work-pipeline
The work-pipeline skill activates a structured development workflow when user messages begin with square bracket tags like [new-feature] or [bugfix]. It orchestrates a multi-agent pipeline that analyzes requirements, creates planning documents, and executes work through specifier, planner, scheduler, builder, verifier, and committer agents, with built-in approval gates unless the user specifies "auto" mode for uninterrupted execution.
git clone --depth 1 https://github.com/davepoon/buildwithclaude /tmp/work-pipeline && cp -r /tmp/work-pipeline/plugins/agents-uc-taskmanager/skills/work-pipeline ~/.claude/skills/work-pipelineSKILL.md
# WORK-PIPELINE Trigger
When the user's message starts with a `[]` tag, start the WORK-PIPELINE by reading `../skills/sdd-pipeline/references/agent-flow.md` and following the orchestration flow.
## Trigger Detection
Any message starting with `[...]` triggers this pipeline:
- `[new-feature]`, `[enhancement]`, `[bugfix]`, `[new-work]`, `[WORK start]`
- Or any custom tag in square brackets
## References Directory (CRITICAL)
When this skill is triggered, Claude Code provides the "Base directory for this skill" as an absolute path.
Derive the **REFERENCES_DIR** from it:
```
REFERENCES_DIR = {Base directory}/../sdd-pipeline/references
```
You MUST pass this absolute path to **every sub-agent invocation** (specifier, planner, scheduler, builder, verifier, committer).
Include it at the top of the prompt text:
```
REFERENCES_DIR={absolute_path}
```
Sub-agents need this path to read their reference files. Without it, they cannot find the files and will loop.
## Pipeline Flow
1. **Call specifier agent** — analyzes the requirement, creates `works/WORK-NN/Requirement.md`, determines execution-mode (direct/pipeline/full)
2. **⛔ STOP — Present the specifier's output summary to the user and WAIT for explicit approval.** Do NOT call the next agent until the user approves. Show what was created (Requirement.md, PLAN.md if direct mode, TASK files) and ask "Proceed?"
3. **Follow the execution-mode** returned by specifier:
- `direct`: call builder → committer
- `pipeline`: call builder → verifier → committer in sequence
- `full`: call planner → **⛔ STOP for 2nd approval** → scheduler → [builder → verifier → committer] × N
## Auto Mode
If the user's message ends with "auto" or "자동으로", skip ALL approval steps and execute the entire pipeline automatically. This is the ONLY case where approval gates can be skipped.
## Arguments
User requirement: $ARGUMENTSAutomate ActiveCampaign tasks via Rube MCP (Composio): manage contacts, tags, list subscriptions, automation enrollment, and tasks. Always search tools first for current schemas.
Analytics your AI agent can actually use. Track, analyze, run A/B experiments, and optimize across all your projects via CLI. Includes a growth playbook so your agent knows HOW to grow, not just what to track.
Automate Airtable tasks via Rube MCP (Composio): records, bases, tables, fields, views. Always search tools first for current schemas.
Automate Amplitude tasks via Rube MCP (Composio): events, user activity, cohorts, user identification. Always search tools first for current schemas.
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
Automate Asana tasks via Rube MCP (Composio): tasks, projects, sections, teams, workspaces. Always search tools first for current schemas.
Sonnet Amplified fullstack engine. 34 modes, SEC-01~15 OWASP security, 13 runtime hooks, 75% token reduction. Install: npx @smorky85/aurakit
Automate BambooHR tasks via Rube MCP (Composio): employees, time-off, benefits, dependents, employee updates. Always search tools first for current schemas.