Not in the top 1,000 by GitHub stars
BuildGreatProducts/builder-os
BuilderOS is your operating system for building with AI
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
skills/build-loop-claude-code/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → fb74cac0fc9d
No earlier version was observed for comparison.
skills/build-loop-codex/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → fb74cac0fc9d
No earlier version was observed for comparison.
skills/build-loop-cursor/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → fb74cac0fc9d
No earlier version was observed for comparison.
skills/build-mvp/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → fb74cac0fc9d
No earlier version was observed for comparison.
skills/design-better/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → fb74cac0fc9d
No earlier version was observed for comparison.
skills/design-system/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → fb74cac0fc9d
No earlier version was observed for comparison.
skills/idea-generator/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → fb74cac0fc9d
No earlier version was observed for comparison.
skills/idea-validator/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → fb74cac0fc9d
No earlier version was observed for comparison.
skills/launch-checklist/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → fb74cac0fc9d
No earlier version was observed for comparison.
skills/product-planner/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → fb74cac0fc9d
No earlier version was observed for comparison.
Heat
1.7- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
- build-loop-claude-code
skills/build-loop-claude-code - build-loop-codex
skills/build-loop-codex - build-loop-cursor
skills/build-loop-cursor - build-mvp
skills/build-mvp - design-better
skills/design-better - design-system
skills/design-system - idea-generator
skills/idea-generator - idea-validator
skills/idea-validator - launch-checklist
skills/launch-checklist - product-planner
skills/product-planner
How it works
build-loop-claude-code
When your agent uses it
Use when building features with **Claude Code** in any codebase and the work should go through a disciplined build → review → test → fix loop. Triggers on "run the build loop", "build the next task", "continue the plan", "build this feature properly", or any request to implement work from a plan file or a direct feature prompt. Builds from the plan (or the prompt if no plan exists), runs Claude Code's `/review` (plus `/security-review` for sensitive surfaces) and fixes every issue found, tests and verifies the feature end to end, fixes anything testing surfaces, and reports back once complete. Repeats until all plan tasks are checked off.
What it loads into context
Frontmatter
170 tokensAlways available to the agent
SKILL.md
777 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Source of work
- The loop
- Rules
Files
SKILL.mdcore3,498 bytes
Read SKILL.md
# Claude Code Build Loop
Quality-gated feature work: nothing ships on "it compiles" — every increment is built, reviewed, tested end to end, and fixed before the user hears "done."
## Source of work
- **A plan file exists** (roadmap, refactor plan, or task list with `- [ ]` checkboxes — search the repo): work the first unchecked task. Tasks are ordered intentionally — never skip ahead. If the plan references spec docs, read only the sections relevant to the current task.
- **No plan (or the request is outside it):** build from the user's prompt. Restate it as a verifiable goal with 2–4 success criteria and confirm scope in one message before building.
## The loop
Run per task (or per prompted feature). Do not advance until every step passes.
1. **Build.** Implement exactly what the task specifies. Simplest implementation that satisfies it, surgical changes, no speculative scope. Match existing project conventions.View the complete source on GitHubbuild-loop-codex
When your agent uses it
Use when building features with **Codex** (OpenAI Codex CLI) in any codebase and the work should go through a disciplined build → review → test → fix loop. Triggers on "run the build loop", "build the next task", "continue the plan", "build this feature properly", or any request to implement work from a plan file or a direct feature prompt. Builds from the plan (or the prompt if no plan exists), runs Codex's `/review` on uncommitted changes and fixes every issue found, tests and verifies the feature end to end, fixes anything testing surfaces, and reports back once complete. Repeats until all plan tasks are checked off.
What it loads into context
Frontmatter
171 tokensAlways available to the agent
SKILL.md
801 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Source of work
- The loop
- Rules
Files
SKILL.mdcore3,579 bytes
Read SKILL.md
# Codex Build Loop
Quality-gated feature work: nothing ships on "it compiles" — every increment is built, reviewed, tested end to end, and fixed before the user hears "done."
## Source of work
- **A plan file exists** (roadmap, refactor plan, or task list with `- [ ]` checkboxes — search the repo): work the first unchecked task. Tasks are ordered intentionally — never skip ahead. If the plan references spec docs, read only the sections relevant to the current task.
- **No plan (or the request is outside it):** build from the user's prompt. Restate it as a verifiable goal with 2–4 success criteria and confirm scope in one message before building.
## The loop
Run per task (or per prompted feature). Do not advance until every step passes.
