aibast-easy-mode-copilot
Skill8 starsChanged 3 months agoMITView on GitHub
Run supported AIBAST workshops directly through GitHub Copilot Agent mode.
We split this skill into the rules it gives an agent
25 rules. About 0 are common, 17 are distinctive, and 8 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈17
Distinctive · estimate
This author's own choices. Worth a look.
8
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 29
When the user asks what is available, or asks for a workshop without naming one (for example Show me the AIBAST library, then give me the …
- Very specific: line 37
Ask one question: which workshop they want.
- Distinctive: line 43
Never choose for the user, and never download a workshop before they choose.
- Distinctive: line 47
Before resolving or deploying a workshop, run the repository-owned, fail-closed setup step:
- Very specific: line 54
Stop when it exits nonzero or reports passed: false.
- Very specific: line 61
Check whether the mcs-assistant Copilot Studio capabilities are already available.
- Distinctive: line 63
If they are missing, execute these GitHub Copilot plugin-manager commands in order:
- Distinctive: line 84
Verify the installed plugin exposes the Copilot Studio manage, describe, initialize, and architect capabilities.
- Very specific: line 88
Use only microsoft/copilot-studio-plugin and the installed ID mcs-assistant@copilot-studio-plugin.
- Very specific: line 95
When the user says Give me <solution> using Easy Mode and test it for me:
- Very specific: line 97
Run python3 tools/easy_mode_preflight.py --json and require passed: true.
- Distinctive: line 103
Verify the portable source SHA.
- Distinctive: line 104
Create an isolated workspace with only required files and BasicAgent.
- Very specific: line 105
Import the class named by deployment.json.
- Distinctive: line 120
Use the plugin's read-only describer for an existing agent and its deterministic initializer only when a new target project is required.
- Distinctive: line 122
Use the plugin architect to assemble or migrate the exact reviewed instructions, knowledge, skills, model, and modern agentic-loop YAML.
- Distinctive: line 124
If the recorded schema exists, use the plugin manager to clone and reconnect automatically, then pull and reconcile it.
- Distinctive: line 126
Remove web search and unapproved tools, then validate the generated source and PAC project before any remote write.
- Distinctive: line 128
Use the plugin manager to push the Draft.
- Distinctive: line 137
Never ask the user for URLs, environment IDs, commands, or test markers.
- Distinctive: line 138
Never mix assets from different Git revisions.
- Distinctive: line 139
Never deploy without the verified Microsoft Copilot Studio plugin and supported PAC CLI.
- Distinctive: line 141
Never invent a missing result or success-shaped fallback.
- Distinctive: line 142
Never retry until a response happens to pass.
- Distinctive: line 143
Stop at Draft. Never publish.
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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
AIBAST Easy Mode — GitHub Copilot
Once this file is dragged into GitHub Copilot Chat in VS Code, run the complete Easy Mode harness directly in Copilot. This skill owns discovery, local testing, Draft deployment, Preview validation, and evidence capture.
Public source
- Repository:
microsoft/aibast-agents-library - Workshop branch:
main - Registry path:
registry.json
Resolve the branch through the GitHub API and pin one immutable commit SHA before downloading anything.
Persist the active run in .aibast/easy-mode-state.json, including solution,
revision, local test results, Copilot Studio identity, status, and
published: false. Also persist the Copilot Studio plugin repository,
installed plugin ID, resolved revision or installed version, PAC CLI version,
and verification status.
Choose from the library
When the user asks what is available, or asks for a workshop without naming
one (for example Show me the AIBAST library, then give me the workshop I pick
using Easy Mode and test it for me):
- Fetch
registry.jsonfrom the pinned commit. - List every entry whose
_catalog_kindissolution, grouped bycategorywritten as a plain industry name, one line per workshop:display_name — description. Do not paste JSON or file paths. - Ask one question: which workshop they want. Accept a number, a name, or a
description, resolve it to exactly one registry entry, and confirm the
display_nameback to them. - Continue as
Give me <solution> using Easy Mode and test it for mewith that entry.
Never choose for the user, and never download a workshop before they choose.
Required local Copilot Studio plugin
Before resolving or deploying a workshop, run the repository-owned, fail-closed setup step:
python3 tools/easy_mode_preflight.py --jsonStop when it exits nonzero or reports passed: false. Record the reported
installed plugin/version and PAC CLI version in
.aibast/easy-mode-state.json.
