implement-task — Claude Code skill: step-by-step builds with review
Runs a task step by step, one agent per step, then one reviewer per phase and fixes until it passes.
npx skills add NeoLabHQ/context-engineering-kit --skill implement-task -a claude-codeWhat implement-task does
The skill reads a task file and works through its steps, each defined in .specs/sub-tasks/<task-name>/<NN>-<step-slug>.md. Every step gets its own implementation agent. Once a phase's steps are finished, a single sdd:code-reviewer checks that phase; problems get fixed before the next phase opens.
One quality threshold covers every phase: --target-quality, 4.0 out of 5.0 unless you change it. Fix-and-re-review loops stop at --max-iterations, 3 by default. Add --skip-reviews to drop the gates. With --strict, a phase counts as passed only when it reaches the threshold, no early exit.
Resuming and re-checking are built in. --continue picks up the unfinished phase and completes its remaining steps. --refine compares project changes via git and starts verification from the phase owning the earliest touched step. --human-in-the-loop pauses after the phases you name, and --model overrides the model for all sub-agents.
The threshold lives only in the flag. Planning agents are not allowed to write one into the task file, so a task carrying its own bar will be ignored. No task file split into phases and steps means nothing runs.
What it helps with
- build a task step by step without steering agents by hand
- clear reviewer findings until a phase passes
- resume from the last finished step
- re-verify only the steps git changes touched
- pause for a manual check after chosen phases
Example prompts for the agent
- Implement the task in
add-validation.feature.mdstep by step - Resume from the last completed step with
--continue - Re-check my git changes:
--refine --target-quality 4.5
How to install implement-task
1Skills CLI (Vercel)
npx skills add NeoLabHQ/context-engineering-kit --skill implement-task -a claude-code2Manually: put the files in place
~/.claude/skills/implement-task/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/implement-task/
1Skills CLI (Vercel)
npx skills add NeoLabHQ/context-engineering-kit --skill implement-task -a codex2Manually: put the files in place
.agents/skills/implement-task/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add NeoLabHQ/context-engineering-kit --skill implement-task -a cursor2Manually: put the files in place
.cursor/skills/implement-task/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install NeoLabHQ/context-engineering-kit implement-task2Manually: put the files in place
.github/skills/implement-task/SKILL.md1Skills CLI (Vercel)
npx skills add NeoLabHQ/context-engineering-kit --skill implement-task -a gemini-cli2Platform CLI
gemini skills install https://github.com/NeoLabHQ/context-engineering-kit --path skills/implement-taskManually: put the files in place
.devin/skills/implement-task/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add NeoLabHQ/context-engineering-kit --skill implement-task -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about implement-task
How do I install implement-task in Claude Code?
Run npx skills add NeoLabHQ/context-engineering-kit --skill implement-task -a claude-code. The skill lands in ~/.claude/skills/implement-task/SKILL.md.
What does implement-task do?
It implements a task step by step from sub-task files and runs the sdd:code-reviewer agent after each phase. Issues are fixed until the phase passes or iterations run out.
What does it need to run?
A task file with a phase overview and parallelization overview, plus step files under .specs/sub-tasks/<task-name>/.