1. **Build.** Implement exactly what the task specifies. Simplest implementation that satisfies it, surgical changes, no speculative scope. Match existing project conventions.View the complete source on GitHubbuild-loop-cursor
When your agent uses it
Use when building features with **Cursor** in any codebase and the work should go through a disciplined build → review → test → fix loop. Triggers on "run the build loop", "build the next task", "continue the plan", "build this feature properly", or any request to implement work from a plan file or a direct feature prompt. Builds from the plan (or the prompt if no plan exists), runs Cursor's `/review` and fixes every issue found, tests and verifies the feature end to end, fixes anything testing surfaces, and reports back once complete. Repeats until all plan tasks are checked off.
What it loads into context
Frontmatter
156 tokensAlways available to the agent
SKILL.md
738 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Source of work
- The loop
- Rules
Files
SKILL.mdcore3,334 bytes
Read SKILL.md
# Cursor Build Loop
Quality-gated feature work: nothing ships on "it compiles" — every increment is built, reviewed, tested end to end, and fixed before the user hears "done."
## Source of work
- **A plan file exists** (roadmap, refactor plan, or task list with `- [ ]` checkboxes — search the repo): work the first unchecked task. Tasks are ordered intentionally — never skip ahead. If the plan references spec docs, read only the sections relevant to the current task.
- **No plan (or the request is outside it):** build from the user's prompt. Restate it as a verifiable goal with 2–4 success criteria and confirm scope in one message before building.
## The loop
Run per task (or per prompted feature). Do not advance until every step passes.
1. **Build.** Implement exactly what the task specifies. Simplest implementation that satisfies it, surgical changes, no speculative scope. Match existing project conventions.View the complete source on GitHubbuild-mvp
When your agent uses it
Use inside a product repository when the user wants the full MVP built from their BuilderOS spec documents. Triggers on phrases like "build my MVP", "build the app", "execute the roadmap", "start the build", "work through the whole roadmap", "build everything", or any request to implement the entire plan rather than a single task or phase. Requires `docs/prd.md` and `docs/product-roadmap.md` (plus `docs/product-vision.md` and `docs/design.md` for context). Works through every roadmap task in order — implementing, testing, and verifying each before moving on, marking checkboxes and updating the status line — and runs until all tasks are complete and the magic moment works end to end, then initializes git with an initial commit and offers to connect a remote repo.
What it loads into context
Frontmatter
192 tokensAlways available to the agent
SKILL.md
1,050 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Setup
- Work loop
- Rules
- Wrap up
Files
SKILL.mdcore4,685 bytesSKILL.mdcore4,685 bytes
Read SKILL.md
# Build MVP
Build the complete app by executing every task in `docs/product-roadmap.md`, in order, until all tasks are checked off.
## Setup
Read `docs/product-roadmap.md` first — it is the source of truth for what to build and in what order. `docs/prd.md` is the technical spec behind it; `docs/design.md` holds the visual design tokens; `docs/product-vision.md` holds the product strategy. Do not load these documents wholesale — each phase lists the specific Reference sections to read, plus whatever a task's Notes line points to. If `docs/product-roadmap.md` or `docs/prd.md` is missing, stop and tell the user to run the **Product Planner** skill first (part of BuilderOS: https://github.com/BuildGreatProducts/builder-os).
## Work loop
Repeat until every task in the roadmap is complete:
1. **Find the first unchecked task** (`- [ ]`). Tasks are ordered intentionally — never skip ahead.
2. **Read what the task needs** — its Files and Notes lines, plus the current phase's Reference sections if not yet read this session.View the complete source on GitHubdesign-better
When your agent uses it
Use when the user is building or refactoring UI in their product codebase and wants designer-quality frontend code — not just functional code. Triggers on phrases like "design better", "make this UI feel more designed", "elevate the design quality", "build this with design best practices", "follow UX heuristics", "make this feel professional", "apply design polish", "review this for craft", or any request to apply UX/UI craft heuristics to code generation or review. Pairs with `docs/design.md` when it exists — the design system file owns **style** (colors, typography, spacing tokens, components), this skill owns **craft** (hierarchy, interaction, accessibility, motion, polish). Reference `docs/design.md` tokens by name for every visual decision; apply the 50-item heuristics catalogue and the Laws of UX catalogue below for every craft decision. When `docs/design.md` is absent, fall back to the codebase's existing design conventions and recommend the **Design System** skill. When a heuristic implies a token the design system doesn't have, flag it as a New Pattern to add via the **Design System** skill — never invent a value inline. Fully standalone.
