get-account-intelligence
Skill8 starsChanged 3 months agoMITView on GitHub
Add Account Intelligence Agent to the user's own Copilot Studio. Use when asked to get, add or deploy Account Intelligence Agent.
- Pipes a download into a shell
In this repository616 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- community_rapp/project/CLAUDE.mdCLAUDE.md
- rapp_ai/CLAUDE.mdCLAUDE.md
- rapp_brainstem/CLAUDE.mdCLAUDE.md
- community_rapp/project/.github/copilot-instructions.mdCopilot instructions
- .github/copilot-instructions.mdCopilot instructions
- rapp_ai/.github/copilot-instructions.mdCopilot instructions
- docs/vault/llms-full.txtllms.txt
- docs/vault/llms.txtllms.txt
- llms.txtllms.txt
- csv-surgeonSkill
- json-doctorSkill
- log-detectiveSkill
- markdown-medicSkill
- pii-scoutSkill
- generate-demoSkill
- community_rappSkill
- aibast-brainstemSkill
- brainstem-first-20-minutesSkill
- generate-demoSkill
- rapp-brainstemSkill
- aibast-easy-mode-brainstemSkill
- aibast-easy-mode-copilotSkill
- aibast-easy-modeSkill
- aibast-staging-ring-testSkill
- deploy-to-copilot-studioSkill
- account-intelligence-account-overviewSkill
- account-intelligence-competitive-intelSkill
- account-intelligence-executive-briefingSkill
- account-intelligence-risk-assessmentSkill
- account-intelligence-stakeholder-mapSkill
- account-intelligence-value-messagingSkill
- escalation-routingSkill
- follow-up-planSkill
- handle-inquirySkill
- interaction-summarySkill
- knowledge-searchSkill
- prepare-actionsSkill
- recommend-resolutionSkill
- satisfaction-surveySkill
- get-ai-customer-assistantSkill
- benefits-summarySkill
- health-insuranceSkill
- leave-balanceSkill
- parental-leaveSkill
- remindersSkill
- remote-workSkill
- submit-time-offSkill
- time-off-checkSkill
- get-ask-hrSkill
- asset-maintenance-forecast-asset-healthSkill
- asset-maintenance-forecast-budget-projectionSkill
- asset-maintenance-forecast-maintenance-forecastSkill
- asset-maintenance-forecast-work-order-planSkill
- get-asset-maintenance-forecastSkill
- compare-plansSkill
- deadline-remindersSkill
- document-checklistSkill
- election-draftSkill
- enrollment-windowSkill
- The first 60 shown.
The file
Show its rules and text
We split this skill into the rules it gives an agent
15 rules. About 0 are common, 11 are distinctive, and 4 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈11
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Do all of this yourself. The user only answers one question: yes or no.
- Distinctive: line 10
Keep every reply to three short lines or fewer.
- Distinctive: line 17
If it does not answer, remember to offer it in step 5.
- Distinctive: line 21
Wait up to two minutes for the health check.
- Very specific: line 29
Check the sign-in (check).
- Very specific: line 30
If pac is missing, install it with dotnet tool install --global Microsoft.PowerApps.CLI.Tool and check again.
- Very specific: line 32
If not signed in, run pac auth create --deviceCode and tell the user: "Sign in with your Microsoft account in the browser window." Never …
- Distinctive: line 36
Ask: "Go ahead?" Wait for yes.
- Distinctive: line 37
If Brainstem is not running, add one optional line, once, in these words: "Optional: I can also set up Brainstem, a free AI that runs on …
- Distinctive: line 42
Never replace an existing install unless the user asked to overwrite.
- Distinctive: line 44
Add: "To remove it later, just ask me." If Brainstem was used, add one last line: "Any time, ask me to 'start up the Brainstem' to use it …
- Distinctive: line 45
If Brainstem was used, add one last line: "Any time, ask me to 'start up the Brainstem' to use it for learning and quick prototypes."
- Very specific: line 47
If the user asks to remove it, run undo with confirmation.
- Distinctive: line 48
If the user asks to "start up the Brainstem": if the health check answers, say it is running at http://localhost:7071 and open that page.
- Distinctive: line 53
If anything fails, say what happened in one sentence and stop.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Add Account Intelligence Agent to Copilot Studio
Do all of this yourself. The user only answers one question: yes or no. Speak in plain words. Never show JSON, commands, file paths, account names or IDs unless asked. Keep every reply to three short lines or fewer.
- Get the agent and check it is the right file:
curl -fsSLo copilot_studio_deploy_agent.py https://raw.githubusercontent.com/microsoft/aibast-agents-library/main/agents/@aibast-agents-library/templates/copilot_studio_deploy_agent.pyIts SHA-256 must befe3046c1372ee78812bddd29fba26d159c798916960ca9ab68d855e598eb4095. If not, stop. - Brainstem is optional. If
curl -fs http://localhost:7071/healthanswers, it is already running: use it (step 2b) and do not mention it. If it does not answer, remember to offer it in step 5. Never push it; "no" is a fine answer. 2a. Only if the user said yes to Brainstem in step 5, install it with the official one-liner (macOS/Linux:curl -fsSL https://microsoft.github.io/aibast-agents-library/install.sh | bash, Windows:irm https://github.com/microsoft/aibast-agents-library/releases/download/installers/install.ps1 | iex). Wait up to two minutes for the health check. If it never answers, say so in one line and carry on without it. 2b. Hot-load the agent into Brainstem:curl -fs -F file=@copilot_studio_deploy_agent.py -F sha256=fe3046c1372ee78812bddd29fba26d159c798916960ca9ab68d855e598eb4095 http://localhost:7071/agents/importFrom then on, send each step below to Brainstem in plain words withcurl -fs http://localhost:7071/chat -H 'Content-Type: application/json' -d '{"user_input": "..."}'(for example "CopilotStudioDeploy: plan account-intelligence") and read theresponsefield. Without Brainstem, run the same steps withpython3 copilot_studio_deploy_agent.py <step>. - Check the sign-in (
check).- If
pacis missing, install it withdotnet tool install --global Microsoft.PowerApps.CLI.Tooland check again. - If not signed in, run
pac auth create --deviceCodeand tell the user: "Sign in with your Microsoft account in the browser window." Never ask for a password.
- If
- Get the plan for account-intelligence in the active environment from the check (
plan). - Tell the user in one or two sentences what will happen and where, plus any note. Ask: "Go ahead?" Wait for yes. Do not explain how you are running. If Brainstem is not running, add one optional line, once, in these words: "Optional: I can also set up Brainstem, a free AI that runs on your computer. It keeps this agent, so later you can just say 'remove it' or 'add another one'. Say 'yes, with Brainstem' if you want it." Then do step 2a and 2b before deploying. Plain "yes" deploys without it.
- Deploy it with confirmation (
deploy ... --yes, or "confirm yes" to Brainstem). Never replace an existing install unless the user asked to overwrite. - Say: "Done. Open Copilot Studio, pick
<environment>, open Account Intelligence Agent, and ask:" and the test question. Add: "To remove it later, just ask me." If Brainstem was used, add one last line: "Any time, ask me to 'start up the Brainstem' to use it for learning and quick prototypes." - If the user asks to remove it, run
undowith confirmation. - If the user asks to "start up the Brainstem": if the health check answers, say it is running at
http://localhost:7071 and open that page. Otherwise start it with
~/.brainstem/src/rapp_brainstem/start.sh(Windows:%USERPROFILE%/.brainstem/src/rapp_brainstem/start.ps1) in the background, wait for the health check, then open http://localhost:7071. If Brainstem was never installed, offer to install it (step 2a).
If anything fails, say what happened in one sentence and stop.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
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.

