xiduzo/wtf / skills/wtf.epic-to-features
wtf.epic-to-features
VerifiedThis skill should be used when a user wants to decompose an Epic into its complete set of Features all at once, invoked automatically after write-epic completes, or triggered by phrases like "create all features for this epic", "walk me through all the features", "let's break down this epic", or "plan the features for epic
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 10.1 KB |
| evals/evals.json | config | 3.8 KB |
| evals/fixtures/existing-features-epic.json | config | 1.7 KB |
| evals/fixtures/multi-actor-epic.json | config | 1.5 KB |
| evals/fixtures/ordered-capabilities-epic.json | config | 1.5 KB |
evals/evals.json
View on GitHub{
"skill_name": "wtf.epic-to-features",
"evals": [
{
"id": 1,
"prompt": "Run wtf.epic-to-features in test mode. Skip steps 0, 0b, and 1 (gh setup already confirmed, planning mode `guided` and feature scope `single-story` already resolved, Epic already fetched). Use the Epic from `evals/fixtures/multi-actor-epic.json`, field `epic`. The `existing_features` array is empty — no Features have been created yet. Run step 2 only: propose the full Feature list. Output the proposed list.",
"expected_output": "A proposed Feature list covering both the Merchant and Finance Manager actors, with at least one Feature per actor, all following the [Actor] can [verb] [object] pattern and using no implementation vocabulary.",
"files": ["evals/fixtures/multi-actor-epic.json"],
"expectations": [
"At least one proposed Feature names Merchant as the actor (e.g. 'Merchant can view settlement status')",
"At least one proposed Feature names Finance Manager as the actor (e.g. 'Finance Manager can export settlement report')",
"Every proposed Feature follows the [Actor] can [domain verb] [domain object] pattern",
"No proposed Feature contains implementation vocabulary such as 'API', 'database', 'endpoint', or 'table'"
]
},
{
"id": 2,
"prompt": "Run wtf.epic-to-features in test mode. Skip steps 0, 0b, and 1 (gh setup already confirmed, planning mode `guided` and feature scope `single-story` already resolved, Epic already fetched). Use the Epic from `evals/fixtures/existing-features-epic.json`, field `epic`. The `existing_features` field lists Features already created under this Epic — do not re-propose them. Run step 2 only: propose the remaining Features. Output the proposed list.",
"expected_output": "The output explicitly acknowledges the two Features already created (Feature #10 and Feature #11) before listing only the remaining Features. The remaining proposals cover Finance Manager capabilities and the notification capability, totalling at least 2 new Features.",
"files": ["evals/fixtures/existing-features-epic.json"],
"expectations": [
"The output explicitly lists or references Feature #10 ('Merchant can view settlement status') as already existing before presenting the remaining proposals",
"The proposed list does not include 'Merchant can view settlement status' as a new proposal",
"The proposed list does not include 'Merchant can filter settlements by date range' as a new proposal",
"The proposed list includes at least 2 new Features not yet created (covering Finance Manager or notification capabilities)"
]
},
{
"id": 3,
"prompt": "Run wtf.epic-to-features in test mode. Skip steps 0, 0b, and 1 (gh setup already confirmed, planning mode `guided` and feature scope `single-story` already resolved, Epic already fetched). Use the Epic from `evals/fixtures/ordered-capabilities-epic.json`, field `epic`. No existing Features. Run step 2 only: propose the full Feature list. Output the proposed list.",
"expected_output": "A proposed Feature list of 5 Features corresponding to the 5 Success Metrics, ordered so that view precedes filter and filter precedes export for the Merchant actor.",
"files": ["evals/fixtures/ordered-capabilities-epic.json"],
"expectations": [
"The proposed list includes exactly 5 Features, one per Success Metric",
"The Feature corresponding to 'Merchant can view settlement list' appears before the Feature for 'Merchant can filter settlements' in the proposed order",
"The Feature corresponding to 'Merchant can filter settlements' appears before the Feature for 'Merchant can export settlements' in the proposed order",
"All 5 proposed Features follow the [Actor] can [verb] [object] pattern"
]
}
]
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |