Best for
- Use this CLI when an agent or technician needs to query Action1 patch, vulnerability, endpoint, software, automation, or report data - especially across multiple client organizations at once, offline, or over time. It i…
Servosity/msp-skills/skills/action1/SKILL.md
Every Action1 endpoint, plus the fleet-wide patch and vulnerability views the org-siloed API cannot give you. Trigger phrases: `action1 patch posture`, `which endpoints are missing patches`, `triage action1 vulnerabilities`, `find stale action1 agents`, `action1 fleet view across organizations`, `use action1`, `run action1-cli`.
Decision brief
Every Action1 endpoint, plus the fleet-wide patch and vulnerability views the org-siloed API cannot give you. Trigger phrases: `action1 patch posture`, `which endpoints are missing patches`, `triage action1 vulnerabilities`, `find stale action1 agents`, `action1 fleet view across organizations`, `use action1`, `run action1-cli`.
Compatibility matrix
| Platform | Status | Evidence | What to check |
|---|---|---|---|
| Codex | Not declared | No explicit evidence | Portability before use |
| Claude Code | Not declared | No explicit evidence | Portability before use |
| Cursor | Not declared | No explicit evidence | Portability before use |
| Gemini CLI | Not declared | No explicit evidence | Portability before use |
Installation
The source command is displayed only when detected. A safe inspection prompt is always available so your agent can explain every action before execution.
npx skills add https://github.com/Servosity/msp-skills --skill "skills/action1"Inspect the Agent Skill "action1" from https://github.com/Servosity/msp-skills/blob/30e109db0872897de0b88adb38d81d4c292da3ae/skills/action1/SKILL.md at commit 30e109db0872897de0b88adb38d81d4c292da3ae. List every install step, command, network request, credential, file read/write, external action, and rollback step. Explain whether it fits my task. Do not install or execute anything until I approve.
Workflow
Action1 uses OAuth2 token-mint. Generate a Client ID and Client Secret on the API Credentials page in the Action1 console, then set ACTION1CLIENTID and ACTION1CLIENTSECRET. The CLI POSTs them to /oauth2/token (JSON body) to obtain a bearer token automatically. Set ACTION1ORGID t…
This skill drives the action1-cli binary. You must verify the CLI is installed before invoking any command from this skill. If it is missing, install it first:
Use this CLI when an agent or technician needs to query Action1 patch, vulnerability, endpoint, software, automation, or report data - especially across multiple client organizations at once, offline, or over time. It is the right tool for fleet-wide patch posture, exploit-aware…
Do not use this CLI for: - Do not use fleet commands for one client's live data - use the per-org commands (e.g. endpoints managed , vulnerabilities list ) which call the API directly. - Do not use fleet vuln-triage for a single CVE's detail - use cve-descriptions . - Do not run…
These capabilities aren't available in any other tool for this API.
Permission review
The documentation asks the agent to run terminal commands or scripts.
npx -y @mvanhorn/printing-press-library install action1 --cli-onlyThe documentation asks the agent to run terminal commands or scripts.
go install github.com/mvanhorn/printing-press-library/library/monitoring/action1/cmd/action1-cli@latestThe documentation includes network, browsing, or remote request actions.
Use this CLI when an agent or technician needs to query Action1 patch, vulnerability, endpoint, software, automation, or report data - especially across multiple client organizations at once, offline, or over time. It is the right tool for The documentation includes network, browsing, or remote request actions.
`action1-cli endpoints managed-id-remote-sessions-post` - **Requires permission: `remote_connect`** Sends a request to the endpoint to start a new remote session.The documentation includes sending, uploading, or posting data to a remote service.
| `webhook:<url>` | POST the output body to the URL (`application/json` or `application/x-ndjson` when `--compact`) |Evidence record
| Signal | Value | Evidence type | Meaning |
|---|---|---|---|
| Quality score | 83/100 | Computed | Documentation, specificity, maintenance, and trust rules |
| Repository stars | 15 | Source | Repository attention, not individual Skill quality |
| Compatibility | 0 platforms | Source | Declared in the catalog source record |
| Usage guide | automated source guide | Editorial | Generated or reviewed according to the visible evidence level |
Pinned source
This skill drives the action1-cli binary. You must verify the CLI is installed before invoking any command from this skill. If it is missing, install it first:
$HOME/.local/bin on macOS/Linux and %LOCALAPPDATA%\Programs\PrintingPress\bin on Windows:
npx -y @mvanhorn/printing-press-library install action1 --cli-only
action1-cli --version$PATH for the agent/runtime that will invoke this skill.If the npx install fails (no Node, offline, etc.), fall back to a direct Go install (requires Go 1.26.4 or newer). This installs into $GOPATH/bin (default $HOME/go/bin), so add that directory to $PATH instead:
go install github.com/mvanhorn/printing-press-library/library/monitoring/action1/cmd/action1-cli@latest
If --version reports "command not found" after install, the runtime cannot see the binary directory on $PATH. Do not proceed with skill commands until verification succeeds.
