

Also from Kynth Studios


Also from Kynth Studios


Also from Kynth Studios
123456# story: e45s2978# Slice Tasks910> **Spine position:** Step 2 — scope-work → slice-tasks → plan-work.1112Produce **epic capsule story tasks** in `specs/epics/eNN-slug/` — vertical slices, each independently deliverable and testable. Output: decoupled `eNNsYY-tasks.yaml` files with runnable verify commands. Legacy `specs/epics/ (see slice-tasks)` is deprecated; use capsule dirs + `execution-status.yaml`.1314## Pre-flight1516- [ ] Does `specs/product/SCOPE_LATEST.yaml` exist? If not, run `scope-work` first — you can't slice what you haven't bounded.17- [ ] Is the `release-plan.yaml` populated with the epics you're slicing? Epic IDs (e01, e02…) should exist before you create stories.18- [ ] Do you understand the difference between a horizontal layer and a vertical slice? (See anti-patterns below.)1920## Process21220. **Read planning-context.yaml** — If `specs/planning-context.yaml` exists, read it first:23```bash24 test -f specs/planning-context.yaml && echo "Context found" || echo "No context — starting fresh"25```26 Use `feature_name`, `constraints`, and `out_of_scope` to inform slice boundaries. `key_decisions` in the file may constrain how stories are cut (e.g., "no external deps" constrains slice 2). If absent, proceed normally.27281. **Read context** — Read `specs/product/SCOPE_LATEST.yaml` and/or `specs/release-plan.yaml`. Understand what the epic delivers end-to-end.29302. **Cut tracer-bullet slices** — Identify the thinnest possible vertical path through the stack that delivers user value. Start with this slice; it will catch integration issues first. For example:31 - A search feature: first slice is "user types query → API returns results" (no filters, no pagination, no ranking — just the plumbing working end-to-end).32 - A checkout flow: first slice is "user clicks buy → order created" (no payment, no inventory, no email).33343. **Assign BCPs** — For each story, estimate Business Complexity Points (1–13). A 1-BCP story is a trivial change (one file, one concept). A 13-BCP story is a major feature across multiple modules. If a story exceeds 8 BCPs, consider splitting it.35364. **Each story** writes:37 - `eNNsYY-tasks.yaml` with `story_id`, `title`, `status`, `bcps`, `tasks[]` (each with `id`, `description`, `verify`, `status`)38 - Story spec `.md` files are written by `plan-work` and follow countable-story-format.md39 - The epic capsule manifest (`epic.yaml`) is updated to list the story ID and BCPs40 - **Requirement deltas (e45s29):** Stories that alter existing behavior MUST carry `delta:` in `epic.yaml` (`ADDED` | `MODIFIED` | `REMOVED` | `RENAMED`). `plan-work` expands deltas into full before/after requirement text.41425. **Order by WSJF** in `release-plan.yaml` epic list — highest WSJF first. Weight-shortest-job-first ensures the highest value arrives earliest.43446. **Validate slices** — Every slice must answer: "If this story ships, does a user get new value?" If the answer is "no, they need a later story too", the slice is too horizontal — cut vertically deeper.4546> **HARD GATE** — No horizontal-only slices ("add all models") without a vertical path that proves integration. Every story must be independently demonstrable, even if it only handles the happy path.4748> **HARD GATE** — Each task's `verify:` field must contain a runnable command (not "manually check" or "review visually"). If verification requires manual steps, prefix with `verify-script:` and write the steps in the story file.4950## Anti-Patterns5152- **Layer cakes** — "Week 1: all models. Week 2: all controllers. Week 3: all views." This hides integration risk until the end. Every story must cut through all layers.53- **Too-small slices** — If a slice takes < 30 minutes to implement, it's probably noise. Combine with adjacent slices.54- **Too-large slices** — If a slice takes > 3 days, it's an epic, not a story. Split further.5556## Output5758- `specs/epics/eNN-slug/eNNsYY-tasks.yaml` — per-story task breakdown with verify commands59- `specs/epics/eNN-slug/epic.yaml` — updated with story list and BCPs60- `specs/release-plan.yaml` — updated WSJF ordering (if needed)6162## Verify6364→ verify: `[ "$(find specs/epics -name '*-tasks.yaml' 2>/dev/null | wc -l | tr -d ' ')" -gt 0 ]`656667<!-- story: e03s01 -->68
One repository carrying more than one format is the comparison this product exists for: does anyone actually write different content in each file, or is one a copy of the other?
| Repository | Format | Stack | Covers | Score | Changed |
