chrome-devtools-axi
Skill0 starsChanged 2 months agoMITView on GitHub
Control a Chromium session through chrome-devtools-axi after opencode-chromium-cdp start. Use when an observed browser issue needs diagnostics (click, form, console, network). Skip if curl or web_fetch is enough. Not for exploratory multi-role QA (use browser-act).
9 other projects use a version of this, 8 of them edited.
Adopted by
Most recently taken up by
- n-n-code/n-n-code-skillstheir own version, first seen Nov 1, 2026
- quocld/hephaestus-agent-skillsedited, first seen Oct 20, 2026
- layer5io/sistentedited, first seen Oct 9, 2026
- meshery/schemasedited, first seen Oct 9, 2026
- meshery/meshkitedited, first seen Oct 8, 2026
- kunchenguid/chrome-devtools-axiedited, first seen Oct 8, 2026
Used with
Projects with it also use quota-axi, lavish and 2 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
layer5ioSkillquota-axi
Report local Claude, Codex, Cursor, GitHub Copilot, and Grok quota windows via the quota-axi CLI - remaining percentages, reset times, and provider status read from local auth sources, with no routing, recommendation, or provider mutation. Use before deciding whether it is safe to keep spending a provider's quota, when the user asks about usage, rate limits, or remaining quota, or when comparing local provider headroom.
Also in 6 projects that use this
kunchenguidSkilllavish
Turn complex or visual agent responses into rich, reviewable HTML artifacts (HTML files) the user can annotate and send feedback on, using the lavish-axi CLI. Use when about to give a plan, comparison, diagram, table, code diff, report, or anything easier to grasp visually than as prose.
Also in 6 projects that use this
SentrySkilliterate-pr
Iterate on a PR until actionable CI passes and high/medium review feedback is addressed. Use for PR CI failures, review feedback, or green-check loops; do not wait for human approval, draft status, or merge gates.
Also in 4 projects that use this
MicrosoftSkillcut-release
Use this skill to cut an APM release from the current worktree: assess whether the cycle since the last tag warrants a patch or minor bump (semver discipline against the merged-since-last-tag diff), sanitize the [Unreleased] CHANGELOG block into a dated version block with one concise "so what" entry per merged PR (drop internal-only churn, consolidate duplicates), bump pyproject.toml + uv.lock, run the CI-mirror lint chain, and open the release PR. Activate on "ship a release", "cut v0.x", "release prep", "bump and PR", "open release PR", "what kind of release do we need", or any phrasing that ends in opening a release PR -- even when the user does not say "skill". Stops BEFORE tagging; tagging stays a human gate that triggers the release workflow. Refuses to bump to a major (>= 1.0.0) version without explicit operator confirmation.
Also in 4 projects that use this
Other versions9 projects use a version of this.
Word for word · 0
None found.
Edited · 8
- meshery/meshery★ 12k77% same
- kunchenguid/chrome-devtools-axi★ 45024% same
- meshery/meshkit★ 23377% same
- layer5io/sistent★ 14077% same
- layer5io/docs★ 10477% same
- meshery/schemas★ 8577% same
- meshery-extensions/kanvas-site★ 4377% same
- quocld/hephaestus-agent-skills★ 817% same
Wrote their own version · 1
- n-n-code/n-n-code-skills★ 4same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository47 other files it gives its agents.
- templates/AGENTS.mdAGENTS.md
- academicSkill
- adhdSkill
- agent-architecture-auditSkill
- api-designSkill
- automation-audit-opsSkill
- browser-actSkill
- click-path-auditSkill
- codebase-designSkill
- code-tourSkill
- contract-firstSkill
- cost-aware-llm-pipelineSkill
- diagnosing-bugsSkill
- diagram-designSkill
- domain-modelingSkill
- emil-design-engSkill
- eval-harnessSkill
- found-this-designSkill
- full-audit-keamananSkill
- full-performance-auditSkill
- gh-axiSkill
- grill-with-docsSkill
- humanizerSkill
- hyperframesSkill
- id-demo-videoSkill
- img2threejsSkill
- impeccableSkill
- install-anti-slopSkill
- markitdownSkill
- matt-code-reviewSkill
- mongodb-opsSkill
- playwright-qaSkill
- prompt-optimizerSkill
- prototypeSkill
- researchSkill
- scroll-craftSkill
- scroll-worldSkill
- skill-stocktakeSkill
- smartbook-ingestSkill
- smartdocSkill
- supabase-opsSkill
- tddSkill
- to-specSkill
- to-ticketsSkill
- vercel-opsSkill
- visual-studioSkill
- writing-for-agentsSkill
The file
We split this skill into the rules it gives an agent
11 rules. 0 are common, 1 is distinctive, and 10 are very specific to this project.
0
Common
Most of the 9 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
10
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 10
Follow the 4-door browser hierarchy:
- Very specific: line 18
Start background Chromium: opencode-chromium-cdp start (or $HOME/.local/bin/opencode-chromium-cdp start).
- Very specific: line 20
Never set CHROME_DEVTOOLS_AXI_HEADED=1 or CHROME_DEVTOOLS_AXI_AUTO_CONNECT=1 unless the user asks to see a window.
