Give your agent a craft.

routing

Caffeinity Routing

Start here. Tell it the outcome you want and it picks one of ten workflows, lists the skills in order with what each hands the next, and names the ones you have not installed instead of improvising their work.

4 files · 347 lines · 8 KB

npx skills add arm-pz/caffeinity-skills --skill caffeinity-routing

Install page Source

authoring

Draft Skill

Creates a new agent skill from a plain idea: confirms the purpose before writing anything, checks the installed siblings for overlap, splits scripts from references from assets, writes a description that actually triggers, then validates it with check_skill.py. Written from scratch, so it carries no text from Qoder's built-in skill-creator, which ships without a licence permitting redistribution.

2 files · 112 lines · 8 workflow steps · 0 API keys

npx skills add arm-pz/draft-skill

Install page Source

authoring

Prompts To Skill

Turns a list of your own prompts into a finished, tested skill, one skill per prompt: an intent interview, an overlap check against what is already installed, a draft written with draft-skill, trigger test cases that include near-misses, and a tune-skill gate at the end. It needs draft-skill and tune-skill and stops with a clear message if either is missing.

3 files · 141 lines · depends on draft-skill + tune-skill · 0 API keys

npx skills add arm-pz/prompts-to-skill

Install page Source

authoring

Tune Skill

Audits and fine-tunes a skill that already exists: the description that never fires, overlap with installed siblings, stale names and counts, handoff contracts that do not hand off. Ships check_skill.py, a deterministic validator over frontmatter, folder and heading agreement, description length and reference paths that do not exist. Not for creating one from scratch; that is draft-skill.

4 files · 268 lines · 1 validator script · 0 API keys

npx skills add arm-pz/tune-skill

Install page Source

release

Prompts To Skill Release

Packages a finished skill for release: runs its trigger test cases and records which passed and which did not, sets the version and CHANGELOG, builds the archive, writes the README, and ends with a per-platform install checklist. Failed tests stay in the report instead of being dropped from it.

3 files · 113 lines · 5 release sections · 0 API keys

npx skills add arm-pz/prompts-to-skill-release

Install page Source

authoring

Skill to Mod

Checks whether a skill should become a Claude Code mod, then builds the plugin with your skill unchanged and a thin trigger, validates and tests it, and lists what it can touch. Says no when a skill should stay a skill.

12 files · 1,790 lines · 3 trigger patterns · 0 API keys

npx skills add arm-pz/skill-to-mod --skill skill-to-mod

Install page Source

authoringchain

Skill Launch

The full pipeline from idea to launched skill: Draft-Skill writes it, Tune-Skill gates it through the validator, Findable-Polish polishes its discovery surfaces. Six chain skills went through this loop in one day — and every public change still needs your go-ahead.

3 files · 110 lines · 3 gated phases · 0 API keys

npx skills add arm-pz/skill-launch --skill skill-launch

Install page Source

authoringchain

Tune And Polish

For a skill that both misfires and hides: Tune-Skill fixes the triggering description, sibling overlaps and stale counts, gated on check_skill.py with zero FAILs; then Findable-Polish audits and polishes the README, About and site copy against real queries. Listings are written from the final description, never before.

3 files · 89 lines · 2 gated phases · 0 API keys

npx skills add arm-pz/tune-and-polish --skill tune-and-polish

Install page Source

authoringClaude Code mod

Tune Skill Mod

Arms when Claude edits a SKILL.md, then holds git push, PRs and releases until tune-skill has validated the change. Edits to any other file are ignored.

16 files · 1,288 lines · 2 hook files · fails open

/plugin install tune-skill-mod --marketplace arm-pz/caffeinity-skills

Install page Source

releaseClaude Code mod

Skill Release Mod

Holds gh release create and npm publish in Claude Code until prompts-to-skill-release has run the skill's test cases since your last edit.

12 files · 627 lines · 2 hook files · fails open

/plugin install skill-release-mod --marketplace arm-pz/caffeinity-skills

Install page Source

discovery

Findable

Sets up discovery for a GitHub repo, skill, plugin or MCP server so it gets found by what it does, not only by its name. It audits where you rank today, works out the queries strangers type, then drafts the About text, topics, README opening, release notes, site page and directory plan — real numbers only, and nothing public changes without your go-ahead.

