parallel-brief

Solid

Write a subagent brief that isolates ports, files, worktrees, scratch output, baselines, and primary evidence before parallel work begins.

AI & Automation 103 stars 15 forks Updated today MIT

Install

View on GitHub

Quality Score: 85/100

Stars 20%
67
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
80
License 10%
100
Description 5%
100

Skill Content

# Parallel brief Concurrency is not the risk; uncoordinated shared state is. Every rule here came from a real failure on 2026-08-03 or 2026-08-04. ## 1. Give every browser run its own server `playwright.config.ts` may reuse an existing local server. Two agents can therefore measure different code while both report success. - Assign a unique port and explicit `PLAYWRIGHT_BASE_URL`. - Use `PLAYWRIGHT_STATIC=1` when proof must cover the exported build. - Run one spec at a time so server failure is distinguishable from product failure. ## 2. One person owns each ratchet baseline Two branches lowering the same literal from one stale starting value cannot be combined arithmetically. The merging owner recounts after integration, lowers the number once, and proves one step lower turns red. Only one agent edits a ratchet file. Others may report measurements, never commit competing baselines. ## 3. Worktrees and stash - Never run `git add -A`; a worktree directory can be staged as an empty gitlink. - Subagents do not remove worktrees. The coordinating owner may remove a task-created worktree only after confirming ownership, preserved changes, and no active users. Otherwise report its path for later cleanup. - Never use `git stash`; stash is repository-wide and has erased another agent's work in this project. ## 4. Keep measurement scratch outside the repository Git may ignore a path that ESLint still scans. Probe files under `output/` or `.tmp/` have inflated warning c...

Details

Author
wlsdks
Repository
wlsdks/ontology-atlas
Created
4 months ago
Last Updated
today
Language
TypeScript
License
MIT

Integrates with

Similar Skills

Semantically similar based on skill content — not just same category

AI & Automation Listed

parallel-agents

Fan independent work out to multiple subagents that run concurrently, each with a focused scope and self-contained instructions, then review and integrate their results. Use when you face two or more genuinely independent tasks — separate failing test files, unrelated bugs, distinct subsystems — that share no state and don't depend on each other's order.

5 Updated 3 days ago
KhaledSaeed18
AI & Automation Listed

agent-sync

Use when several coding agents work one repository at the same time and must not collide - claiming a task, reserving the next decision/question/ticket id, journaling a run, filing or answering a cross-repo dependency, or regenerating the shared board. Triggers - 'claim this task' / 'возьми задачу', 'who is working on X' / 'кто сейчас делает X', 'reserve an id' / 'зарезервируй id', 'sync the board' / 'обнови доску', 'set up agent coordination' / 'настрой координацию агентов', /agent-sync. Use it BEFORE editing any shared registry file (decisions, open questions, roadmap, workstreams, dependencies) in a project that has .claude/agent-sync.json, even when the user never mentions coordination - an unclaimed edit to those files is how two agents overwrite each other.

2 Updated today
appvillis-com
AI & Automation Listed

agent-isolation

Use before spawning any agent that writes files, and by every developer/fixer agent as its first and last action. Gives each agent its own git worktree, forbids blanket staging, and requires confirming a mutation actually landed. Triggers from /app-build, /app-audit, parallel-orchestrator, and any parallel agent launch. Prevents parallel agents corrupting each other's work.

4 Updated yesterday
vmobifystudio