菜单
Research-driven positioning exercise — competitive research, guided framework application, and positioning document generation
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
Backlog-scale orchestration on top of /workflow — drives PM items through refine → plan → implement → review → local-merge via role-specialized sub-agents dispatched in parallel waves, each item isolated in its own git worktree. Bare /swarm summarizes state; /swarm <goal> runs the orchestrator; /swarm:setup sets up the charter and .agent-tools/ umbrella; /swarm:continue resumes a paused run.
Capture durable knowledge from any engineering work — debugging solutions, refactors, features, design decisions, reusable patterns — and maintain memory quality so each unit of work compounds the next
Principal workflow entry — resolve portfolio mode (swarm resume/handoff or unit state machine), drive work without inventing path; hard-stop when path is not established
Initialize and maintain planning root (.agent-tools/planning preferred), conventions (tracks, gates, integration), runs ledger scaffold, and shared memory under .agent-tools/memory/ (AGENTS.md memory-link) for the workflow family.
Parent skill for the workflow family — principal session entry is /workflow:continue (also bare /workflow). Horizon mapping, brainstorm, refine, plan, execute, review, audit, compound. Vertical-slice and deliverable-partition modes.
Detect gaps in the canonical skill corpus, propose targeted improvements, validate changes, and present for review. Inventories src/** skill trees; optional run-ledger seeds for process IP gaps.
| name | product:position |
| description | Research-driven positioning exercise — competitive research, guided framework application, and positioning document generation |
| argument-hint | ['.', directory path, or 'continue'] |
| user-invocable | true |
References: @product
Research-driven positioning exercise producing ./planning/positioning.md (April Dunford framework + competitive research). Not a template fill-in — research first, then guided decisions.
$ARGUMENTS
| Input Pattern | Scope | Action |
|---|---|---|
. or empty | Current project | Full positioning from scratch |
| Directory path | Target project | Position that project |
continue | Resume | Continue from ./planning/positioning.md |
--from-audit | Post-audit | Start from recent /product:audit report |
Read README hero, landing page, package metadata, existing ./planning/ positioning, docs intro.
Extract current claims: what / who / problem.
Spawn 3 parallel research agents:
Return structured profiles with citations.
Present findings using templates/discovery-summary.md (load and fill).
For each Dunford step: present research evidence; user decides.
Write ./planning/positioning.md using templates/positioning-doc.md (load and fill from decisions + research sources + last_research date).
/product:audit — assess gaps then re-audit after positioning/product:brief — content generation from positioning doc/workflow:plan — feature gaps from claims vs codebase/workflow:compound — capture competitive research findings