agentsclimarketplace

Axi

Skill MoizIbnYousaf/marketing-cli/skills/axi

Agent eXperience Interface (AXI) router — the main entry point for agent-ergonomic CLIs. Use whenever the agent needs GitHub, browser automation, human review, quota routing, Slack, Notion, AWS/Docker/K8s, databases, or any AXI-catalog tool; when choosing AXI vs MCP vs raw CLI; when building or reviewing an agent-facing CLI; or when the user says axi, gh-axi, chrome-devtools-axi, TOON output, agent ergonomics, or "prefer AXI". When in doubt about which external tool interface to use, start here.From its SKILL.md

Install
npx -y skills add MoizIbnYousaf/marketing-cli --skill axi

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • runs commandsInstructs the agent to run 8 commands, including `which gh-axi chrome-devtools-axi 2>/dev/null; npx -y gh-axi --version 2>/dev/null | head -1` and 7 more.

SKILL.md

10.5 KB, ~2.9k tokens by cl100k_base, as published. Nobody here has run it

/axi — Agent eXperience Interface Router

AXI is not a protocol. It is 10 design principles for agent-ergonomic CLIs that beat both raw CLI and MCP on success, cost, duration, and turns (axi.md, kunchenguid/axi).

This skill is the main router for the AXI catalog (official + community). It picks the right AXI, installs/runs it agent-first (npx -y <axi>), and teaches the principles when you build or review agent-facing CLIs.

North Star

DepthFile
10 principles (full spec)rules/principles.md
Official + community catalogrules/catalog.md
AXI vs MCP vs raw CLI vs mktg toolsrules/prefer-axi.md
Build / review an AXIrules/build.md
Benchmark numbersrules/benchmarks.md
Upstream build-skill snapshotreferences/upstream-axi-skill.md

Workflow (escalation)

  1. Unclear — User wants "the right tool." Detect domain → route via the table. Explain out loud.
  2. Use — An AXI exists for the domain. Prefer npx -y <axi> … (zero global install). Fall back to global binary if already on PATH.
  3. Ambient — Repeated sessions in one domain → suggest <axi> setup hooks (SessionStart) after explicit user opt-in.
  4. Build / review — Designing an agent-facing CLI → load rules/principles.md + rules/build.md. Do not invent a parallel MCP server first.
  5. Missing AXI — No catalog entry → prefer the least-bad existing path (mktg skill, raw CLI, MCP) per rules/prefer-axi.md, and offer to scaffold a new AXI.

On Activation (every time)

  1. Restate the domain in one sentence ("You need GitHub PR/CI triage" / "You need live browser extraction").
  2. Probe availability (non-blocking):
    • which gh-axi chrome-devtools-axi 2>/dev/null; npx -y gh-axi --version 2>/dev/null | head -1
    • Optional: mktg doctor --json --fields checks and note cli-gh, cli-gh-axi, cli-chrome-devtools-axi.
  3. Route via the AXI Routing Table. Always say why: "I'm using gh-axi instead of raw gh / GitHub MCP because AXI wins on cost and success for GitHub tasks."
  4. Prefer content-first invocation: run the AXI with no args once to see live state + help[] next steps, then follow those templates.
  5. If the user is building a CLI for agents → skip catalog routing; open principles + build rules.
  6. Never silently fall back to MCP when an AXI exists for that domain.

AXI Routing Table

NeedAXIInstall / runLayer
GitHub issues, PRs, CI runs, releases, secrets, projectsgh-axinpx -y gh-axi (needs gh auth login)Official
Browse, click, fill, extract, tables, Lighthousechrome-devtools-axinpx -y chrome-devtools-axiOfficial
Human review of HTML artifacts (annotate → agent feedback)lavish-axinpx skills add kunchenguid/lavish-axi / see catalogOfficial
Local Claude/Codex/Cursor/Copilot/Grok quota windowsquota-axisee rules/catalog.mdOfficial
Jujutsu historyjj-axicommunityVCS
npm registry inspectnpm-axicommunityPackages
SQLite inspect / capped queriessqlite-axicommunityData
Slack read/search/draftslack-axicommunityComms
Gmail/Calendar/Docs/Drive/Slides (draft-only mail)gws-axicommunityWorkspace
Harvest time trackingharvest-axicommunityOps
Spec-driven agent workflow (AXI-in-skill demo)specopscommunityProcess
Git-backed record sheetsgitsheets-axicommunityData
Metabase SQL/MBQLmetabase-axicommunityAnalytics
Otter.ai transcriptsotter-axicommunityMeetings
Notion pages/databasesnotion-axicommunityDocs
ClickUp tasksclickup-axicommunityTasks
Databricks jobs/runsdatabricks-axicommunityData
AWS host/deployaws-axicommunityCloud
Docker app lifecycledocker-axicommunityCloud
DynamoDBdynamodb-axicommunityData
PostgreSQLpg-axicommunityData
MongoDBmongodb-axicommunityData
Elasticsearchelasticsearch-axicommunityData
Kubernetes workloadskubernetes-axicommunityCloud
Redisredis-axicommunityData
Celery queuescelery-axicommunityCloud
Design / review agent CLI ergonomics(this skill → principles)read rulesMeta
Marketing playbook (brand, content, publish)/cmomktg skillsOut of scope

Full URLs + one-liners: rules/catalog.md.

