MCAF: Developer Experience
Trigger On
- the repo is hard to run, test, debug, or onboard into
- local setup differs too much across contributors
- the inner loop is slow or undocumented
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
- production deployment or pipeline policy
- pure documentation cleanup with no developer workflow impact
Inputs
- the current local setup and first-run path
- actual build, run, debug, and test commands
- pain points in onboarding or the inner loop
Quick Start
- Read the nearest
AGENTS.md and confirm scope and constraints.
- Run this skill's
Workflow through the Ralph Loop until outcomes are acceptable.
- Return the
Required Result Format with concrete artifacts and verification evidence.
Workflow
- Find the slowest or most fragile part of the inner loop:
- clone and setup
- build
- run and debug
- test
- Standardize tasks before optimizing them.
- Prefer one documented way to run the full solution locally.
- Pull only the references that match the local-dev problem you are fixing.
Deliver
- lower-friction local workflow
- better onboarding
- reproducible build, run, test, and debug paths
Validate
- a newcomer can follow the docs without hidden setup knowledge
- the inner loop is explicit and reproducible
- cross-platform or containerized guidance is used only where it helps
- local development uses real services, containers, or sandbox environments instead of fakes or stubs
Ralph Loop
Use the Ralph Loop for every task, including docs, architecture, testing, and tooling work.
- Plan first (mandatory):
- analyze current state
- define target outcome, constraints, and risks
- write a detailed execution plan
- 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_applicable with explicit reason and fallback path.
Required Result Format
status: complete | clean | improved | configured | not_applicable | blocked
plan: concise plan and current iteration step
actions_taken: concrete changes made
validation_skills: final skills run, or skipped with reasons
verification: commands, checks, or review evidence summary
remaining: top unresolved items or none
For setup-only requests with no execution, return status: configured and exact next commands.
Load References
- read
references/developer-experience.md first
- open
references/onboarding-guide-template.md only when relevant
Example Requests
- "Make this repo easier to onboard into."
- "Document a sane local run and debug loop."
- "Fix the dev setup drift across machines."
1---2name: mcaf-devex3description: Improve developer experience for multi-component solutions: onboarding, F5 contract, cross-platform tasks, local inner loop, and reproducible setup. Use when the repo is hard to run, debug, test, or onboard into.4---56# MCAF: Developer Experience78## Trigger On910- the repo is hard to run, test, debug, or onboard into11- local setup differs too much across contributors12- the inner loop is slow or undocumented1314## Value1516- produce a concrete project delta: code, docs, config, tests, CI, or review artifact17- reduce ambiguity through explicit planning, verification, and final validation skills18- leave reusable project context so future tasks are faster and safer1920## Do Not Use For2122- production deployment or pipeline policy23- pure documentation cleanup with no developer workflow impact2425## Inputs2627- the current local setup and first-run path28- actual build, run, debug, and test commands29- pain points in onboarding or the inner loop3031## Quick Start32331. Read the nearest `AGENTS.md` and confirm scope and constraints.342. Run this skill's `Workflow` through the `Ralph Loop` until outcomes are acceptable.353. Return the `Required Result Format` with concrete artifacts and verification evidence.3637## Workflow38391. Find the slowest or most fragile part of the inner loop:40 - clone and setup41 - build42 - run and debug43 - test442. Standardize tasks before optimizing them.453. Prefer one documented way to run the full solution locally.464. Pull only the references that match the local-dev problem you are fixing.4748## Deliver4950- lower-friction local workflow51- better onboarding52- reproducible build, run, test, and debug paths5354## Validate5556- a newcomer can follow the docs without hidden setup knowledge57- the inner loop is explicit and reproducible58- cross-platform or containerized guidance is used only where it helps59- local development uses real services, containers, or sandbox environments instead of fakes or stubs6061## Ralph Loop6263Use the Ralph Loop for every task, including docs, architecture, testing, and tooling work.64651. Plan first (mandatory):66 - analyze current state67 - define target outcome, constraints, and risks68 - write a detailed execution plan69 - list final validation skills to run at the end, with order and reason702. Execute one planned step and produce a concrete delta.713. Review the result and capture findings with actionable next fixes.724. Apply fixes in small batches and rerun the relevant checks or review steps.735. Update the plan after each iteration.746. Repeat until outcomes are acceptable or only explicit exceptions remain.757. If a dependency is missing, bootstrap it or return `status: not_applicable` with explicit reason and fallback path.7677### Required Result Format7879- `status`: `complete` | `clean` | `improved` | `configured` | `not_applicable` | `blocked`80- `plan`: concise plan and current iteration step81- `actions_taken`: concrete changes made82- `validation_skills`: final skills run, or skipped with reasons83- `verification`: commands, checks, or review evidence summary84- `remaining`: top unresolved items or `none`8586For setup-only requests with no execution, return `status: configured` and exact next commands.8788## Load References8990- read `references/developer-experience.md` first91- open `references/onboarding-guide-template.md` only when relevant9293## Example Requests9495- "Make this repo easier to onboard into."96- "Document a sane local run and debug loop."97- "Fix the dev setup drift across machines."