jeremylongshore/tons-of-skills-marketplace / plugins/ai-agency/hyperflow/skills/dispatch
dispatch
FlaggedUse when a task file exists in .hyperflow/tasks/ and workers need dispatching. Fans out parallel workers under per-batch Reviewers, runs a final integration review, and commits per sub-task. Endpoint of the auto-chain — no auto-deploy. Trigger with /hyperflow:dispatch, "run the plan", "execute the task", "build it", "run the batches".
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 50.8 KB |
| references/examples.md | markdown | 5.9 KB |
| references/git-workflow.md | markdown | 5.9 KB |
| references/memory-system.md | markdown | 15.3 KB |
| references/output-style.md | markdown | 8.2 KB |
| references/quality-gates.md | markdown | 1.9 KB |
| references/review-levels.md | markdown | 4.4 KB |
| references/reviewer-prompt.md | markdown | 3.7 KB |
| references/worker-prompt.md | markdown | 2.7 KB |
references/quality-gates.md
View on GitHub# Quality Gates
Automated checks that must pass before a worker's output is approved. Runs after code review, before marking a task done.
## Flow
```
Worker completes
|
[Reviewer] Reviews code quality
|
[Worker] Runs quality gates
|
All green? -> Mark task done
|
Red? -> Send failures back to worker -> worker fixes -> re-run gates
```
## Checks
The orchestrator auto-detects which checks are available by scanning the project's package.json scripts and config files.
| Check | Detection | Command |
|-------|-----------|---------|
| Lint | `eslint.config.*` or `scripts.lint` | `pnpm lint` / `npm run lint` |
| Typecheck | `tsconfig.json` | `pnpm typecheck` / `npx tsc --noEmit` |
| Tests | `vitest.config.*` or `jest.config.*` | `pnpm test` (affected files only) |
| Build | `scripts.build` | `pnpm build` (only on final review) |
## Scope
- **Per-task gates:** Lint + typecheck + tests for affected files only (not full suite)
- **Final review gates:** Full lint + typecheck + build + full test suite
Running the full suite per task is wasteful. Scope checks to what the worker touched.
## Failure Handling
1. Gate fails -> the Reviewer extracts the error message
2. The Reviewer sends specific fix instructions to the worker
3. Worker fixes -> gates re-run
4. Max 3 retry loops per gate. After 3 failures, surface the error to the user
## Configuration
To disable specific gates or add custom checks, users can add to their project CLAUDE.md:
```markdown
## Hyperflow Quality Gates
- skip: typecheck
- add: pnpm format --check
```
Or say in conversation: "hyperflow: skip typecheck for this session"
## Worker Prompt Addition
When quality gates are active, append to the worker prompt constraints:
```
## Quality Requirements
- Code must pass lint (eslint)
- Code must pass typecheck (tsc --noEmit)
- Tests must pass for affected files
- Run these yourself before reporting completion
```
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deployment | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy. | Stars: 119k | Updated | Claude CodeCodex | Verified | Install |
| childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |