From ham-autocode
Detect current project state. Scans files, git, docs to determine which phases are complete. Prevents re-executing completed work. Use when: "detect state", "project status", "where are we".
How this skill is triggered — by the user, by Claude, or both
Slash command
/ham-autocode:detectThis 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"
Scan systematically, report factually, recommend next action.
ls project root, check: CLAUDE.md, PROJECT.md, docs/, .planning/, src/, tests/git log --oneline -20, git status| Phase | Look for |
|---|---|
| 1 Initiation | design docs, product definition, competitive analysis |
| 2 Requirements | PROJECT.md, WBS, .planning/, milestone plans |
| 3 Planning | PLAN.md per phase, architecture docs, task breakdowns |
| 4 Execution | Source code, feat/fix commits, test code |
| 5 Review | Code review records, QA results, VERIFICATION.md |
| 6 Release | PRs, CHANGELOG, git tags, deploy records |
## Project State: [name]
### Overall: Phase [X] ([percentage]%)
| Phase | Status | Evidence |
|-------|--------|----------|
| 1-6 | Done/Partial/Not Started | key files |
### Recommended Next Steps:
1. [action + skill command]
ham-cli dag init <plan-file> # parse tasks
ham-cli route batch # route all
ham-cli dag status # check progress
docs/06-WBS.md = GSD ROADMAP)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.