execute
Weave execute: compare independent adversarial implementations, then synthesize their best parts
- License 许可
- MIT
- 所属仓库
- tony/skills
- 最近更新
- 2026-11-08
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- execute
- description
- Weave execute: compare independent adversarial implementations, then synthesize their best parts
- allowed-tools
- [ "Bash", "Read", "Grep", "Glob", "Edit", "Write", "Task", "AskUserQuestion", "EnterPlanMode", "ExitPlanMode" ]
- argument-hint
- [--passes=N] [--timeout=N|none] [--mode=fast|balanced|deep] [--workers=subagents|model-clis] <task description>
- disable-model-invocation
- true
02 资源文件 1
- 参考文档agents/openai.yaml296 B
03 SKILL.md 正文
Weave Execute
Run a task across independent adversarial workers, using host-native sub-agents by default or separate model CLIs when selected. Each sub-agent or external worker uses its own git worktree. After all workers finish, synthesize the best elements of every implementation into one result. Unlike /weave:prompt, which picks one winner, this command cherry-picks the best parts of each worker's work.
The task comes from $ARGUMENTS. If there are none, ask the user what they want implemented.
A request like /weave:execute apply the latest session runs no workers: follow ../../references/mutating-run.md (Apply a recorded session) with this skill's adopt and update commands from its final phase, and skip the other phases.
<engine> is ../../scripts/engine.py resolved from this skill's directory to an absolute path, written literally in every command, and run with python3.
If context already proves there is no repository or no commit, stop there. Use only: "Stopped: execute needs a project checkout with at least one commit." Then one bullet: "Run it from that checkout." Do not explain the stash or worktree machinery or ask the user to create a commit.
Worker selection
<!-- portable: ask-user-choice=headless-default -->
Before any other unresolved configuration choice or operational step, read
../../references/worker-backends.md (Caller contract). Resolve
worker_backend from --workers=subagents|model-clis using that reference;
if the flag is absent, ask its worker question first.
If interactive choice is unavailable, honor its documented headless default.
Orchestration Plan
Enter plan mode before the first edit. In Claude Code call EnterPlanMode; in Cursor, Codex, or Gemini use /plan or Shift+Tab. Where plan mode is unavailable, present the plan as text.
Produce the plan per ../../references/mutating-run.md (Shared phases, Orchestration plan).
Present the plan and wait for approval, then exit plan mode (ExitPlanMode).
Phase 1: Start the session
Follow ../../references/ensemble-core.md (Start the session) with --command execute --mutating; it asks each unresolved setting through AskUserQuestion. Then start and dispatch per ../../references/mutating-run.md (Shared phases).
Phase 2: Implement in parallel
Use the worker prompt body of ../../references/mutating-run.md (Shared phases), with the task as <the task>.
Phase 3: Analyze the implementations
Capture, run the gates, and record the pass per ../../references/mutating-run.md (Shared phases). Judge per ensemble-core.md (Blind judging, Synthesis protocol). The convergence mode is file-by-file. Its brief asks it, for each file any participant modified, to compare the original (git show HEAD:<file>) with each snapshot, verify what the code does against what the participant claims, and score each version per file. Select the files per ../../references/mutating-run.md (Shared phases), and write the analysis per ../../references/prose-rules.md.
Phase 4: Multi-pass refinement
Follow ../../references/mutating-run.md (Refinement passes), repeating Phases 2 and 3.
Phase 5: Apply the best implementation
Follow ../../references/mutating-run.md (Apply gate and presentation): show the synthesis plan and wait before touching the main checkout.
-
Adopt the selected files:
$ python3 <engine> adopt \ --session "<session_dir>" \ --pass <final N> \ --pick <path>=<participant> \ --delete <path>If
adoptrefuses, follow../../references/mutating-run.md(Apply gate and presentation). -
Read the combined result and fix integration problems: imports, signatures, and API mismatches between files from different participants; naming, docstring, and import style per the project's conventions.
-
Run the project's quality gates, then record the state:
$ python3 <engine> update \ --session "<session_dir>" \ --event synthesis_applied -
Clean up per
../../references/mutating-run.md(Shared phases) (Apply). -
Read
../../references/present-results.mdand../../references/results/execute.md, and apply them withRESULT_KIND=execute,ARTIFACT_PATH=<session_dir>/pass-NNNN/synthesis.md,SESSION_DIR,PASS_COUNT=passes,IN_PLAN_MODE= false,LABEL_MAP_PATH=<session_dir>/pass-NNNN/label-map.json.
Finish
Follow ensemble-core.md (Finish). Report the files applied and the participant each came from, the quality-gate result, and unavailable participants with their failure class.
04 同仓库更多 Skills
serene-bliss
Use when asked to make a CLI --help, docs page, error message, or tooling UX more serene or calmer for developer experience; returns text, no edits.
review
Weave code review: run independent adversarial reviews in parallel, then synthesize findings
refine
Use when asked to refine a draft, iterate on code until cleaner, or polish a README through repeated critique and improvement.
prompt
Weave prompt: compare independent adversarial implementations, then adopt the single best one
plan
Weave planning: compare independent adversarial plans, then synthesize the best one
fix-review
Fix weave review findings: validate, add test coverage, fix, and commit each as atomic changes