What it loads into context
Frontmatter
307 tokensAlways available to the agent
SKILL.md
5,426 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Inputs
- Workflow
- The heuristics catalogue (50 items)
- The Laws of UX
- Handling New Patterns
- What "done" looks like
Files
SKILL.mdcore23,524 bytesSKILL.mdcore23,524 bytesSKILL.mdcore23,524 bytesSKILL.mdcore23,524 bytes
Read SKILL.md
# Design Better
A craft layer for any coding agent generating or reviewing UI. Style is owned by `docs/design.md`; this skill owns the timeless UX/UI craft heuristics — drawn from Nielsen Norman Group, the [Laws of UX](https://lawsofux.com/), Shneiderman, Refactoring UI, WCAG 2.2, Don Norman, Apple HIG, Material 3, and 2025–2026 AI-product patterns — that separate "shipped" from "designed."
> **Boundary.** When a heuristic implies a visual property, reference a `docs/design.md` token by name (`{colors.primary}`, `{rounded.md}`). If `docs/design.md` doesn't have the token, flag it as a New Pattern to add via the **Design System** skill — never inline hex, font names, or arbitrary px. If `docs/design.md` doesn't exist at all, follow the codebase's existing convention for that property (theme config, CSS custom properties, component library) and note it.
## Inputs
- **`docs/design.md`** — the style layer (recommended, not required). When present, reference its tokens by name for every visual decision. When absent, this skill still applies: fall back to the codebase's existing design conventions (theme config, CSS custom properties, existing components) as the style source, and recommend running the **Design System** skill to establish a single token source of truth (part of BuilderOS: https://github.com/BuildGreatProducts/builder-os).
- **The thing being built or refactored** — a brief, a file, or uncommitted diff.
- **`docs/product-vision.md`** — optional. Its strategy and brand inform microcopy tone and help weight which heuristic categories dominate.
## Workflow
View the complete source on GitHubdesign-system
When your agent uses it
Translates an image (or a set of image references — screenshots, mockups, Figma URLs, live websites) into two mirrored design-system artifacts: `docs/design.md` (YAML tokens + prose, following Google's open [design.md](https://github.com/google-labs-code/design.md) format, for the coding agent) and `docs/design.html` (a self-contained, token-driven style guide rendering every token and component live, for the human to read). Reads the imagery, asks targeted clarifying questions, derives the design tokens (colors, typography, spacing, rounded, components), and writes both files. Fully standalone — requires no other document or skill. Use when the founder says "create a design system", "design from image", "translate image to design", "create design.md", "image to design system", "extract design tokens", or shares an image with no other clear intent.
What it loads into context
Frontmatter
257 tokensAlways available to the agent
SKILL.md
4,439 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use This
- Modes
- Voice
- Step 0: Image Intake
- Step 1: Image Analysis
- Step 2: Context Questions
- Step 3: Token Derivation
- Step 4: Prose Drafting
- Step 5: Confirm and Write
- Step 6: Build the design.html mirror
- Step 7: Handoff
- Editing the design system
Files
SKILL.mdcore19,467 bytesSKILL.mdcore19,467 bytesSKILL.mdcore19,467 bytesSKILL.mdcore19,467 bytesSKILL.mdcore19,467 bytes
Read SKILL.md
# Design System — Image to design.md + design.html
This skill takes an image (or a set of image references) and translates them into a design system captured as **two mirrored files**:
- **`docs/design.md`** — a YAML token block in [Google's open design.md format](https://github.com/google-labs-code/design.md) that gives a coding agent exact implementation values, plus prose rationale explaining the *why*. This is the **source of truth**.
- **`docs/design.html`** — a self-contained, human-readable style guide that renders every token and component live in a browser, styled directly from the same token values. This is the **mirror** the human reads.
Same design system, two audiences: the agent reads the `.md`, the human opens the `.html`. They must always be written and updated together so they never drift.
## When to Use This
- Founder shares a screenshot, mockup, Figma file, inspiration board, or live website and wants it captured as a structured design system
- Founder needs design tokens a coding agent can implement without guessing
- Founder wants a precise token spec to supplement an existing product vision or PRDView the complete source on GitHubidea-generator
When your agent uses it
Guided discovery of a product idea by mining what the founder already knows or already does — covers source selection (business vs. expertise), context capture, pattern synthesis, candidate scorecard, and writes `docs/product-idea.md`. Use when the founder says "generate an idea", "help me find an idea", "what should I build", "product idea from my business", "product idea from my expertise", or otherwise needs to discover a product concept worth building.
What it loads into context
Frontmatter
146 tokensAlways available to the agent
SKILL.md
2,856 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Shared Context
- Modes
- Voice
- Step 0: Source Selection
- Step 1: Context Capture
- Step 2: Pattern Synthesis
- Step 3: Scorecard
- Step 4: Pick One
- Step 5: Sharpen
- Step 6: Write `docs/product-idea.md`
- Step 7: Handoff
- Editing the Idea
Files
SKILL.mdcore12,526 bytesSKILL.mdcore12,526 bytes
Read SKILL.md
# Idea — Product Idea Discovery
This skill helps a founder identify a great product idea by mining what they already know or already do. The output, `docs/product-idea.md`, feeds the downstream BuilderOS skills **Idea Validator** and **Product Planner** — but stands on its own if those aren't installed.
## Shared Context
You are a product development advisor. You are warm, direct, and opinionated. You treat the founder as capable and smart — you're here to help them articulate what's already in their head, not to lecture them.
**Resumability:** This skill is designed to be interrupted and resumed. Always check the current project state before starting work — does `docs/product-idea.md` already exist? Pick up from where things left off rather than restarting.
## Modes
**Starting fresh** (no `docs/product-idea.md` exists):
Run the full idea discovery conversation from Step 0.View the complete source on GitHubidea-validator
When your agent uses it
Pressure-tests a product idea before the founder invests in planning, building, or launching. Surfaces fatal flaws, tests whether the problem is real, maps real competition (including current behavior), plans first 10 customers, defines a 2-week MVP test, returns a strong/weak/pivot verdict, then sharpens `docs/product-idea.md` based on the founder's direction calls. Use when the founder says "validate my idea", "pressure-test", "is this idea good", "find fatal flaws", "stress test my idea", or otherwise wants to evaluate an idea before committing.
What it loads into context
Frontmatter
175 tokensAlways available to the agent
SKILL.md
3,513 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Shared Context
- Modes
- Entry Paths
- Voice
- Step 1: Identify the Core Assumption
- Step 2: Find Fatal Flaws
- Step 3: Problem Reality
- Step 4: Competition Map
- Step 5: First 10 Customers
- Step 6: MVP
- Step 7: Scorecard
- Step 8: Verdict
- Step 9: Direction Check
- Step 10: Apply Sharpened Edits to `docs/product-idea.md`
- Step 11: Write `docs/validation-report.md`
- Step 12: Handoff
- Re-running Validate
Files
SKILL.mdcore15,442 bytes
Read SKILL.md
# Validate — Pressure-Test the Idea
This skill pressure-tests a product idea before the founder invests in planning, building, or launching. It surfaces fatal flaws, tests whether the problem is real, maps actual competition (including current behavior), defines the smallest 2-week MVP test, and returns a direct strong / weak / pivot verdict.
The Idea Validator sits between the **Idea Generator** and **Product Planner** skills in the BuilderOS pipeline. It also runs fully standalone — if no `docs/product-idea.md` exists, it gathers the minimum input itself and writes a fresh `docs/product-idea.md` after a strong or pivot verdict.
## Shared Context
You are a product development advisor. You are warm, direct, and opinionated. You treat the founder as capable and smart — you're here to help them articulate what's already in their head, not to lecture them.
**Resumability:** This skill is designed to be interrupted and resumed. Always check the current project state before starting work — does `docs/validation-report.md` already exist? Has `docs/product-idea.md` been edited since the last run? Pick up from where things left off rather than restarting.
## Modes
View the complete source on GitHublaunch-checklist
When your agent uses it
Use when the user's product is built (or nearly built) and they want to get it live and accessible to customers. Triggers on phrases like "create my launch checklist", "how do I deploy this", "help me launch", "get this live", "put this in production", "ship it to customers", "what do I need to do to go live", or any request for a step-by-step path from working code to a product customers can use. Audits the current codebase — stack, services, environment variables, payments, deploy config — then writes a plain-English, step-by-step launch guide to `docs/launch-checklist.md`. Every step is marked as something the user must do themselves, something their coding agent can do, or both together, and all technical terms are explained for non-technical founders.
What it loads into context
Frontmatter
196 tokensAlways available to the agent
SKILL.md
1,362 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Step 1: Audit the codebase
- Step 2: Write `docs/launch-checklist.md`
- Step 3: Walk the user in
- Rules
Files
SKILL.mdcore6,218 bytes
Read SKILL.md
# Launch Checklist
This skill turns "the app works on my machine" into "customers can use it." It reviews the actual codebase, works out everything standing between the current state and a live product, and writes a personalised, step-by-step guide the founder can follow without a technical background.
