

Also from Kynth Studios


Also from Kynth Studios


Also from Kynth Studios
123456# Using bigpowers7> **HARD GATE** — **HARD GATE** — This skill is the entry point. Do NOT skip it when onboarding new users or starting a new session. It establishes the bigpowers methodology, lifecycle phases, and conventions.8910Welcome to **bigpowers** — a lifecycle of agent skills for production-ready, TDD-driven software by solo developers. The live catalog and its count are generated in [`SKILL-INDEX.md`](../../SKILL-INDEX.md); never hardcode the number here.1112## Install1314```bash15npx bigpowers setup # one-shot setup16npm install -g bigpowers # global install17bigpowers setup # sync skills + link to your tools18```1920From source: `git clone` → `bash scripts/install.sh`. Package: [bigpowers on npm](https://www.npmjs.com/package/bigpowers).2122**Reach tools:** **Cline** — native AGENTS.md reader (no extension). **Aider** — opt-in `.aider.conf.yml` with `read: AGENTS.md` ([Aider-AI/aider](https://github.com/Aider-AI/aider)). **Codex CLI** — optional `.codex/config.toml` via seed-conventions; global `~/.codex/AGENTS.md` from install.sh.2324## What bigpowers is2526A curated set of skills organized around the PMBOK developer lifecycle. Each skill does one thing. Skills reference each other by name only — low coupling, high cohesion. All written output goes to `specs/` at your project root.2728## The lifecycle at a glance2930See orchestrate-project for the canonical 6-phase lifecycle.3132```33BOOTSTRAP using-bigpowers (this skill, first time only)34 ↓35DISCOVER survey-context → research-first → elaborate-spec36 ↓37DESIGN model-domain / define-language / grill-me / deepen-architecture / design-interface38 ↓39PLAN scope-work → slice-tasks → plan-work / plan-refactor40 ↓41INITIATE kickoff-branch → guard-git / hook-commits / seed-conventions42 ↓43SPIKE? spike-prototype → (feeds back to plan-work)44 ↓45EXECUTE develop-tdd + enforce-first ←→ delegate-task / dispatch-agents / execute-plan46 ↓47VERIFY run-evals → verify-work48 ↓49HARDEN wire-observability (any phase)50 ↓51BUG? investigate-bug → diagnose-root → validate-fix52 ↓53REVIEW audit-code → request-review → respond-review54 ↓55INTEGRATE commit-message → release-branch56 ↓57SUSTAIN inspect-quality / organize-workspace (ongoing)5859UTILITY terse-mode / craft-skill / edit-document (any phase)60```6162## Where to start6364| Your situation | First skill to call |65|---------------|---------------------|66| Greenfield project, nothing set up | `seed-conventions` |67| Existing project, new task | `survey-context` |68| Vague idea that needs shaping | `elaborate-spec` |69| Plan exists, ready to implement | `kickoff-branch` → `develop-tdd` |70| Bug to fix | `investigate-bug` |71| Code ready for review | `audit-code` |72| Shipping a feature | `commit-message` → `release-branch` |73| Solo dev, PRs feel heavy | Enable `profiles/solo-git.md` → `specs/WORKFLOW-solo-git.md` → land via `scripts/land-branch.sh` |7475## Solo Git profile7677If you work alone and do not want PR ceremony every task:78791. Read [profiles/solo-git.md](../../profiles/solo-git.md).802. Register with `compose-workflow` → `specs/WORKFLOW-solo-git.md`.813. Ship with `release-branch` in **solo-local** mode (`land-branch.sh`), not `gh pr create`.8283You still use worktrees, protected `main`, and verification gates — only the integrate step changes.8485## YAML cockpit and dashboard8687Operational source of truth:8889- `specs/state.yaml` — session, active epic/story, handoff90- `specs/release-plan.yaml` — release index and epic list91- `specs/epics/eNN-*.yaml` — stories and tasks with `verify`92- `specs/execution-status.yaml` — done/pending per story9394Start the HTTP dashboard with `visual-dashboard` → `GET /api/status?projectDir=<abs>` and `GET /cockpit.html` for a read-only PM view.9596## Key conventions9798- **specs/ is your memory.** All domain docs, plans, and investigation outputs go in `specs/` at your project root.99- **Integrate:** team default is `gh pr` (team-pr); solo profile uses `land-branch.sh`. Never create GitHub issues from skills — use local Markdown files instead.100- **One skill, one thing.** If you're unsure which skill to call, call `survey-context` — it reads your current state and recommends the next step.101- **verify: every step.** Every epic task must have `verify: <runnable command>`. Evidence over claims.102- **The full catalog is auto-generated.** See `SKILL-INDEX.md`; find skills with `search-skills`.103104## After this105106Call `survey-context` to read your project's current state and get a personalized recommendation for where to go next.107108109110<!-- story: e03s02 -->111
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-using-bigpowers)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.