|---|---|---|---|---|---|
| danielvm-git/bigpowers.cursor/rules/simple-english.mdc · 134 | Cursor rules | styletypesgitdatabase+6 | 47/100 | 14 days ago | |
| danielvm-git/bigpowers.cursor/rules/build-epic.mdc · 134 | Cursor rules | buildgit | 58/100 | 14 days ago | |
| danielvm-git/bigpowers.cursor/rules/extract-design.mdc · 134 | Cursor rules | lint-formatstyledependenciesui | 82/100 | 14 days ago | |
| danielvm-git/bigpowers.cursor/rules/plan-tests.mdc · 134 | Cursor rules | teststyletesting-strategyagent-behaviour | 66/100 | 14 days ago | |
| danielvm-git/bigpowers.cursor/rules/plan-release.mdc · 134 | Cursor rules | testlint-formatarchdeployment | 74/100 | 14 days ago | |
| danielvm-git/bigpowers.cursor/rules/request-review.mdc · 134 | Cursor rules | git | 62/100 | 14 days ago | |
| danielvm-git/bigpowers.cursor/rules/research-first.mdc · 134 | Cursor rules | buildarchdependencies | 70/100 | 14 days ago | |
| danielvm-git/bigpowers.cursor/rules/run-benchmark.mdc · 134 | Cursor rules | styleperformance | 58/100 | 14 days ago | |
| danielvm-git/bigpowers.cursor/rules/reset-baseline.mdc · 134 | Cursor rules | no sections | 40/100 | 14 days ago | |
| danielvm-git/bigpowers.windsurf/rules/define-language.md · 134 | Windsurf rules | lint-formatdo-not | 65/100 | 14 days ago | |
| danielvm-git/bigpowers.windsurf/rules/context7-mcp.md · 134 | Windsurf rules | style | 54/100 | 14 days ago | |
| danielvm-git/bigpowers.windsurf/rules/delegate-task.md · 134 | Windsurf rules | git | 62/100 | 14 days ago | |
| danielvm-git/bigpowers.windsurf/rules/extract-design.md · 134 | Windsurf rules | lint-formatstyledependenciesui | 82/100 | 14 days ago | |
| danielvm-git/bigpowers.windsurf/rules/security-review.md · 134 | Windsurf rules | lint-formattesting-strategygitsecurity+2 | 60/100 | 14 days ago | |
| danielvm-git/bigpowers.windsurf/rules/verify-work.md · 134 | Windsurf rules | buildtestlint-formatagent-behaviour | 74/100 | 14 days ago | |
| danielvm-git/bigpowers.windsurf/rules/wire-ci.md · 134 | Windsurf rules | buildtestlint-formatstyle+1 | 81/100 | 14 days ago | |
| danielvm-git/bigpowerswebsite/AGENTS.md · 134 | AGENTS.md | docs | 31/100 | 14 days ago | |
| danielvm-git/bigpowers.windsurf/rules/terse-mode.md · 134 | Windsurf rules | styledo-not | 56/100 | 14 days ago | |
| danielvm-git/bigpowers.windsurf/rules/trace-requirement.md · 134 | Windsurf rules | buildtesting-strategy | 54/100 | 14 days ago | |
| danielvm-git/bigpowers.cursor/rules/align-grid.mdc · 134 | Cursor rules | lint-formatdo-notagent-behaviour | 65/100 | 14 days ago |
Same format, overlapping stack, ranked by quality.
| Repository | Format | Stack | Covers | Score | Changed |
|---|---|---|---|---|---|
| TechSquidTV/Hermes.cursor/rules/10-hermes-api.mdc · 45 | Cursor rules | testlint-formatstylearch+5 | 100/100 | 14 days ago | |
| hiromaily/go-crypto-wallet.cursor/rules/typescript.mdc · 126 | Cursor rules | setupbuildtestlint-format+6 | 100/100 | 14 days ago | |
| deifos/clipmira-subtitles.cursor/rules/frontend.mdc · 1 | Cursor rules | setuptestlint-formatstyle+7 | 99/100 | 14 days ago | |
| markstev/mark-starter.cursor/rules/frontend.mdc · 0 | Cursor rules | setuptestlint-formatstyle+6 | 99/100 | 14 days ago | |
| Allymahmoud/case-intake-platform.cursor/rules/frontend.mdc · 0 | Cursor rules | setuptestlint-formatstyle+7 | 99/100 | 14 days ago | |
| dodgecfr/combatfilms-webapp.cursor/rules/frontend.mdc · 0 | Cursor rules | setuptestlint-formatstyle+7 | 99/100 | 14 days ago | |
| langflow-ai/langflow.cursor/rules/docs_development.mdc · 153k | Cursor rules | setupbuildtestlint-format+7 | 97/100 | 14 days ago | |
| TechSquidTV/Hermes.cursor/rules/20-hermes-api-tests.mdc · 45 | Cursor rules | teststyletesting-strategysecurity+3 | 97/100 | 14 days ago |
A badge carrying the measured quality of the strongest agent config file in this repository, out of 100. It reads from this index every time somebody loads your page, so it changes when the measurement changes and there is nothing to keep up to date. Free, no account, and the value is not something you or we can set by hand.
[](https://rulestack.kynth.studio/configs/danielvm-git-bigpowers-cursor-rules-slice-tasks)Would rather not hotlink us? Every badge is also served in shields.io’s endpoint schema, so shields renders the image and your readers never talk to our domain:
Published by Toolproof, the masthead over this index and eight others. The method behind the number is at toolproof.kynth.studio/methodology, and the whole thing is readable as JSON with no key at /api.