8 workflow steps · 10 kit sections · 4 reference guides · 1 listing validator · 0 API keys

npx skills add arm-pz/findable --skill findable

Install page Source

publishing

Publish Pipeline

Turns a pile of skill repos into a published site: a committed manifest decides what is public, discovery opens a pull request, and a green merge deploys generated pages, both discovery indexes, a sitemap and a verified build.

9 files · 1,272 lines · 22 KB

npx skills add arm-pz/publish-pipeline

Install page Source

publishing

Upstream Check

Finds local commits that never reached GitHub, pushes only clean fast-forwards after a secret screen, then checks that the site index, the homepage, the marketplace and the READMEs agree with the repos that actually ship a SKILL.md.

3 files · 354 lines · 8 KB

npx skills add arm-pz/upstream-check

Install page Source

discoverychain

Findable Polish

Chains Findable and Wordsmith: audits a README, skill page or landing copy against the queries a real stranger types, then writes two or three alternatives per finding that fix it without inventing a fact. Proven on its own repo: seven live searches, zero hits, six named gaps, fixes applied the same day.

3 files · 125 lines · 2 chained skills · 0 API keys

npx skills add arm-pz/findable-polish --skill findable-polish

Install page Source

publishingchain

Upstream Polish

Chains Upstream-Check — fetch-based push verdicts, fast-forward only, screened for credential-shaped lines — with Wordsmith rewriting drifted descriptions, topics and README rows, so repos and listings tell the same story again. An unreadable source is inconclusive, never counted as empty.

3 files · 122 lines · 7 verdicts · 0 API keys

npx skills add arm-pz/upstream-polish --skill upstream-polish

Install page Source

build

Site Prompt

Turns a website topic into one self-contained, paste-and-build prompt: it builds and verifies the site in a scratch folder first, then embeds every file verbatim with a pinned stack and the checks that actually ran.

8 files · 869 lines · 17 KB

npx skills add arm-pz/site-prompt

Install page Source

build

Production Code

Delivers code as a finished artifact rather than a snippet: complete scripts, bug fixes with the root cause, reviews, API integrations and SQL, each with the run instructions and the edge cases handled.

4 files · 320 lines · 9 KB

npx skills add arm-pz/production-code

Install page Source

release

Web Preflight

Checks a site you own before you ship it, without pretending a status code is a finding. A 200 on /.env that matches the app shell is catch-all routing, a blanket 403 is an unanswered question, and a check that never ran becomes INCONCLUSIVE — never a pass.

4 verdicts · 19 fixed paths · 9 behavioral tests · ~215 lines · 0 API keys

npx skills add arm-pz/web-preflight

Install page Source

release

Pre Ship Security Red Team

Red-teams a web app you own before launch, in an isolated local environment. Three parallel read-only subagents run fourteen authorization and abuse checks across three groups (identity and authorization; UI and API bypass; browser, network, cache and AI), each with captured evidence, then the fix is rerun against the same check. A check that cannot fail is falsified first, and findings stay on the record even when the pass clears.

3 subagents · 14 checks · 9 files · local environments only

npx skills add arm-pz/pre-ship-security-red-team

Install page Source

performance

Pre Ship Performance Audit

Audits and fixes a web app's real-world speed before launch: four read-only subagents sweep twenty known slow-downs across images, bundles, database queries and servers, then the same mobile Lighthouse protocol, three runs per page, proves each fix before and after. Never removes a feature for a score, never invents a baseline, and asks before touching dependencies, the database or the deploy region.

4 subagents · 20 slow-downs · 6 phases · ~120 lines · 0 API keys

npx skills add arm-pz/pre-ship-performance-audit

Install page Source

release

Release Gate · Chair

One answer to “can we deploy?”: runs web-preflight, the security red team and the performance audit in order, keeps three separate verdicts, and computes HOLD or ready with a script instead of judgement.

4 files · 391 lines · 8 KB

npx skills add arm-pz/release-gate-chair

Install page Source

release

Release Gate · Ledger

The release gate where each lane writes its own rows into one ledger through a validating recorder, so a malformed or missing verdict is rejected the moment it is written.

8 files · 530 lines · 9 KB

npx skills add arm-pz/release-gate-ledger

Install page Source

release

Release Gate · Validator

The cheapest release gate: turns three pre-launch reports that already exist into one posture, HOLD or ready, without running any lane or sending a single request.

