Write, draft, rewrite, edit, proofread, polish and improve text while preserving the author's intended meaning, facts and voice. Use when the user wants clearer, shorter or better-toned writing; grammar, structure or flow fixes; emails, website or marketing copy, headlines, outlines or summaries; a

Subagents (12)

• decision-analyst

  Makes a business or product decision: researches what is known with dated sources, reads the user's own data if there is any, stress-tests the options with competing sub-agents, and writes the decision memo with a recommendation and roadmap. Use proactively when someone faces a strategic choice, ask

• discovery-lead

  Gets a repo, skill or plugin found: audits where it ranks, drafts the About text, topics, README opening and site page, publishes it through the skills-site pipeline, and checks that every listing agrees with the repos. Use proactively when someone wants more stars, installs or traffic for a project

• estate-lead

  Stands up or audits a whole skill estate: inventories every repo, reconciles the site, marketplace and README listings, tunes the family, closes workflow gaps, wires self-publishing, bundles a plugin with agents, adds trigger tests and directory listings, and leaves a maintenance loop. Use proactive

• harness-lead

  Sets up a coding agent for a repo end to end: writes working rules and guardrails for a repo that has none or prunes a setup that has grown, then tiers the Claude Code models by role, finds why usage drained, and picks the effort level for the next large task. Use proactively when someone wants Clau

• job-search-coach

  Runs a job search end to end: screens the resume the way recruiters do, writes the tailored material from real experience, builds and tracks a shortlist of roles, and prepares offer and promotion moves. Use proactively when someone is job hunting, asks why they get no callbacks, wants applications t

• learning-coach

  Teaches a skill or topic and builds the practice system around it: lessons from absolute zero to expert, then a decomposition, practice routine, spaced repetition and an honest mastery check. Use proactively when someone wants to learn something, asks for a study plan, or keeps forgetting what they

• outbound-lead

  Runs cold-email outbound at volume: gates a lead list against the ICP before it loads, sizes inboxes, domains and warmup from a send target, audits deliverability, and writes the sequence and landing copy. Use proactively when someone is starting or scaling cold email, asks why reply rates fell, or

• release-gatekeeper

  Decides whether a site or web app is safe to launch: runs the exposure preflight, the isolated security red team and the performance audit in order, then computes one HOLD or ready posture with a script. Use proactively before a deploy or launch, or when someone asks for a go/no-go, whether it is sa

• seo-lead

  Grows organic search traffic: crawls a site you own for measured technical findings, maps one owner page per query to end keyword cannibalization, then rewrites titles, meta descriptions and copy for the approved findings. Use proactively when someone asks why a site does not rank, wants an SEO audi

• skill-builder

  Builds an agent skill end to end: drafts it from an idea or a prompt list, tunes its trigger and sibling boundaries, packages and tests it for release, and decides whether it needs a Claude Code mod. Use proactively when someone wants a new skill, wants a rough SKILL.md taken to release, or asks to

• skill-maintainer

  Maintains a family of agent skills: runs tune-skill's family regression against the saved baseline, fixes each regression (dangling handoffs, trigger collisions, stale counts, invalid frontmatter) with minimal edits, re-releases a skill whose behaviour changed, and checks every clone is pushed and e

• solo-launcher

  Launches a one-person online product: picks one business model and offer from the user's skills, time and budget, writes the build prompt, ships the code, runs the full release gate, and writes platform-native launch content. Use proactively when someone wants to make money online, start a side busi

Similar plugins