e8e572e0af
New skills for container agent task orchestration: - /decompose: break tasks into subtasks with dependency graph, write .agent-tasks.json - /orchestrate: check task state, launch container agents in git worktrees, poll for completion Updated with learnings from first real run (agent-runtimes M3, 9 tasks): - Prompts must end with "run pytest and fix failures" - State import conventions explicitly in prompts - Warn about uncommitted files before decomposing (worktrees need committed content) - Copy dependency outputs into downstream worktrees before launching Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
1.5 KiB
1.5 KiB
Custom Claude Skills — Future Ideas
F1: Pre-commit validation skill
- Problem: The "validate locally, deploy once" pattern is frequently violated — errors caught in prod that could be caught locally
- Idea: A
/validateskill that detects the project type and runs appropriate local validation (helm template, kustomize build, docker compose config, etc.) - Open questions: How to detect project type reliably? Should it be one skill or per-type?
- Depends on: More experience with which validations are commonly missed
F2: Milestone setup skill
- Problem: Starting a new milestone has boilerplate (create verify script skeleton, update README table, etc.)
- Idea: A
/new-milestone M9 "Velero backup"skill that scaffolds the milestone - Open questions: How much should be templated vs. left to Claude?
- Depends on: Stable milestone conventions across projects
F3: Task retry skill
- Problem: When a container agent task fails (via
/orchestrate), retrying requires manually editing.agent-tasks.jsonto reset status and optionally appending the error context to the prompt - Idea: A
/retry <task-id>skill that reads the failed task's error/logs, appends them to the prompt as "Previous attempt failed with: ...", resets status topending, and cleans up the old worktree/branch - Open questions: Should the retry prompt include the full error log or a summary? Should it increment a retry counter and give up after N attempts?
- Depends on:
/decomposeand/orchestratebeing validated in real use