Action1's REST API is organization-siloed - every call is scoped to one org and nothing is kept over time. This CLI mirrors the full API, then fans out across all your organizations into a local SQLite store so you can rank the worst-patched endpoints fleet-wide (fleet patch-posture), triage CVEs by blast radius and CISA KEV status (fleet vuln-triage), find dark agents (fleet stale), and diff patch drift week over week (fleet patch-drift). Agent-native output, typed exit codes, and offline search throughout.
Use this CLI when an agent or technician needs to query Action1 patch, vulnerability, endpoint, software, automation, or report data - especially across multiple client organizations at once, offline, or over time. It is the right tool for fleet-wide patch posture, exploit-aware CVE triage, dark-agent detection, and patch-drift reporting that the org-scoped Action1 API cannot answer directly. All fleet commands read the local SQLite store; run sync --full first or they return empty results.
Do not use this CLI for:
These capabilities aren't available in any other tool for this API.
fleet patch-posture - See every endpoint across all your client organizations ranked by how many updates it is missing - one fleet-wide view.
Reach for this when an agent needs the worst-patched machines across the whole book of business, not one client at a time.
action1-cli fleet patch-posture --agent --limit 25
fleet vuln-triage - Rank CVEs across every organization by how many endpoints they hit, weighted by CVSS and the CISA Known-Exploited flag.
Pick this to answer 'what should we patch first across all clients' with exploit-aware prioritization.
action1-cli fleet vuln-triage --kev-only --agent
fleet software-rollup - Deduplicate installed software across the whole fleet into app name x version spread x install count.
Use this for license counting and version-spread audits across all clients at once.
action1-cli fleet software-rollup --name "Google Chrome" --agent
fleet automation-health - Success and failure rates across automation instances and their per-endpoint results, aggregated across organizations.
Use this to spot automations that are quietly failing on a subset of endpoints across clients.
action1-cli fleet automation-health --agent
fleet org-scorecard - One row per client organization: endpoint count, missing updates, open CVEs, KEV exposure, and stale agents - the per-client posture number MSPs report to account managers.
Reach for this when an agent needs a per-client posture summary across every organization, not per-endpoint detail.
action1-cli fleet org-scorecard --agent
fleet reboot-pending - Every endpoint fleet-wide where an installed update is waiting on a reboot to finish - the action queue that closes out a patch cycle.
Reach for this when an agent needs the concrete list of machines blocking patch-cycle completion, not a composite health score.
action1-cli fleet reboot-pending --agent
fleet stale - Surface endpoints that have not checked in for N days, or are offline, across all organizations.
Use this to find agents that silently stopped reporting before they become a coverage gap.
action1-cli fleet stale --days 14 --agent
fleet patch-drift - Diff two synced snapshots to show which updates were remediated and which newly appeared since last sync.
Reach for this to prove remediation progress week over week, or catch regressions.
action1-cli fleet patch-drift --agent
fleet health-score - A single composite score per endpoint from missing updates, open vulnerabilities, reboot-required, and staleness - fleet-ranked.
Pick this when you need a triage-ranked worst-to-best list of machines across the fleet.
