Files
custom-claude-skills/MEMORY.md
Paul O'Reilly e5dbe95acb Add /ask-minimax-with-context skill
Walks CONTEXT.md and CLAUDE.md files from a given folder up to the git
root, assembles them into a context bundle via shell redirects (file
contents never enter the calling session), then delegates a one-line
question to MiniMax M2.7. Token cost to the main session: paths only.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-11 21:43:29 +12:00

2.3 KiB

Custom Claude Skills — Memory

Skill Development Learnings

  • Skills in ~/.claude/skills/ are available across all projects (personal scope)
  • !command`` injection runs at skill load time — great for pre-fetching git logs, file contents, etc.
  • Inline skills (no context: fork) retain full conversation history — essential for reflection-type skills
  • allowed-tools reduces permission prompts by declaring what the skill needs upfront
  • Bang-command exit codes matter: !command`` fails the skill if the command exits non-zero, even if the output is valid. Scripts that use exit 1 as "issues found" (not error) need || true appended in the skill invocation.
  • Every binary in bang-commands needs allowed-tools coverage: ls, head, cat, hostname — each needs its own Bash(<binary> *) pattern or the skill fails to load
  • Broad Bash(git *) is acceptable when justified: orchestrate skill needs worktree/branch/merge/checkout — listing 6+ specific subcommands is worse than the broad pattern with a validator warning
  • Skills that launch containers need careful entrypoint handling: Use --entrypoint uid-wrapper.sh when running claude --print in agent containers — the default entrypoint expects AGENT_PAYLOAD

Topic Files

  • Process Lessons — Container agent workflow patterns, skill development rules
  • Decisions — Task orchestration architecture decisions, harness design rationale
  • skill-ask-minimax-with-context — Walk CONTEXT.md+CLAUDE.md up to git root, bundle via shell redirects, delegate question to MiniMax

Task Orchestration Skills (2026-03-24)

Added /decompose and /orchestrate for parallel container agent work:

  • /decompose breaks tasks into subtasks with dependency graph → .agent-tasks.json
  • /orchestrate dispatches container agents in git worktrees, checks status, updates state
  • Designed for /loop 2m /orchestrate auto-polling pattern
  • Git worktrees provide isolation: each agent gets its own branch, no file conflicts
  • No hardcoded concurrency limit — user approves max_concurrent during decompose
  • Memory files created in claude-foundations/memory/skill-decompose.md and skill-orchestrate.md