hyperflow-dispatch
Hyperflow-dispatch executes planned batches of implementation work from a task file, performing each sub-task sequentially with self-review against syntax, specification, and security checklists before committing individually. Use it when a task file exists in `.hyperflow/tasks/` and work involves building, implementing, adding, or refactoring code, with the single agent handling all execution itself rather than delegating to sub-agents.
git clone --depth 1 https://github.com/jeremylongshore/claude-code-plugins-plus-skills /tmp/hyperflow-dispatch && cp -r /tmp/hyperflow-dispatch/plugins/ai-agency/hyperflow/templates/antigravity/skills/hyperflow-dispatch ~/.claude/skills/hyperflow-dispatchSKILL.md
# hyperflow-dispatch — execution phase (Antigravity single-agent) Execute the task file from `hyperflow-scope`. **No sub-agent dispatch and no model tiers in Antigravity** — you do each batch yourself, then self-review before committing. Follow the `hyperflow` doctrine. ## Per batch 1. **Implement** every sub-task in the batch (sequentially; they were planned as small, independent units). 2. **Self-review** the batch diff against the level checklist: - **L1** syntax/format/obvious bugs · **L2** spec compliance, naming, edge cases · **L3** cross-file integration + security (secrets, injection, validation). - Elevate to L3 when the change touches auth, data, or external input. Fix anything found before committing. 3. **Quality gates** on affected files: run the project's lint, typecheck, and tests. Fix failures (never `--no-verify`). 4. **Commit per sub-task** — one sub-task = one conventional commit (respect commitlint: lowercase subject, allowed scope). Stage only that sub-task's files; never commit files you didn't change. 5. **Update the task file's status block** (tick the sub-task, bump progress) and append any durable learning to `.hyperflow/memory/`. ## After all batches 6. **Final integration self-review** over the cumulative diff — catch cross-batch contradictions, scope leaks, and `any`/type regressions. 7. **End gate** via AskUserQuestion: offer to run `hyperflow-audit` (independent review) and/or `hyperflow-deploy`. Both are binary (no recommended marker). Never auto-push. ## Rules - A `SECURITY_VIOLATION` halts immediately — no commit, no continue. - If the working tree is dirty with files you didn't create (concurrent work), never stage them; re-check `git status` before each commit. - Auto mode completes every sub-task before any summary — no partial "to resume" hand-offs.
Audit and fix Claude Code SKILL.md files to meet enterprise compliance standards. Analyzes frontmatter, required sections, and style. Use when you need to validate or repair skills in a plugin directory.
Learn how SKILL.md files work in Claude Code plugins, then build a production-quality agent skill from scratch. Covers frontmatter schema, body structure, testing, and iteration.
Step-by-step guide to writing a SKILL.md file for Claude Code. Learn how to plan, structure, and test auto-activating skills with proper frontmatter, allowed-tools, dynamic context injection, and supporting files.
|
|
|
|
|