Mcaf Agile Delivery
Productivitymcaf-agile-deliveryMcaf Agile Delivery is an Agent Skill for productivity published in the managedcode/dotnet-skills repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.
Apply MCAF agile-delivery guidance for backlog quality, roles, ceremonies, and engineering feedback. Use when defining how the team plans, tracks work, and turns feedback into durable improvements. USE FOR: the team needs backlog, ceremony, role, or feedback-loop rules; delivery process is vague, too heavy, or living only in chat; recurring team pain needs to become durable. DO NOT USE FOR: repo governance that belongs in AGENTS.md; feature planning for one specific feature doc. INVOKES: inspect the repository context, edit targeted files, and run relevant build, test, lint, or validation commands when changes are made.
How to use this skill
Bring this guide into your coding agent with a prompt tailored to the tool you use.
- Open your project in Codex.
- Copy and paste the prompt below.
- Review files and risks before approving any action.
Inspect the Agent Skill at https://github.com/managedcode/dotnet-skills/blob/HEAD/catalog/Platform/MCAF/skills/mcaf-agile-delivery/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/mcaf-agile-delivery, but wait for my approval before writing files or running scripts.
Copying this prompt does not install or run the skill. Review third-party files before use.
MCAF: Agile Delivery
Trigger On
- the team needs backlog, ceremony, role, or feedback-loop rules
- delivery process is vague, too heavy, or living only in chat
- recurring team pain needs to become durable repo guidance
Value
- produce a concrete project delta: code, docs, config, tests, CI, or review artifact
- reduce ambiguity through explicit planning, verification, and final validation skills
- leave reusable project context so future tasks are faster and safer
Do Not Use For
- repo governance that belongs in
AGENTS.md - feature planning for one specific feature doc
Inputs
- the current delivery pain point
- backlog, role, ceremony, and feedback mechanisms that already exist
- where the team stores durable agreements, if anywhere
Quick Start
- Read the nearest
AGENTS.mdand confirm scope and constraints. - Run this skill's
Workflowthrough theRalph Loopuntil outcomes are acceptable. - Return the
Required Result Formatwith concrete artifacts and verification evidence.
Workflow
- Keep delivery artefacts concrete:
- backlog
- roles
- ceremonies
- engineering feedback
- Prefer lightweight agreements over process theatre.
- When a pain point repeats, turn it into a rule, doc, or skill update.
- Pull only the references that match the current process problem.
Deliver
- concrete delivery guidance
- durable team agreements
- feedback loops that update docs, skills, and rules
Validate
- the process guidance fixes a real delivery problem
- roles and rituals are explicit enough to use
- recurring pain is converted into a durable artifact, not more chat
Ralph Loop
Use the Ralph Loop for every task, including docs, architecture, testing, and tooling work.
- Brainstorm first (mandatory):
- analyze current state
- define the problem, target outcome, constraints, and risks
- generate options and think through trade-offs before committing
- capture the recommended direction and open questions
- Plan second (mandatory):
- write a detailed execution plan from the chosen direction
- list final validation skills to run at the end, with order and reason
- Execute one planned step and produce a concrete delta.
- Review the result and capture findings with actionable next fixes.
- Apply fixes in small batches and rerun the relevant checks or review steps.
- Update the plan after each iteration.
- Repeat until outcomes are acceptable or only explicit exceptions remain.
- If a dependency is missing, bootstrap it or return
status: not_applicablewith explicit reason and fallback path.
Required Result Format
status:complete|clean|improved|configured|not_applicable|blockedplan: concise plan and current iteration stepactions_taken: concrete changes madevalidation_skills: final skills run, or skipped with reasonsverification: commands, checks, or review evidence summaryremaining: top unresolved items ornone
For setup-only requests with no execution, return status: configured and exact next commands.
Load References
- read references/agile-delivery.md first
- open references/roles.md only for a narrower topic
Example Requests
- "Define a lighter delivery model for this team."
- "Turn repeated feedback pain into repo guidance."
- "Fix our backlog and ceremony chaos."