action1-cli fleet health-score --agent --limit 50
audit - Manage audit
action1-cli audit events-get - Requires permission: view_audit 'The Audit Trail contains event records associated with user actionsaction1-cli audit events-id-get - Requires permission: view_audit Get a specific audit record by its ID.action1-cli audit export-get - Requires permission: view_audit Exports audit data. Use parameters to filter out exported data.automations - Manage automations
action1-cli automations actions-templates-get - Gets a list of existing action templates.action1-cli automations actions-templates-template-id-get - Gets details for an action template specified by its ID.action1-cli automations policies-instances-org-id-get - **Requires permissionaction1-cli automations policies-instances-org-id-id-get - Requires permission: view_automations Gets details about a automation instance specified by its ID.action1-cli automations policies-instances-org-id-instance-id-endpoint-results-endpoint-id-details-get - **Requires permissionaction1-cli automations policies-instances-org-id-instance-id-endpoint-results-get - **Requires permissionaction1-cli automations policies-instances-org-id-instance-id-stop-post - **Requires permissionaction1-cli automations policies-instances-org-id-post - **Requires permissionaction1-cli automations policies-schedules-org-id-get - Requires permission: view_automations Lists existing scheduled automations.action1-cli automations policies-schedules-org-id-id-actions-action-id-delete - Requires permission: manage_automations Deletes a specified action from a scheduled automation.action1-cli automations policies-schedules-org-id-id-delete - Requires permission: manage_automations Deletes a scheduled automation specified by its ID.action1-cli automations policies-schedules-org-id-id-deployment-statuses-get - Requires permission: view_automations Gets the deployment statuses of a automation specified by its ID.action1-cli automations policies-schedules-org-id-id-get - Requires permission: view_automations Gets a scheduled automation specified by its ID.action1-cli automations policies-schedules-org-id-id-patch - **Requires permissionaction1-cli automations policies-schedules-org-id-post - Requires permission: manage_automations Schedules a new automation.cve-descriptions - Manage cve descriptions
action1-cli cve-descriptions <cveId> - Requires permission: view_vulnerabilities Retrieves detailed information about a specific vulnerability in generaldata-sources - A data source is a scripting template that queries certain endpoint data, such as disk volume or local group members, and presents it in a structured way consumed by reports or alerts. Data sources can be built-in or custom (defined by 'builtin' parameter). Built-in data sources are maintained by Action1 and cannot be modified. Custom data sources can be created and maintained by the user.
action1-cli data-sources all-post - Requires permission: manage_data_sources Creates a new custom data source.action1-cli data-sources org-id-get - **Requires one of the following permissions: manage_data_sourcesaction1-cli data-sources org-id-id-delete - Requires permission: manage_data_sources Deletes an existing custom data source.action1-cli data-sources org-id-id-get - **Requires one of the following permissions: manage_data_sourcesaction1-cli data-sources org-id-id-patch - Requires permission: manage_data_sources Updates a custom data source specified by its ID.endpoints - The endpoint object represents a server, workstation, or other device managed by Action1 within a specific organization. Endpoints can only belong to one Action1 organization at one time, but can be moved between organizations.
action1-cli endpoints agent-installation - Requires permission: manage_endpoints In order to manage an endpointaction1-cli endpoints connector-installation-org-id-windows-exe-get - Requires permission: manage_endpoints Obtains an URL to download the Deployer installation file.action1-cli endpoints connectors-org-id-deployer-id-delete - **Requires permissionaction1-cli endpoints connectors-org-id-deployer-id-get - **Requires permissionaction1-cli endpoints connectors-org-id-get - Requires permission: manage_endpoints Lists all Action1 Deployer services in the specified organization.action1-cli endpoints discovery-org-id-get - Requires permission: manage_endpoints Obtains the current Agent Deployment settings in a specified organization.action1-cli endpoints discovery-org-id-patch - Requires permission: manage_endpoints Updates the Agent Deployment configuration for a specific organization.action1-cli endpoints groups - Requires permission: manage_endpoints Creates a new endpoint group within the specified organization.action1-cli endpoints groups-group-id - Requires permission: view_endpoints Gets a specific endpoint group by its ID.action1-cli endpoints groups-group-id-contents-get - Requires permission: view_endpoints Lists all endpoints included in the specified group.action1-cli endpoints groups-group-id-contents-post - Requires permission: manage_endpoints Joins endpoints with specified IDs or names to the endpoint group.action1-cli endpoints groups-group-id-delete - Requires permission: manage_endpoints Deletes an existing group in the specified organization.action1-cli endpoints groups-group-id-patch - **Requires permissionaction1-cli endpoints groups-org-id - Requires permission: view_endpoints Lists existing endpoint groups.action1-cli endpoints managed - Requires permission: view_endpoints Lists all endpoints within the organization.action1-cli endpoints managed-id - Requires permission: view_endpoints Obtains current information about the endpoint with the specified ID.action1-cli endpoints managed-id-delete - Requires permission: manage_endpoints Removes a specified endpoint and attempts to uninstall its agent.action1-cli endpoints managed-id-missing-updates - Requires permission: view_endpoints Obtains a list of missing software updates for a specific endpoint.action1-cli endpoints managed-id-move - Requires permission: manage_endpoints Moves the endpoint to another organization.action1-cli endpoints managed-id-patch - Requires permission: manage_endpoint_attributes Changes the user-defined 'comment'action1-cli endpoints managed-id-remote-sessions-post - Requires permission: remote_connect Sends a request to the endpoint to start a new remote session.action1-cli endpoints managed-id-remote-sessions-session-id-get - Requires permission: remote_connect Gets details for an existing remote session specified by ID.action1-cli endpoints managed-id-remote-sessions-session-id-patch - Requires permission: remote_connect Changes the 'current_monitor' parameter for a specific remote session.action1-cli endpoints status - Retrieves information if any endpoints were added to an organization.enterprise - Manage enterprise
action1-cli enterprise get - Gets settings for an enterprise. You can query data for your enterprise only.action1-cli enterprise patch - Requires permission: manage_enterprise Updates settings for a current enterprise.action1-cli enterprise request-closure - Requires permission: manage_enterprise The request is available only for a free Action1 account.action1-cli enterprise revoke-closure - **Requires permissioninstalled-software - Manage installed software
logs - Manage logs
action1-cli logs <orgId> - Requires permission: manage_endpoints Gets diagnostic logs. Use parameters to pre-filter returned results.me - Manage me
action1-cli me me - Gets settings for the currently authenticated user.action1-cli me patch - Updates settings for the currently authenticated user.action1-cli me subscriptions-get - Gets a list of report subscriptions.action1-cli me subscriptions-post - Requires permission: view_reports Creates a new report subscription.action1-cli me subscriptions-subscription-id-delete - Removes the report subscription.action1-cli me subscriptions-subscription-id-patch - Requires permission: view_reports Updates the report subscription.oauth2 - Manage oauth2
action1-cli oauth2 - Generates a token.organizations - Manage organizations
action1-cli organizations get - Gets a list of organizations within the current Action1 enterprise.action1-cli organizations org-id-delete - Requires permission: manage_organizations Removes an organization from the enterprise.action1-cli organizations org-id-patch - Requires permission: manage_organizations Updates settings for an organization specified by its ID.action1-cli organizations post - Requires permission: manage_organizations Creates a new organization.permissions - Manage permissions
action1-cli permissions - Gets a list of available permission templates.remote_search - Manage remote search
action1-cli remote-search <orgId> - **Requires permissions: view_endpoints, view_software_repositoryreportdata - Manage reportdata
reports - Manage reports
action1-cli reports all-get - Gets a list of existing reports. At this time all reports are enterprise-wide.action1-cli reports org-id-category-id-get - Gets a list of reports and categories. At this time all reports are enterprise-wide.action1-cli reports org-id-custom-id-delete - Requires permission: manage_reports Deletes a custom report specified by its ID.action1-cli reports org-id-custom-id-patch - Requires permission: manage_reports Updates a custom report. You cannot changes a custom report's category.action1-cli reports org-id-custom-post - Requires permission: manage_reports Creates a custom report in the predefined Custom report category.roles - Manage roles
action1-cli roles get - Requires permission: manage_roles Gets a list of available roles.action1-cli roles id-delete - Requires permission: manage_roles Deletes a role specified by its ID.action1-cli roles id-get - Requires permission: manage_roles Gets details about a role specified by its ID.action1-cli roles id-patch - Requires permission: manage_roles Updates a role specified by its ID.action1-cli roles post - Requires permission: manage_roles Creates a new role.scripts - Manage scripts
action1-cli scripts org-id-get - Requires permission: use_scripts Gets a list of existing scripts from the Script Library.action1-cli scripts org-id-id-delete - Requires permission: manage_scripts Deletes an existing custom script specified by its ID.action1-cli scripts org-id-id-get - Requires permission: use_scripts Gets details for a script specified by its ID.action1-cli scripts org-id-id-patch - Requires permission: manage_scripts Updates details for an existing custom script specified by its ID.action1-cli scripts org-id-post - Requires permission: manage_scripts Creates a new custom script and adds it to the Script Library.setting-templates - Manage setting templates
action1-cli setting-templates org-id-get - Gets a list of existing setting templates. Setting templates are maintained by Action1 and cannot be modified.action1-cli setting-templates org-id-template-id-get - Gets details about a setting template specified by its ID.settings - Manage settings
action1-cli settings org-id-get - Requires permission: manage_advanced_settings Lists all existing settings.action1-cli settings org-id-id-delete - Requires permission: manage_advanced_settings Deletes an existing setting specified by its ID.action1-cli settings org-id-id-get - Requires permission: manage_advanced_settings Gets details about the setting configuration.action1-cli settings org-id-id-patch - Requires permission: manage_advanced_settings Updates an existing setting specified by its ID.action1-cli settings org-id-post - Requires permission: manage_advanced_settings Creates a new setting.software-repository - Action1 Software Repository is a continuously updated private application repository that hosts the latest versions of all supported applications to keep your endpoints secure and patched. Action1 maintains built-in software repository packages that are available to all customers as well as enables users to create private software packages to be shared within their organizations only. The package object is a container of software versions and initially, it should contain the first available version of the software (child object called "version"). New versions are added continuously as the respective vendor releases them. Each version object contains the software binary setup files in MSI, EXE or ZIP format (up to 32Gb in size) and deployment settings, such as silent install switches. It may also include the additional actions to be executed before or after a software installation or uninstallation (e.g., reboot or run a script).
