菜单
List available workflows, show current workflow details, and switch workflows mid-session. Use when checking available workflow types (TDD, trivial, agent-docs), viewing current workflow phase, switching to a different workflow pattern, or managing BikeLane stepped workflows.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | workflow |
| description | List available workflows, show current workflow details, and switch workflows mid-session. Use when checking available workflow types (TDD, trivial, agent-docs), viewing current workflow phase, switching to a different workflow pattern, or managing BikeLane stepped workflows. |
| args | [list|show [name]|set <name>|start <name> [--mode <mode>]|resume [name]|status|check|fix-phase] |
Pennyfarthing uses YAML-defined workflows to control agent sequences. The default TDD workflow (SM > TEA > Dev > Reviewer) can be customized or replaced.
| Command | CLI | Purpose |
|---|---|---|
/pf-workflow or /pf-workflow list | pf workflow list | List all workflows |
/pf-workflow show [name] | pf workflow show [name] | Show workflow details |
/pf-workflow set <name> | Edit session file **Workflow:** line | Switch workflow mid-session |
/pf-workflow start <name> | pf workflow start <name> [--mode M] | Start stepped workflow |
/pf-workflow resume [name] | pf workflow resume [name] | Resume interrupted workflow |
/pf-workflow status | pf workflow status | Show stepped workflow progress |
/pf-workflow fix-phase <id> <phase> | pf workflow fix-phase <id> <phase> [--dry-run] | Repair session phase |
| Check workflow state | pf workflow check [--json] | Current story, phase, state |
| Check phase owner | pf workflow phase-check <workflow> <phase> | Which agent owns a phase |
| Get workflow type | pf workflow type <workflow> | phased/stepped/procedural |
| Emit handoff marker | pf workflow handoff <next-agent> | Handoff marker for BikeRack GUI |
| Complete step | pf workflow complete-step [name] [--step N] | Advance stepped workflow |
| Workflow | Flow | Triggers |
|---|---|---|
tdd (default) | SM > TEA > Dev > Reviewer > SM | features, 3+ points |
tdd-tandem | SM > TEA(+Arch) > Dev(+TEA) > Rev(+PM) > SM | tandem tag, 3+ points |
trivial | SM > Dev > Reviewer > SM | chores/fixes, 1-2 points |
bdd | SM > UX > TEA > Dev > Reviewer > SM | UI/UX features |
bdd-tandem | SM > UX(+Arch) > TEA > Dev(+UX) > Rev(+PM) > SM | bdd-tandem tag |
agent-docs | SM > Orchestrator > Tech Writer > SM | docs, agent-file label |
architecture | 7 stepped phases with gates | architecture/design/ADR |
Detailed options and behavior: usage.md Practical examples: examples.md
Interactive playtest — full-stack (UI + Playwright + UX Designer) or headless (API-only + Python driver). Coordinates cross-workspace bug reporting via ping-pong file with FIXER.
LLM cost and cache forensics — reconcile server-log narrator costs against the Anthropic Admin API, attribute per-model spend, detect dead caching and invisible callers. Use when analyzing API costs, auditing cache efficiency, or when the Console bill doesn't match expectations.
Create epic or story context documents. Reads sprint YAML for epic/story data, reads context-schema.yaml for required sections, populates templates, and writes output to sprint/context/. Epic context is a single-agent operation (no tandem). Story context uses PM + tandem partner for domain-specific observations.
Jira CLI commands for sprint management. Use when viewing, assigning, or updating Jira issues from the command line.
Sprint status, backlog, and story management for Pennyfarthing. Use when checking current sprint status, finding available stories, reviewing backlog, or understanding story context and history. IMPORTANT: Always use `pf sprint` CLI commands - never manually edit sprint YAML.
Create epic or story context documents. Reads sprint YAML for epic/story data, reads context-schema.yaml for required sections, populates templates, and writes output to sprint/context/. Epic context is a single-agent operation (no tandem). Story context uses PM + tandem partner for domain-specific observations.