The preflight owns plugin discovery, installation, and PAC remediation. Its explicitly reviewed CLI sequence is:
- Check whether the
mcs-assistantCopilot Studio capabilities are already available. If they are missing, execute these GitHub Copilot plugin-manager commands in order:
copilot plugin marketplace add microsoft/copilot-studio-plugin copilot plugin install mcs-assistant@copilot-studio-plugin- Recheck
copilot plugin list, then resolvemicrosoft/copilot-studio-pluginthrough the GitHub API and record its immutable default-branch commit SHA or the installed plugin version in.aibast/easy-mode-state.json. Inspect
pac --version, including version output from a nonzero exit. The plugin requires a Power Platform CLI version newer than 2.9.3. When PAC is too old and .NET is available, run:dotnet tool update --global Microsoft.PowerApps.CLI.ToolRecheck PAC and otherwise stop with the reported remediation.
- Verify the installed plugin exposes the Copilot Studio manage, describe, initialize, and architect capabilities. Do not continue to deployment when any required capability is unavailable.
Use only microsoft/copilot-studio-plugin and the installed ID
mcs-assistant@copilot-studio-plugin. Do not substitute a fork or execute
unreviewed plugin source directly. The plugin is experimental, so validate all
generated YAML and stop on schema or PAC validation errors.
Build and test
When the user says Give me <solution> using Easy Mode and test it for me:
- Run
python3 tools/easy_mode_preflight.py --jsonand requirepassed: true. - Resolve the requested solution from immutable
registry.json. - Fetch its
deployment.json,export-manifest.json, portable*_agent.py,tests/demo_cases/<slug>.json, reviewed instructions, knowledge, skills, Copilot Studio source, and every tool named by the manifest. - Verify the portable source SHA.
- Create an isolated workspace with only required files and BasicAgent.
- Import the class named by
deployment.json. - Execute every locked case with its operation and arguments.
- Validate every
must_includeandmust_not_includemarker. - Persist
status: tested. - Return the verdict and:
Deploy it into Copilot Studio for me.
Deploy
When the user says Deploy it into Copilot Studio for me:
- Resolve
itfrom.aibast/easy-mode-state.json. - Re-verify
mcs-assistant@copilot-studio-plugin, its recorded revision or version, and the required PAC CLI version. - Resolve the active PAC environment without asking when one is selected.
- Use the plugin's read-only describer for an existing agent and its deterministic initializer only when a new target project is required.
- Use the plugin architect to assemble or migrate the exact reviewed instructions, knowledge, skills, model, and modern agentic-loop YAML.
- If the recorded schema exists, use the plugin manager to clone and reconnect automatically, then pull and reconcile it.
- Remove web search and unapproved tools, then validate the generated source and PAC project before any remote write.
- Use the plugin manager to push the Draft. Never invoke publish.
- Open the real Draft and run every locked case in a fresh Preview chat.
- Validate all markers and capture evidence.
- Persist
status: completeand report exact totals, plugin provenance, andpublished: false.
Rules
- Own all terminal, file, PAC CLI, browser, and evidence work.
- Never ask the user for URLs, environment IDs, commands, or test markers.
- Never mix assets from different Git revisions.
- Never deploy without the verified Microsoft Copilot Studio plugin and supported PAC CLI.
- Never invent a missing result or success-shaped fallback.
- Never retry until a response happens to pass.
- Stop at Draft. Never publish.
In this repository509 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- rapp_ai/CLAUDE.mdCLAUDE.md
- rapp_brainstem/CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- rapp_ai/.github/copilot-instructions.mdCopilot instructions
- community_rappSkill
- generate-demoSkill
- rapp-brainstemSkill
- aibast-easy-mode-brainstemSkill
- aibast-staging-ring-testSkill
- 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
- benefits-summarySkill
- health-insuranceSkill
- leave-balanceSkill
- parental-leaveSkill
- remindersSkill
- remote-workSkill
- submit-time-offSkill
- time-off-checkSkill
- asset-maintenance-forecast-asset-healthSkill
- asset-maintenance-forecast-budget-projectionSkill
- asset-maintenance-forecast-maintenance-forecastSkill
- asset-maintenance-forecast-work-order-planSkill
- compare-plansSkill
- deadline-remindersSkill
- document-checklistSkill
- election-draftSkill
- enrollment-windowSkill
- life-event-changeSkill
- provider-networkSkill
- approval-routeSkill
- content-scanSkill
- draft-briefSkill
- figure-checkSkill
- gap-reportSkill
- list-templatesSkill
- proactive-applicant-updatesSkill
- new-application-intake-checkSkill
- automated-code-compliance-reviewSkill
- synthetic-permit-fee-estimateSkill
- inspector-board-and-coverageSkill
- intake-triage-and-review-routingSkill
- permit-backlog-and-complaint-riskSkill
- permit-issuance-packageSkill
- permit-status-and-zoning-detailSkill
- permit-review-checklistSkill
- plan-review-routingSkill
- The first 60 shown.
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.