action1-cli software-repository packages-all-get - **Requires permissionaction1-cli software-repository packages-all-package-id-delete - Requires permission: manage_software_repository Deletes a custom Software Repository package specified by its ID.action1-cli software-repository packages-all-package-id-get - Requires permission: view_software_repository Gets details for a Software Repository package specified by its ID.action1-cli software-repository packages-all-package-id-patch - **Requires permissionaction1-cli software-repository packages-all-post - **Requires permissionsubscription - View Action licenses, start or extend a free trial, or request a price quote.
action1-cli subscription license-enterprise-get - Requires permission: manage_enterprise Gets details about the enterprise license.action1-cli subscription license-enterprise-quote-post - Requires permission: manage_enterprise Sends a quote request to the Action1 Sales department.action1-cli subscription license-enterprise-trial-post - **Requires permissionaction1-cli subscription license-usage-enterprise-get - Requires permission: manage_enterprise Gets details about license usage for the entire enterprise.action1-cli subscription license-usage-organizations-get - **Requires permissionaction1-cli subscription license-usage-organizations-org-id-get - **Requires permissionupdates - Manage updates
action1-cli updates org-id-get - **Requires one of the following permissions: approve_updates, view_dashboardsaction1-cli updates org-id-package-id-get - **Requires one of the following permissions: approve_updates, view_dashboardsusers - Manage users
action1-cli users get - Requires permission: view_users Gets a list of users within the current Action1 enterprise.action1-cli users id-delete - Requires permission: manage_users Deletes an existing user.action1-cli users id-get - Requires permission: view_users Gets an existing user.action1-cli users id-patch - Requires permission: manage_users Updates an existing user.action1-cli users post - Requires permission: manage_users Creates a new user.vulnerabilities - Manage vulnerabilities
action1-cli vulnerabilities org-id-cve-id-get - **Requires permissionaction1-cli vulnerabilities org-id-get - **Requires permissionWhen you know what you want to do but not which command does it, ask the CLI directly:
action1-cli which "<capability in your own words>"
which resolves a natural-language capability query to the best matching command from this CLI's curated feature index. Exit code 0 means at least one match; exit code 2 means no confident match - fall back to --help or use a narrower query.
action1-cli fleet patch-posture --agent --limit 25
Cross-org rollup of endpoints ranked by missing-update count.
action1-cli fleet vuln-triage --kev-only --agent
CISA KEV CVEs across all orgs, ranked by affected endpoints and CVSS.
action1-cli fleet stale --days 14 --agent
Endpoints that stopped checking in over two weeks ago across the fleet.
action1-cli endpoints managed 00000000-0000-0000-0000-000000000000 --agent --select items.name,items.OS,items.last_seen,items.online_status
orgId is positional (00000000-... = all organizations); dotted --select trims the large managed-endpoint payload to just the fields an agent needs.
action1-cli fleet patch-drift --agent
What got patched and what newly appeared since the previous sync.
Action1 uses OAuth2 token-mint. Generate a Client ID and Client Secret on the API Credentials page in the Action1 console, then set ACTION1_CLIENT_ID and ACTION1_CLIENT_SECRET. The CLI POSTs them to /oauth2/token (JSON body) to obtain a bearer token automatically. Set ACTION1_ORG_ID to scope the fleet commands to one organization by default, and ACTION1_REGION (us/eu/au) to pick your data center. Per-organization API commands like 'endpoints managed ' take the organization id as their first argument.
