m3dcodie
- 14 skills
- 0 followers
- 11 hours ago last updated
- ▌ Eng Flow QA · m3dcodieProduction Stage 7 — browser-based, front-end-only behavioral QA. Exercises the running app (not the diff) to find bugs a code review can't catch. Drives the browser via the plugin-bundled eng-flow-browse skill — falls back to a guided manual checklist if browser automation is unavailable in a given session. Documents bugs; does not fix them — fixes route through eng-flow-implement.
- ▌ Eng Flow Mvp · m3dcodieMVP mode — the fast, low-ceremony counterpart to the ten-stage production track (PROCESS.md). Captures a one-pager, breaks it into a flat checklist (no epics/stories), gives a ballpark time/token estimate and gets an explicit go/no-go, then runs an auto-continuous implement loop that keeps committing (and, if the user opts in, pushing) until the checklist is done or a hard-stop condition hits, then hands off to eng-flow-ship. Self-triggerable — reuses an existing eng-flow-spec spec.md if one exists instead of re-capturing it, but doesn't require one.
- ▌ Eng Flow Ship · m3dcodieProduction Stage 8, terminal — ships a feature branch. Gate-checks Stage 6/7 verdicts (code-review.md, qa-report.md) instead of re-reviewing, merges base before a final regression pass, bumps version/changelog if the project tracks them, commits, pushes, and opens a PR. Never deploys to a cloud target — matches local/container/GitHub practice.
- ▌ Eng Flow Spec · m3dcodieFront door for new work — routes an idea, a stakeholder-greenlit product, or a feature/story into the right requirements process, interrogates for a spec, optionally runs bounded competitor research, and saves to eng-flow/specs/. Pure requirements only — never asks technical questions except on the feature/story path where code already exists.
- ▌ Eng Flow Retro · m3dcodieProduction Stage 9 — blameless retrospective on a shipped (or in-progress) story, capturing durable learnings to a project-level log so future implementation work doesn't repeat the same mistakes. Distinct from a weekly velocity report — this is per-story, root-cause-focused, and only as useful as whether later stages actually consult what it logs.
- ▌ Eng Flow Browse · m3dcodieGeneral-purpose visual-verification tool wrapping the plugin-bundled Playwright MCP server — navigate a URL, screenshot, check console errors, verify a page/component renders correctly. Usable standalone by any agent/skill in this plugin, any time — not tied to a production-track stage.
- ▌ Eng Flow Analytics · m3dcodieProduction Stage 10 — on-demand rollup report of eng-flow/analytics.jsonl (time/token log) and eng-flow/findings.jsonl (bug counts), both incrementally written by other eng-flow skills. Reports per-story and per-stage totals, tokens by category, cycle time (elapsed vs. active), stage-transition gaps, review/QA rework cycles, and bug rate. Read-only; doesn't instrument itself.
- ▌ Eng Flow Implement · m3dcodieProduction Stage 5 — implements one pending task from a story's tasks.md, one at a time, using an incremental TDD loop (implement, test, verify, commit). Terminal stage after eng-flow-epics-stories-tasks. Whole-story auto mode is not built yet — this only ever does the next single task, then stops.
- ▌ Eng Flow UI Design · m3dcodieProduction Stage 3.6 — takes a saved spec/domain-model/architecture and produces the UI design a UI-touching story needs before Stage 4 exists — a reusable project-level design system, per-journey wireframes, and (once gated) static HTML/CSS mockups. Skipped entirely if the spec's journeys have no UI surface. Between Stage 3.5 (Eng Review) and Stage 4 (Epics/Stories/Tasks).
- ▌ Eng Flow Eng Review · m3dcodieProduction Stage 3.5 — reviews a saved architecture.md against engineering-leadership judgment before it becomes epics/stories/tasks. Catches architecture problems while they're still cheap to fix (before backlog breakdown, before implementation), not a code review — no code exists yet at this point in the track.
- ▌ Eng Flow Code Review · m3dcodieProduction Stage 6 — reviews an implemented diff (branch vs. base, or a specific story's commits) across five axes before it ships. Post-implementation counterpart to Stage 3.5's pre-implementation architecture review — this one reviews actual code, not a design doc.
- ▌ Eng Flow Architecture · m3dcodieProduction Stage 3 — takes a saved eng-flow spec and domain model and produces the technical design — tech stack, a tech-labeled system diagram, API contracts, quantified non-functional requirements, deployment topology, and ADRs. This is where technical decisions actually get made; Stages 1 and 2 deliberately deferred all of them here.
- ▌ Eng Flow Domain Model · m3dcodieProduction Stage 2 — takes a saved eng-flow spec and turns its named domains into a domain model, data flows, and a conceptual system diagram. No tech stack, no deployment, no API shape — that's Stage 3. Run by an "architect" persona, after eng-flow-spec, before eng-flow-architecture.
- ▌ Eng Flow Epics Stories Tasks · m3dcodieProduction Stage 4 — turns a spec's domains and journeys, cross-checked against the architecture's system diagram, into epics and stories in a project-level backlog (not per-spec — epics/stories outlive any one spec run). Task-level breakdown is separate and on-demand, only generated per-story once the user decides to implement it.