$npx -y skills add evanklem/evanflow --skill evanflow-goSingle entry-point orchestrator for the entire EvanFlow loop. The user says "let's evanflow this", "use evanflow", "evanflow this idea", "run this through evanflow", "implement with evanflow", or any similar phrasing — and you walk the full loop (brainstorm → plan → execute → tdd
| 1 | # EvanFlow: Go (Entry-Point Orchestrator) |
| 2 | |
| 3 | Single entry point for the EvanFlow workflow. The user gives you an idea or task and asks to "evanflow it" — you take responsibility for walking the whole loop end-to-end, picking the right sub-skill at each step, and respecting checkpoints where the user must stay in control. |
| 4 | |
| 5 | You are the conductor; the other `evanflow-*` skills are the orchestra. |
| 6 | |
| 7 | ## Vocabulary |
| 8 | |
| 9 | See `evanflow` meta-skill for the shared vocabulary (deep modules, deletion test, vertical slice, grill, mockup quick-mode). |
| 10 | |
| 11 | ## When to Use |
| 12 | |
| 13 | Trigger phrases (or anything semantically equivalent): |
| 14 | - "let's evanflow this" |
| 15 | - "use evanflow" |
| 16 | - "evanflow this idea" |
| 17 | - "run this through evanflow" |
| 18 | - "implement with evanflow" |
| 19 | - "let's [do X] using evanflow" |
| 20 | |
| 21 | **SKIP when:** |
| 22 | - The user is asking a factual question (no skill needed at all) |
| 23 | - The user wants quick mockups only (the brainstorming skill's mockup quick-mode handles this directly — no full loop needed) |
| 24 | - The user explicitly invoked a specific sub-skill by name (`evanflow-debug`, etc.) — let them control granularly |
| 25 | - The work is a one-line fix or trivial change — full loop is overkill |
| 26 | |
| 27 | ## The Walk |
| 28 | |
| 29 | ### Phase 0 — Restate and Confirm Scope (one sentence) |
| 30 | |
| 31 | Confirm you've understood the idea in your own words, in one sentence. Examples: |
| 32 | > "Got it — you want to add an `archived` flag to messages so cancelled ones drop off the dashboard." |
| 33 | |
| 34 | Then ask one calibration question if scope isn't obvious: |
| 35 | > "Quick scope check: is this a small targeted change or a feature with multiple components?" |
| 36 | |
| 37 | If the user signals quick/small → consider whether a full evanflow loop is overkill. Offer a shortcut: "This sounds small — want me to skip brainstorming/planning and just TDD it directly? Or run the full loop anyway?" |
| 38 | |
| 39 | ### Phase 1 — Brainstorm (always, unless user opts out) |
| 40 | |
| 41 | **Announce:** "Step 1: brainstorming via `evanflow-brainstorming`." |
| 42 | |
| 43 | Invoke `evanflow-brainstorming`: |
| 44 | - Quick context check (skim relevant files; don't exhaustively explore) |
| 45 | - Scope check (decompose if multi-subsystem) |
| 46 | - Clarifying questions one at a time, multiple-choice when possible |
| 47 | - Propose 2–3 approaches with your recommendation as option (a) |
| 48 | - Embedded grill on the chosen approach |
| 49 | - Present the design in sections; get explicit approval |
| 50 | |
| 51 | **Mockup quick-mode bypass:** if the user originally said "show me mockups" rather than "implement," skip the full loop and produce mockups directly (HTML files, Figma frames, ASCII layouts — whatever the project uses). No spec, no plan, no TDD ceremony. |
| 52 | |
| 53 | **Checkpoint:** before continuing, the user must explicitly approve the design. Not a tacit yes — actual confirmation. |
| 54 | |
| 55 | ### Phase 2 — Plan (if non-trivial) |
| 56 | |
| 57 | **Announce:** "Step 2: writing the plan via `evanflow-writing-plans`." |
| 58 | |
| 59 | If scope is small (one file, one behavior change), skip to Phase 3 with a verbal plan ("I'll write a failing test for X, then minimal impl"). Otherwise: |
| 60 | |
| 61 | Invoke `evanflow-writing-plans`: |
| 62 | - File structure first (name files + responsibilities, deletion test on each) |
| 63 | - Embedded grill on the structure |
| 64 | - Bite-sized tasks |
| 65 | - **Step 2.5: parallelization check.** If the plan has 3+ independent units sharing a contract, offer `evanflow-coder-overseer` to the user as the execution path instead of sequential `executing-plans`. Lay out signals on both sides. User picks. |
| 66 | |
| 67 | If the user picks coder-overseer, structure the plan with a per-coder section + cohesion contract upfront. |
| 68 | |
| 69 | **Checkpoint:** before continuing, the user must approve the plan. |
| 70 | |
| 71 | ### Phase 3 — Execute (sequential or parallel) |
| 72 | |
| 73 | **Announce based on user's pick:** |
| 74 | - Sequential: "Step 3: executing the plan via `evanflow-executing-plans`." |
| 75 | - Parallel: "Step 3: executing in parallel via `evanflow-coder-overseer`." |
| 76 | |
| 77 | **Sequential path** — invoke `evanflow-executing-plans`: |
| 78 | - Step 0: parallelization re-check (one more chance to switch paths) |
| 79 | - Critical review of plan |
| 80 | - Set up TaskCreate items |
| 81 | - Task-by-task; each task uses `evanflow-tdd` for any production code |
| 82 | - Inline verification (typecheck, lint, test for affected workspaces) |
| 83 | - Stop and ask on blockers |
| 84 | |
| 85 | **Parallel path** — invoke `evanflow-coder-overseer`: |
| 86 | - Author cohesion contract (with named tests + integration tests at touchpoints) |
| 87 | - Decompose into coder tasks (max 5) |
| 88 | - Phase A: spawn coders for RED checkpoint (failing tests only) |
| 89 | - Verify all REDs are clean |
| 90 | - Phase B: spawn coders for vertical-slice GREEN |
| 91 | - Spawn per-coder overseers (use `subagent_type: evanflow-overseer` if av |