skills/build/SKILL.md
Implement one phase of a plan. Reads plan, finds next incomplete phase, implements it, runs feedback loops, marks checkboxes, offers commit. One phase per invocation. Use when the user wants to implement, code, build, or work on the next phase of a plan.
npx skillsauth add helderberto/skills buildInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Implement the next incomplete phase of a plan — one phase per invocation.
Context window: recommend /clear before starting to maximize token budget.
Interactive prompts: present options as a numbered list and wait for the user's choice.
The argument (if provided) is: $ARGUMENTS
Use argument as <slug>. If empty, list plans as numbered options and wait for the user's choice.
Accepts slug or @file reference:
/hb:build dark-mode-support
/hb:build @.specs/plans/dark-mode-support.md
If argument starts with @, treat it as a file path — read that file directly as the plan.
Read .specs/plans/<slug>.md. If missing, list plans as numbered options and wait for the user's choice.
Scan the plan for ## Phase N headings. For each phase, count - [ ] and - [x] checkboxes.
The next incomplete phase is the first phase that has at least one unchecked - [ ] item.
If all phases are complete (zero unchecked items across all phases):
All phases complete. Run
/hb:check <slug>to verify.
Stop here.
Show the phase title and its unchecked items:
Phase N — <title> (M remaining)
- [ ] First unchecked item
- [ ] Second unchecked item
If on the default branch (main/master), ask:
Create branch
feat/<slug>?
- Yes, create branch (Recommended)
- No, stay on current branch
If accepted, create and switch to the branch.
If already on a feature branch, skip this step.
Work through each unchecked item in order. For each item:
Do not impose coding rules, style, or conventions. Follow what the project already uses.
Do not implement items from other phases. Stay within the current phase boundary.
After implementing the phase, detect and run available project scripts. Check package.json for these scripts (run only what exists):
| Script pattern | Purpose |
| ---------------------------------- | ------------- |
| typecheck, tsc, type-check | Type checking |
| test, vitest, jest | Tests |
| lint, eslint | Linting |
| format:check, prettier --check | Formatting |
Run each detected script. If any fails:
If a script still fails after 3 attempts, treat it as a blocker — pause and ask the user for help:
Blocker:
<script>fails after 3 attempts. Last error:<error summary>How to proceed?
- I'll fix it — pause and wait
- Skip this check and continue
- Abort this phase
Wait for the user's response before continuing.
After all feedback loops pass, for each completed item change - [ ] → - [x] in .specs/plans/<slug>.md.
Present the changes and ask:
Phase N complete — all checks pass. Commit?
- Yes, commit
- No, I'll review first
If the user chooses to commit:
.specs/ artifacts unless the project dogfoods TracerKit)/hb:build <slug> for Phase N+1, or /hb:check <slug> to verify."If the user chooses to review:
Ready for review. Run
/hb:build <slug>again when ready to continue.
If implementation requires something the agent cannot provide (API key, external service, manual setup, design decision):
Blocker: <description of what's needed>
How to proceed?
- I've resolved it — continue
- Skip this item for now
- Abort this phase
Wait for the user's response. Never guess or work around a blocker silently.
[x]tools
Teach the user a new skill or concept, within this workspace.
documentation
Compact the current conversation into a handoff document for another agent to pick up.
testing
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
development
Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill, or asks "make a skill for X".