6 files · 583 lines · 10 KB

npx skills add arm-pz/release-gate-validator

Install page Source

releaseClaude Code mod

Ship Sentinel

A Claude Code mod that holds git push, PR, publish and deploy commands until your pre-ship check skills have run since the last edit. Ask, block or nudge; fails open and touches no files, network or processes.

1 hook module · 173 lines · 4 calls · 0 network

/plugin install ship-sentinel --marketplace arm-pz/ship-sentinel

Install page Source

release

Paper Trail

Privacy policy, terms, refund and cookie pages written only from facts you confirm, then checked for placeholders, missing sections and emails nobody supplied. Says when a lawyer should look.

6 files · 381 lines · 8 KB

npx skills add arm-pz/caffeinity-skills --skill paper-trail

Install page Source

releaseClaude Code mod

Release Gate Mod

Holds production deploys and PR merges in Claude Code until the release-gate chair has run web-preflight, the security red team and the performance audit since your last edit. Install this one rather than the three single-check mods.

13 files · 950 lines · 2 hook files · fails open

/plugin install release-gate-mod --marketplace arm-pz/caffeinity-skills

Install page Source

releaseClaude Code mod

Web Preflight Mod

Reminds Claude Code to run web-preflight (exposed .env files, source maps, admin and debug surfaces) before a production deploy.

11 files · 872 lines · 2 hook files · fails open

/plugin install web-preflight-mod --marketplace arm-pz/caffeinity-skills

Install page Source

releaseClaude Code mod

Security Red Team Mod

Holds production deploys in Claude Code until the pre-ship security red team has run since your last edit.

17 files · 1,588 lines · 2 hook files · fails open

/plugin install pre-ship-security-red-team-mod --marketplace arm-pz/caffeinity-skills

Install page Source

performanceClaude Code mod

Performance Audit Mod

Reminds Claude Code to run the pre-ship performance audit before a production deploy.

9 files · 597 lines · 2 hook files · fails open

/plugin install pre-ship-performance-audit-mod --marketplace arm-pz/caffeinity-skills

Install page Source

seo

SEO Crawl

Crawls a site you own and returns deterministic, evidence-backed technical SEO findings, with blocked or unrun checks reported INCONCLUSIVE rather than a pass.

14 files · 1,885 lines · 19 KB

npx skills add arm-pz/seo-crawl

Install page Source

seo

Keyword Guard

Plans topic clusters and kills keyword cannibalization so exactly one page wins each query. The cannibalization audit is a mandatory blocker before any content change — with a sitemap fallback for when you have no Search Console access.

6 phases · 3 reference checklists · ~300 lines · 0 API keys

npx skills add arm-pz/keyword-guard

Install page Source

seochain

Keyword Resolver

Resolves keyword cannibalization with Keyword-Guard, then rewrites titles, H1s and meta descriptions with Wordsmith. One query, one owner — the ownership audit blocks until the map is settled, and a sitemap fallback is named as a fallback when you have no Search Console.

3 files · 127 lines · 2 chained skills · 0 API keys

npx skills add arm-pz/keyword-resolver --skill keyword-resolver

Install page Source

seochain

Seo Polish

seo-crawl's measured findings, an optional seo-audit diagnosis, then Wordsmith drafts optimized alternatives for every High and Medium finding: titles, meta descriptions, headings and internal-link anchors.

3 files · 85 lines · 5 audit layers · 0 API keys

npx skills add arm-pz/seo-polish --skill seo-polish

Install page Source

editorial

Wordsmith

Teaches your agent to edit, not just generate: 44 commands across 5 disciplines that tighten, rewrite, critique and proofread while keeping the author's meaning, hedges and voice intact.

44 commands · 5 disciplines · ~1,200 lines · 0 API keys

npx skills add arm-pz/wordsmith

Install page Source

content

Platform Content

Writes platform-native content packs from one brief: X threads, LinkedIn posts, YouTube and TikTok scripts, Instagram captions, newsletters and blog articles, each shaped to how that platform is actually read.

3 files · 453 lines · 11 KB

npx skills add arm-pz/platform-content

Install page Source

content

Sales Copy

Writes buyer-facing conversion assets: long-form sales pages, landing pages, launch and abandoned-cart email sequences and ad variations, built on the offer and the objections you can actually back.