Disambiguation

User saysRoute toNotWhy
"check the PR / CI / issues"gh-axiraw gh, GitHub MCPAXI: 100% success @ $0.050 vs CLI 86% / MCP ~$0.10–0.15
"open this page / click / fill form / extract table"chrome-devtools-axichrome-devtools-mcp, agent-browserCombined ops + --query; 100% @ $0.074, 4.5 turns
"scrape this URL I already have" (static content)firecrawl / exa-contentschrome-devtools-axiDon't pay for a browser when fetch/crawl is enough
"search the web for X" (unknown URLs)exa-search / Exa MCPchrome-devtools-axiSemantic search ≠ browser automation
"automate Instagram/TikTok login post"/cmo + browser profile / mktg publishchrome-devtools-axi aloneMarketing distribution is /cmo's job
"help me market / write copy / SEO"/cmo/axiAXI routes tools; CMO routes marketing skills
"build a CLI for my agent"/axi principles + buildMCP-first designPrincipled CLI beats MCP on the published benches
"use MCP for GitHub/browser"Prefer matching AXI firstEager MCP schemasMCP schema overhead ~2.3× input tokens in browser bench
"what's my Cursor/Claude quota"quota-axiguessing from UILocal-first usage windows for routing-aware agents
"review this HTML with humans"lavish-axipaste into chatAnnotation loop back to the agent

First 5 Minutes (new machine)

  1. Confirm Node 20+ for npx.
  2. For GitHub work: gh auth login once, then npx -y gh-axi (home view).
  3. For browser work: npx -y chrome-devtools-axi open https://example.com --query "Example".
  4. Optional ambient context: npm i -g gh-axi && gh-axi setup hooks (restart session).
  5. Tell the user which AXI you chose and the one-line why.

Guardrails

  • Prefer AXI when a catalog entry exists for that domain. Explain the preference; don't debate protocol religion.
  • Zero-install first: npx -y <axi> … before asking the user to npm i -g.
  • Follow help[]: AXI outputs next-step command templates — use them; don't invent flags.
  • Fail loud: unknown flags must error (exit 2). Never invent flags and trust unscoped output.
  • No interactive prompts. If a required value is missing, fail with a structured error + suggested command.
  • Pipe for tokens: | head, | rg on AXI stdout is encouraged; don't dump full snapshots into context when --query exists.
  • Skills never call skills. /axi orchestrates tool choice; leaf AXIs execute. Exception: /cmo owns marketing — hand off explicitly.
  • Hooks are opt-in. Never run setup hooks without clear user intent.
  • TOON on the wire. When building AXIs, stdout is TOON; keep internals on JSON. Spec: https://toonformat.dev/

Anti-Patterns

Anti-patternWhy it's wrongDo this instead
Loading full MCP tool schemas for GitHub/browser when an AXI existsSchema tax balloons input tokens every turnRoute to gh-axi / chrome-devtools-axi
navigate then separate snapshot every clickDoubles turns; AXI combines opsopen, click --query, fill … --submit
Dumping full page snapshots into contextBurns the token budget--query "…", pipe filters, truncation + --full
Silent fallback to raw gh because "I know the flags"Raw CLI loses accuracy on the GitHub benchUse gh-axi; keep gh only for gaps AXI doesn't wrap yet
Building a new MCP server before an AXI CLIProtocol choice ≠ ergonomicsApply the 10 principles; ship CLI + optional skill + optional hooks
Presenting the entire catalog as a menuShifts the decision to the humanRecommend 1 AXI with a one-line why
Using browser AXI for static URL fetchOverkill cost/latencyfirecrawl / exa-contents / curl

Error Recovery

FailureFix
npx / network blockedInstall global once: npm i -g gh-axi (or the needed AXI); retry
gh-axi auth errorgh auth login (and gh auth refresh -s project when Projects need scope)
chrome-devtools-axi bridge stalechrome-devtools-axi stop then retry; or new CHROME_DEVTOOLS_AXI_SESSION=…
STALE_REF on clickRe-snapshot / open --query and use the new @g:… ref
Unknown command (navigate)Read AXI help[] / --help — prefer open, not MCP verb names
No AXI for domainUse prefer-axi fallback; offer to scaffold per rules/build.md

Progressive Enhancement

LevelWhat /axi can do
L0Route by domain; run via npx -y with no prior setup
L1Binaries on PATH; faster cold start
L2setup hooks ambient home views for Claude Code / Codex / OpenCode
L3Multiple community AXIs installed; quota-aware routing via quota-axi
L4Team ships internal AXIs using principles + contributor catalog workflow

Attribution

Principles, catalog, and benchmarks from AXI / kunchenguid/axi (MIT). This mktg skill is the router + catalog orchestrator adapted for /cmo-style activation; the upstream build-skill snapshot lives in references/upstream-axi-skill.md.

What ships with it: 8 files

32.1 KB alongside SKILL.md, 1 of them executable

references/

scripts/

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.