implement-fleet

Solid

Orchestrator-workers variant of implement-approved-slice that executes independent approved slices in parallel. Reads per-slice Scope and Depends-on from IMPLEMENTATION_PLAN.md, builds the slice DAG, computes parallelizable waves (ready slices whose file scopes are pairwise disjoint with no shared migration, lockfile, codegen, or barrel export), validates disjointness before dispatch, runs one worktree-isolated worker per slice per wave (each executing the implement-approved-slice contract), merges the worktrees, and runs a mandatory build + typecheck + test integration gate after each wave. Use when the active task has an approved multi-slice plan whose Execution waves show at least one wave of size 2 or more. Do not use when the slice DAG is a pure chain (use implement-approved-slice), when slices are unapproved, when Scope/Depends-on are not declared in the plan, or for single-slice tasks.

AI & Automation 6 stars 0 forks Updated 5 days ago MIT

Install

View on GitHub

Quality Score: 81/100

Stars 20%
28
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
80
License 10%
100
Description 5%
100

Skill Content

Act as a senior/staff engineering execution orchestrator running independent approved slices in parallel for the active engineering task. Goal: For an approved multi-slice plan whose slice dependency graph is wider than a chain, dispatch one worktree-isolated worker per independent slice, wave by wave, each worker executing the `implement-approved-slice` contract for exactly one slice. The orchestrator computes the waves from `IMPLEMENTATION_PLAN.md` (`Scope` + `Depends-on` per slice), validates file-scope disjointness before dispatch, merges each wave's worktrees, and runs a mandatory build + typecheck + test integration gate before opening the next wave. This is a parallel orchestrator over `implement-approved-slice`, not a replacement for it; `implement-approved-slice` stays the canonical single-slice unit and the fallback. Expected wall-clock reduction is bounded by the width of the DAG: deep chains see little gain (and route back to sequential execution), wide graphs see up to the parallel-branch count. Mandatory context bootstrap (before any output): <!-- shared:mandatory-context-bootstrap --> - Read these sections in `WORKFLOW_OPERATING_SYSTEM.md` first: - `## LLM execution contract` - `## Editor mode policy` (mode definitions only; the tool mapping table is lazy-loaded in `wos/editor-mode-mappings.md` and needed only for non-Claude-Code tools) - `## Global output contract` (including **Adaptive handoff** and **Mode selection rule**) - `## Cross-cutting workf...

Details

Author
Mozurok
Repository
Mozurok/fhorja.dev
Created
1 months ago
Last Updated
5 days ago
Language
Python
License
MIT

Similar Skills

Semantically similar based on skill content — not just same category

Code & Development Solid

implement-approved-slice

Implement only the approved slice with minimal, explicit, review-friendly changes, then persist execution evidence in slice notes and TASK_STATE.md. The single official execution path of the workflow. Supports an opt-in test-first (TDD) mode, enabled per slice or via --tdd, that writes the failing test before the code (ADR-0063). Use when the task has a valid IMPLEMENTATION_PLAN.md, the current slice is explicitly defined and approved, correctness-critical ambiguity is already resolved, and the files in scope are known well enough to edit safely. Do not use when the task is still in discovery or contract refinement or planning, when unresolved ambiguity still affects correctness, when the slice boundary is still unclear, when the next step is only to sync task memory or close the slice (use sync-task-state or slice-closure), or when the remaining work is a narrow micro-delta anchored to an already-executed slice with the same intent (use implement-slice-complement).

6 Updated 5 days ago
Mozurok
Code & Development Solid

autonomous-run

Drive an approved, waved IMPLEMENTATION_PLAN through the autonomous delivery track. A thin dispatcher over the existing fleet primitives (the Workflow tool, implement-approved-slice as single writer) bounded by two human gates and a runtime governor. Runs verifiable slices with little supervision and emits PROPOSED slice diffs only; it never merges. Use when the plan is approved (approve-plan), autonomous-readiness returned BOOT, broken into dependency-ordered waves, and the maintainer wants the work between the two gates run hands-off in a single supervised session. Do not use when the plan is not yet approved (run approve-plan), readiness is absent or NOT-READY (run autonomous-readiness), the work is a single slice (use implement-approved-slice), the run would need to auto-merge (never allowed; a human always performs the merge), or cross-session durable resume (restart and re-attach) is required (out of v1 scope; a detached continuous background session is in scope via the opt-in background mode).

6 Updated 5 days ago
Mozurok
AI & Automation Solid

implementation-plan

Define an incremental, reviewable, production-safe implementation plan for the active task and persist it as IMPLEMENTATION_PLAN.md plus a TASK_STATE.md update. Breaks work into the smallest safe slices with objective, exact scope, ordering rationale, key risks, validation approach, exit criteria, and work complexity (LOW/MEDIUM/HIGH) per slice. No code is written. Also runs an annotate-only retrofit mode that backfills per-slice Scope and Depends-on plus an Execution waves section onto an existing in-progress plan so it can adopt implement-fleet, without re-planning. A --spec mode derives slices from a spec or PRD, checking every spec item is covered (ADR-0061). Use when impact is understood enough to plan safely, key boundaries are known, and major factual or decision ambiguity is already resolved. Do not use when the task is still too unclear, when key facts or decisions remain open, or when the current need is to implement an already-approved slice (use implement-approved-slice).

6 Updated 5 days ago
Mozurok