3 files · 595 lines · 13 KB

npx skills add arm-pz/sales-copy

Install page Source

outbound

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…

2 files · 96 lines · 2 KB

npx skills add arm-pz/cold-email-list-gate

Install page Source

outbound

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…

4 files · 393 lines · 8 KB

npx skills add arm-pz/cold-email-ops

Install page Source

career

Recruiter Lens

Reviews resumes, CVs and LinkedIn profiles the way recruiters actually screen them: first-impression scans, ATS compatibility, rejection-pattern diagnosis, and interview prep. 13 commands through 5 filters, and it never invents a metric.

13 commands · 5 filters · ~2,500 lines · 0 API keys

npx skills add arm-pz/recruiter-lens

Install page Source

career

Applicant Kit

Writes the better version: decoded job description, tailored resume, bullets rewritten as action-task-result-impact, honest keyword placement, five summaries, a LinkedIn rewrite and twenty interview answers, all built from real experience. recruiter-lens judges; applicant-kit produces. Nothing invented.

7 modes · 6 produce + 1 hand-off · ~320 lines · 0 API keys

npx skills add arm-pz/applicant-kit --skill applicant-kit

Install page Source

career

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 with submission and follow-up dates, flags roles that have gone quiet, drafts the follow-up and the interview briefing, and reads the funnel weekly. applicant-kit writes the packet; application-pilot keeps the search alive. It never submits anything, and never claims a status it did not see.

8 modes · 9 ground rules · 5 files · no CLI, no telemetry

npx skills add arm-pz/application-pilot --skill application-pilot

Install page Source

career

Career Track

For the moves around a career: a positioning line you can repeat, the case for the next level, review and promotion narratives, salary negotiation scripts and a ninety-day plan.

3 files · 382 lines · 12 KB

npx skills add arm-pz/career-track

Install page Source

research

Research Brief

Answers “what is known about this” with a sourced brief: overviews, competitor and industry analysis, fact checks with conflicts flagged, every claim tied to a dated source and every unknown named.

4 files · 520 lines · 14 KB

npx skills add arm-pz/research-brief

Install page Source

research

Data Readout

Turns the numbers you already own into a readout you can act on: it opens the real file first, then gives findings with the business implication of each, chart specs and the caveats that matter.

4 files · 406 lines · 12 KB

npx skills add arm-pz/data-readout

Install page Source

decisions

Crash Test

Crash-tests a decision before you build it. Four fixed roles draft the same task in separate contexts and attack each other's drafts anonymously; the chair merges what survived on evidence, not votes, keeps a dissent log for what it could not settle, and grounds the winner's claims about your files against the source before adopting them.

4 roles · ~9 calls · 1 opt-in Operator seat · 2 modes · 0 API keys

npx skills add arm-pz/crash-test --skill crash-test

Install page Source

arena

Do Better

When an answer is bad, don't ask twice: N sub-agents (100 by default, 16 with --quick) get the exact same task with different strategy cards, then attack, defend and judge each other in a single-elimination bracket until one solution survives.

2,160 strategy cards · 7 rounds at full size · ~1,700 lines · 0 API keys

npx skills add arm-pz/do-better

Install page Source

decisions

Strategy Memo

Turns a business question into a decision document: situation analysis, a recommendation written as ranked options, the risks, and a roadmap someone can execute.

3 files · 384 lines · 9 KB

npx skills add arm-pz/strategy-memo

Install page Source

decisions

Solo Income Blueprint

Turns “I want to make money online” into one plan: a business model that fits your skills, time and budget, one offer, a demand check, a minimal tool stack and a seven-day launch.

3 files · 328 lines · 7 KB

npx skills add arm-pz/solo-income-blueprint

Install page Source

learning

Topic Primer

A world-class teacher for any topic, from zero background toward expert depth. Eight modes: foundations, full curriculum, concept-by-concept lessons, adaptive tutoring, expert mental models, mistake prevention, strict exams, and ELI5. One question at a time, then it waits.

8 modes · 68 lines · 0 API keys

npx skills add arm-pz/topic-primer

Install page Source

learning

Study System

Builds the system around a skill you are acquiring: the minimum components, a beginner-to-practitioner roadmap, deliberate practice, spaced repetition and an honest mastery check.

3 files · 373 lines · 11 KB

npx skills add arm-pz/study-system

Install page Source

learning

Course Builder

A course for a class or cohort: measurable outcomes, modules in prerequisite order, an assessment for every outcome and a time budget that fits, checked by a script before the first session.

5 files · 301 lines · 6 KB

npx skills add arm-pz/caffeinity-skills --skill course-builder

Install page Source