- Very specific: line 21
If the helper prints NOT_CONFIGURED, stop.
- Very specific: line 29
If chrome-devtools-axi output shows a follow-up command starting with chrome-devtools-axi, run it as npx -y chrome-devtools-axi ...
- Very specific: line 33
Use chrome-devtools-axi after an observed browser issue needs diagnostics: click, form, console, or network.
- Very specific: line 39
Run npx -y chrome-devtools-axi open <url> to navigate.
- Very specific: line 42
After a state-changing action, confirm the outcome with a fresh snapshot (or eval document.title / screenshot <path>) before reporting …
- Very specific: line 45
Every response ends with contextual next-step hints - follow them.
- Very specific: line 65
Run npx -y chrome-devtools-axi --help for flags and environment variables, or npx -y chrome-devtools-axi <command> --help for per-command …
- Very specific: line 70
Add --full to snapshot-producing commands to disable truncation.
“Common” is measured: kept by at least 6 in 10 of the 9 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
OpenCode browser contract
Follow the 4-door browser hierarchy:
playwright-qa— primary default for exploratory application UI QA.browser-act— specialized persistent / multi-account / stealth browser sessions.chrome-devtools-axi— deep diagnostics for observed Chromium failures (console, network, heap).click-path-audit— handler vs shared-store sequential-undo side effects.
Invocation only:
- Start background Chromium:
opencode-chromium-cdp start(or$HOME/.local/bin/opencode-chromium-cdp start). - Every command:
CHROME_DEVTOOLS_AXI_BROWSER_URL=http://127.0.0.1:9223 npx -y chrome-devtools-axi <command>. - Never set
CHROME_DEVTOOLS_AXI_HEADED=1orCHROME_DEVTOOLS_AXI_AUTO_CONNECT=1unless the user asks to see a window. - If the helper prints
NOT_CONFIGURED, stop. Do not fall back to Google Chrome.
chrome-devtools-axi
Agent ergonomic interface for diagnosing a Chromium session after opencode-chromium-cdp start. Prefer /browser-act for exploratory multi-role QA.
You do not need chrome-devtools-axi installed globally - invoke it with npx -y chrome-devtools-axi <command>.
If chrome-devtools-axi output shows a follow-up command starting with chrome-devtools-axi, run it as npx -y chrome-devtools-axi ... instead.
When to use
Use chrome-devtools-axi after an observed browser issue needs diagnostics: click, form, console, or network. Start opencode-chromium-cdp first and attach with CHROME_DEVTOOLS_AXI_BROWSER_URL.
Skip it when a plain fetch/curl or web_fetch suffices. Do not use it for exploratory multi-role QA (/browser-act) and do not fall back to Google Chrome.
Workflow
- Run
npx -y chrome-devtools-axi open <url>to navigate. Output includes the page's accessibility snapshot; interactive elements carryuid=refs. - Interact by ref:
click @<uid>,fill @<uid> <text>,fillform @<uid>=<val>...,hover @<uid>,drag @<from> @<to>,upload @<uid> <path>. - Pass refs back exactly as printed, including the
g<N>:generation prefix. If the page re-rendered since the snapshot, the action fails loudly withSTALE_REF- runsnapshotagain and retry with fresh refs. - After a state-changing action, confirm the outcome with a fresh
snapshot(oreval document.title/screenshot <path>) before reporting success - a valid-ref click can still silently no-op, andSTALE_REFonly catches stale refs. - Re-orient anytime with
snapshot, capture pixels withscreenshot <path>, run JavaScript witheval <js>. - Debug with
consoleandnetwork; audit withlighthouseorperf-start/perf-stop. - Every response ends with contextual next-step hints - follow them. The first command auto-starts a persistent bridge, so the browser session survives across invocations; run
stopwhen you are done.
Commands
commands[35]:
open <url>, snapshot, screenshot <path>, click @<uid>, fill @<uid> <text>,
type <text>, press <key>, scroll <dir>, back, wait <ms|text>, eval <js>,
run,
hover @<uid>, drag @<from> @<to>, fillform @<uid>=<val>..., dialog <action>,
upload @<uid> <path>, pages, newpage <url>, selectpage <id>, closepage <id>,
resize <w> <h>, emulate, console, console-get <id>, network,
network-get [id], lighthouse, perf-start, perf-stop,
perf-insight <set> <name>, heap <path>, start, stop, setup hooks
built-in:
update: Upgrade chrome-devtools-axi to the latest published npm version
"update --check": Report current vs latest without installingRun npx -y chrome-devtools-axi --help for flags and environment variables, or npx -y chrome-devtools-axi <command> --help for per-command usage.
Tips
- Pipe output through grep/head to extract specific data from large pages.
- Add
--fullto snapshot-producing commands to disable truncation. - Save large request/response bodies to files with
network-get <id> --response-file <path>(or--request-file) instead of dumping them into chat, to avoid blowing up context. - Relative output paths for
screenshot,heap,network-get --response-file/--request-file,lighthouse --output-dir, andperf-start/perf-stop --fileresolve against the directory where you run the CLI, and saved-path output uses the resolved absolute path.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

