framework/core/skills/epic/SKILL.md
Use when the user asks to plan a LARGE feature that spans multiple sessions or phases — produces an epic under the `tasks` role from AGENTS.md with dependency-ordered phases, atomic tasks, and per-phase status tracking. Use plan for single-session tasks. Do NOT trigger on generic planning, roadmap, or brainstorming requests.
npx skillsauth add korchasa/flowai epicInstall 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.
Create a structured, decomposed epic under the tasks role resolved from AGENTS.md for features too large for a single agent session. The template default uses today's date as a directory hierarchy; the file slug begins with epic- (no date prefix in the slug).
epic when feature spans >3 files AND requires >2 sessions, OR has >5 phasesplan for tasks completable within one agent sessionplan; if it outgrows a single task, upgrade to epicFor clarifying / uncertainty-resolution questions asked during research (Step 2):
1., 2., …) — not a heading, bold-only line, or paragraph.agent's choice (or equivalent), pick the subset yourself, emit a one-line justification of the pick, and proceed without re-asking for confirmation.Phase approval (Step 4) and critique-points selection (Step 7) are exempt — phase decomposition is a multi-section content presentation (the same prior that drives variant analysis), and critique triage is auto-classified by the agent without asking the user.
<step_by_step>
Initialize
todo_write, todowrite) to create a plan based on these steps.YYYY-MM-DD format (e.g. via date +%Y-%m-%d). Hold it as <DATE>. Derive <YYYY>, <MM>, <DD> (zero-padded). Resolve tasks from AGENTS.md and derive the eventual epic path from that role's layout.Deep Context & Research
SRS and SDS from AGENTS.md. If you don't know their current content — read the resolved files now.Proactive Resolution from AGENTS.md: analyze prompt, codebase, search for gaps.glob, grep, ripgrep, search, webfetch) for unknowns.Draft Spec Header
mkdir -p).date, status: to do, tags, related_tasks, optional implements.Decompose into Phases (Chat Only)
Detail Phases
Critique
Refine & Finalize
status: is auto-derived from DoD; do not change it manually.)7a. Write SRS-inline **Tasks:** Back-Pointer (FR-DOC-TASK-LINK) — execute immediately, no permission needed. This is a write step.
implements: frontmatter, locate the heading ### <FR-ID>: in the resolved SRS.**Description:** bullet. Look at the line(s) immediately following it.
- **Tasks:** [...] bullet already exists: append , [epic-<name>](tasks/<YYYY>/<MM>/epic-<name>.md) to the comma-separated list. Idempotent: skip if the exact link is already present.**Tasks:** bullet exists yet: insert a new line - **Tasks:** [epic-<name>](tasks/<YYYY>/<MM>/epic-<name>.md) immediately AFTER the **Description:** bullet.</step_by_step>
---
date: YYYY-MM-DD
status: to do
implements:
- FR-XXX
tags: []
related_tasks: []
---
# Epic: {Feature Name}
| Field | Value |
|---------|-----------------------------|
| Status | Draft/Ready/In-Progress/Done |
| Created | YYYY-MM-DD |
| Updated | YYYY-MM-DD |
## Goal
{Why are we building this? Business/user value.}
## Overview
{Current state, why now, relevant context.}
## Non-Goals
<!-- Examples: "No backward compatibility with v1 API", "No UI changes in this phase", "No performance optimization", "No migration of existing data" -->
- {Explicit exclusion 1}
- {Explicit exclusion 2}
## Architecture & Boundaries
### Always (agent autonomy)
- {Things agent can always do}
### Ask First
- {Things requiring user confirmation}
### Never
- {Things agent must never do}
## Definition of Done
- [ ] {Measurable criterion 1}
- [ ] {Measurable criterion 2}
---
## Phase 1: {Name}
**Status:** not-started | **Prerequisites:** none
### Goal
{What this phase achieves.}
### Scope
- {file/component 1}
- {file/component 2}
### Tasks
1. {Atomic, testable task}
2. {Atomic, testable task}
### Verification
- [ ] {Specific check or command}
### Notes
- {Implementation hints, gotchas}
---
## Phase 2: {Name}
...
development
Use when the user asks to add TypeScript strict-mode code-style rules to AGENTS.md for a TypeScript project using strict mode. Do NOT trigger for Deno projects (use setup-agent-code-style-deno) or non-strict TS configurations.
development
Use when the user asks to add Deno/TypeScript code-style rules to AGENTS.md, or during initial Deno project setup when code-style guidelines need to be established. Do NOT trigger for non-Deno TypeScript projects (use setup-agent-code-style-strict), or for runtime-agnostic style advice.
testing
Use when the user provides a source (URL, file path, or free text) to save into the project's memex — a long-term knowledge bank for AI agents. Stores the raw source, extracts entities into cross-linked pages, runs a backlink audit, and updates the index and activity log. Do NOT trigger on casual reads; only when the intent is to persist a source into the memex.
development
Use when the user asks to audit a memex (long-term knowledge bank for AI agents) for orphans, dead SALP REFs, missing sections, contradictions, or index drift. Runs a deterministic structural check, layers LLM-judgement findings, optionally auto-fixes trivial issues with `--fix`. Do NOT trigger on general code linting.