Index of every page on this site: llms.txt
All skills
github avatar

/foundry-agentic-loop

@f10fdb8 official
by githubgithub/awesome-copilot41k stars
5,399
Run it yourself

Build agentic solutions on Microsoft Foundry, GitHub and Azure: hosted agents, toolbox tools and skills, Foundry IQ grounding and a React/FastAPI app. Three modes: rapid prototyping in an existing Foundry project; spec-driven development (SDD), where the foundry-agentic-loop-workflow runs Specify, Implement, Verify and Deploy to create the Foundry project and deploy with azd, or one phase runs alone; and Improve, which refines this skill and the workflow from past runs. Use for Agentic Loop requests and canvas actions, or end-to-end agent solutions from architecture to Azure deployment. Not for isolated Azure administration or unrelated UI edits.

  • 55 files
  • 352.6 KB
  • Updated last month
  • GitHub
Use this Skill: https://skilld.dev/gh/github/awesome-copilot/foundry-agentic-loop

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

referencesrun-skills-catalog.md

≈872 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Run skills catalog

Reusable run-phase agent skills. Unlike the build skills catalog (skills you install to help build the app), these are skills the agent itself runs at execution time.

Reuse, don't regenerate. When the prompt explicitly names one of these skills, reuse it as the local authoring artifact in ./skills/<skill-name>/, then publish/update its governed version and attach it to the agent's toolbox using current microsoft-foundry guidance and supported commands. Verify the agent loads and uses that version. Also reuse explicitly supplied sources outside this catalog. If a named source cannot be resolved, ask rather than silently generating a replacement; author a new skill only when it is actually new or the user approves replacement.

This is a starter set of examples, not an exhaustive list.

Repository Skill Reuse when the prompt explicitly names
github/awesome-copilot eyeball Visually inspect a rendered UI or screenshot and report what is on screen or off-spec
github/awesome-copilot finalize-agent-prompt Polish and finalize an agent's system / instruction prompt
github/awesome-copilot gtm-enterprise-account-planning Build an enterprise go-to-market account plan
github/awesome-copilot gtm-product-led-growth Plan a product-led-growth (PLG) go-to-market motion
github/awesome-copilot incident-postmortem Draft a structured incident postmortem (timeline, impact, root cause, action items)
github/awesome-copilot linkedin-post-formatter Format content into a LinkedIn-ready post
github/awesome-copilot md-to-docx Convert Markdown into a DOCX document
github/awesome-copilot roundup Summarize multiple sources or items into a single roundup
github/awesome-copilot tldr-prompt Produce a concise TL;DR summary of long content
aiappsgbb/agentic-loop factory-operations-triage Triage smart-factory anomalies, maintenance signals, and quality deviations with evidence-backed operator actions
aiappsgbb/agentic-loop production-flow-optimizer Diagnose production bottlenecks and propose safe, constraint-aware flow and shift plans
aiappsgbb/agentic-loop care-gap-outreach-planner Prioritize care gaps and prepare consent-aware patient outreach without making clinical decisions
aiappsgbb/agentic-loop post-discharge-care-coordinator Coordinate follow-up tasks, patient responses, and rule-based escalation after discharge
aiappsgbb/agentic-loop loan-file-readiness-reviewer Review lending files for completeness, consistency, freshness, and traceable exceptions
aiappsgbb/agentic-loop mortgage-underwriting-coordinator Assemble evidence, conditions, and compliance checks for human mortgage underwriting

For cataloged skills that declare a repository, name the source repository to the user, then install with the same command used for build skills:

gh skill install <repository> <skill> --agent github-copilot --scope project

After the skill is present locally, create and version it on Foundry and attach it to the toolbox.

Source: SKILL.md on GitHub

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No third-party reports yet.

Signed by skilld at f10fdb8. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated last month

README badge

README badge for github/awesome-copilot/foundry-agentic-loop