From ham-autocode
Full autonomous development pipeline. 6 phases: initiation, requirements, planning, execution, review, ship. Auto-detects state, skips completed phases. Use when: "auto develop", "full pipeline", "build this project".
How this skill is triggered — by the user, by Claude, or both
Slash command
/ham-autocode:autoThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
> `ham-cli` = `HAM_PROJECT_DIR="$PWD" node "${CLAUDE_PLUGIN_ROOT:-$PWD}/dist/index.js"`
ham-cli=HAM_PROJECT_DIR="$PWD" node "${CLAUDE_PLUGIN_ROOT:-$PWD}/dist/index.js"
Framework: gstack thinks, GSD stabilizes, Superpowers executes.
ham-cli pipeline init "[name]" # start
ham-cli pipeline log "[action]" # before/after every step
ham-cli dag status # progress
ham-cli dag next-wave # next tasks
ham-cli route batch # route all
ham-cli validate <task-id> # run gates
/ham-autocode:detect, continue from last verified phase/ham-autocode:detectSkip if product definition exists. Run /office-hours then /plan-ceo-review.
Skip if PROJECT.md + WBS exist. Run /gsd:new-project then /gsd:new-milestone.
Skip if PLAN.md exists per phase. For each phase:
/gsd:discuss-phase --auto then /gsd:plan-phase then /plan-eng-review.
Solo: /gsd:autonomous. Larger: Agent Teams with file ownership.
Route: complex → Claude Code, clear spec → Codex, simple → OpenCode.
/gsd:verify-work → /review → /qa. Fix CRITICAL/HIGH before proceeding.
Only after user confirms Phase 5. /ship → /document-release.
npx claudepluginhub hammercui/ham-autocodeProvides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.