Run action1-cli doctor to verify setup.
Add --agent to any command. Expands to: --json --compact --no-input --no-color --yes.
Pipeable - JSON on stdout, errors on stderr
Filterable - --select keeps a subset of fields. Dotted paths descend into nested structures; arrays traverse element-wise. Critical for keeping context small on verbose APIs:
action1-cli enterprise get --agent --select id,name,status
Previewable - --dry-run shows the request without sending
Offline-friendly - sync/search commands can use the local SQLite store when available
Non-interactive - never prompts, every input is a flag
Explicit retries - use --idempotent only when an already-existing create should count as success, and --ignore-missing only when a missing delete target should count as success
Commands that read from the local store or the API wrap output in a provenance envelope:
{
"meta": {"source": "live" | "local", "synced_at": "...", "reason": "..."},
"results": <data>
}
Parse .results for data and .meta.source to know whether it's live or local. A human-readable N results (live) summary is printed to stderr only when stdout is a terminal AND no machine-format flag (--json, --csv, --compact, --quiet, --plain, --select) is set - piped/agent consumers and explicit-format runs get pure JSON on stdout.
When you (or the agent) notice something off about this CLI, record it:
action1-cli feedback "the --since flag is inclusive but docs say exclusive"
action1-cli feedback --stdin < notes.txt
action1-cli feedback list --json --limit 10
Entries are stored locally at ~/.local/share/action1-cli/feedback.jsonl. They are never POSTed unless ACTION1_FEEDBACK_ENDPOINT is set AND either --send is passed or ACTION1_FEEDBACK_AUTO_SEND=true. Default behavior is local-only.
Write what surprised you, not a bug report. Short, specific, one line: that is the part that compounds.
Every command accepts --deliver <sink>. The output goes to the named sink in addition to (or instead of) stdout, so agents can route command results without hand-piping. Three sinks are supported:
| Sink | Effect |
|---|---|
stdout | Default; write to stdout only |
file:<path> | Atomically write output to <path> (tmp + rename) |
webhook:<url> | POST the output body to the URL (application/json or application/x-ndjson when --compact) |
Unknown schemes are refused with a structured error naming the supported set. Webhook failures return non-zero and log the URL + HTTP status on stderr.
A profile is a saved set of flag values, reused across invocations. Use it when a scheduled agent calls the same command every run with the same configuration - HeyGen's "Beacon" pattern.
action1-cli profile save briefing --json
action1-cli --profile briefing enterprise get
action1-cli profile list --json
action1-cli profile show briefing
action1-cli profile delete briefing --yes
Explicit flags always win over profile values; profile values win over defaults. agent-context lists all available profiles under available_profiles so introspecting agents discover them at runtime.
| Code | Meaning |
|---|---|
| 0 | Success |
| 2 | Usage error (wrong arguments) |
| 3 | Resource not found |
| 4 | Authentication required |
| 5 | API error (upstream issue) |
| 7 | Rate limited (wait and retry) |
| 10 | Config error |
Parse $ARGUMENTS:
help, or --help → show action1-cli --help outputinstall → ends with mcp → MCP installation; otherwise → see Prerequisites above--agent)go install github.com/mvanhorn/printing-press-library/library/monitoring/action1/cmd/action1-mcp@latest
claude mcp add action1-mcp -- action1-mcp
claude mcp listwhich action1-cli
If not found, offer to install (see Prerequisites at the top of this skill).--agent flag:
action1-cli <command> [subcommand] [args] --agent
action1-cli <command> --help.Alternatives
coreyhaines31/marketingskills
When the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation program. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," "hypothesis," "should I test this," "which version is better," "test two versions," "statistical significance," "how long should I run this test," "growth experiments," "experiment velocity," "experiment backlog," "ICE score," "experimentation program
event4u-app/agent-config
Grounded design brief from the adopted corpus — style, WCAG-checked color tokens, typography, layout pattern, anti-patterns. Use on ui-design-brief or any which-style/palette/font/chart decision.
event4u-app/agent-config
Use BEFORE writing or editing any non-trivial UI — inventories components, design tokens, shadcn primitives, and reusable patterns into state.ui_audit. Hard gate for the ui directive set.
event4u-app/agent-config
Use BEFORE writing/changing tests, adding mocks, or test-only methods on production classes — vs mocking-the-mock, production pollution, partial mocks, and overfit/tautological assertions