The voice is a patient senior engineer onboarding a smart non-technical founder: plain language, no unexplained jargon, never condescending. The founder is capable — they just haven't done this before.
## Step 1: Audit the codebase
Read the repository thoroughly before writing anything. Establish:
- **What the product is and where it runs** — web app, mobile app (App Store / Google Play), desktop, or a mix. Detect the framework, backend, database, auth, and payment providers from the code and dependencies — don't ask the user things the code answers.
- **Configuration state** — environment variables used in code vs. what's documented (`.env.example` or similar), hardcoded values that must become secrets, test/sandbox keys that need live equivalents.
- **Third-party services** — every external service the app calls, and what each needs in production (live API keys, webhook endpoints, billing enabled).
- **Deploy readiness** — existing deploy config (e.g. `vercel.json`, `Dockerfile`, `eas.json`), build scripts, whether the production build currently succeeds, test status.View the complete source on GitHubproduct-planner
When your agent uses it
Vision intake conversation followed by generation of three product documents — `docs/product-vision.md` (strategy and brand), `docs/prd.md` (technical spec for coding agents), and `docs/product-roadmap.md` (phased build plan with task checkboxes). Also captures the founder's answers as `docs/VISION.md`. Use when the founder says "plan my product", "plan a product", "define my vision", "generate a PRD", "create a roadmap", "spec out my idea", "help me build something", or wants to convert an idea into shippable spec documents.
What it loads into context
Frontmatter
180 tokensAlways available to the agent
SKILL.md
4,028 tokensWhen the skill is activated
Reference documents
23,915 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Shared Context
- Modes
- Vision Intake
- Document Generation
- Refreshing Documents
- Editing the Vision
Files
SKILL.mdcore18,542 bytesresources/INTAKE-GUIDE.mddoc21,148 bytesresources/PRD-GENERATION.mddoc16,197 bytesresources/ROADMAP-GENERATION.mddoc20,706 bytesresources/TECH-STACK-OPTIONS.mddoc31,024 bytesresources/VISION-GENERATION.mddoc10,863 bytesresources/VISION-TEMPLATE.mddoc9,487 bytes
Read SKILL.md
# Product Planner — Vision Intake + Document Generation
This skill captures a founder's product vision through a structured intake conversation and then generates three product documents that downstream skills (Launch Checklist, the Build Loop skills) and coding agents consume.
## Shared Context
You are a product development advisor. You are warm, direct, and opinionated. You treat the founder as capable and smart — you're here to help them articulate what's already in their head, not to lecture them.
**Validation rule:** Before generating any documents from `docs/VISION.md`, validate it against the template in [resources/VISION-TEMPLATE.md](./resources/VISION-TEMPLATE.md) — all sections present in order, every field filled, enum values valid, list fields non-empty. If validation fails, report the problems and fix them in `docs/VISION.md` before proceeding.
**Resumability:** This skill is designed to be interrupted and resumed. Always check the current project state before starting work — does `docs/VISION.md` exist? Are docs present? Pick up from where things left off rather than restarting.
## Modes
View the complete source on GitHubSkills included
- build-loop-claude-code
- build-loop-codex
- build-loop-cursor
- build-mvp
- design-better
- design-system
- idea-generator
- idea-validator
- launch-checklist
- product-planner
Repository facts
- License
- MIT
- Created
- Jun 11, 2026
- Last pushed
- Jul 7, 2026
- Forks
- 43
- Open issues
- 2
- Project activity
- Slowing
Before you install
Instructions onlyAutomated signals, not a guarantee
Checked Nov 4, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 9 notes
skills/build-mvp/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/design-better/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/design-better/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/design-better/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/design-system/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/design-system/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/design-system/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/design-system/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/idea-generator/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- No dangerous shell commands
- 17 network referencesin 7 files: design-system/SKILL.md:5 product-planner/resources/ROADMAP-GENERATION.md:255 design-better/SKILL.md:13 and 4 more
- No hidden or obfuscated text
- No instruction overrides
- No executable scripts
- 1 reference to secretsin 1 file: product-planner/resources/PRD-GENERATION.md:420
- No requests to vote in Hot
Show all 18 signals by file
skills/build-mvp/SKILL.md
- Network accessline 16
Read `docs/product-roadmap.md` first — it is the source of truth for what to build and in what order. `docs/prd.md` is the technical spec behind it; `docs/design.md` holds the visual design tokens; `docs/product-vision.md` holds the product
skills/design-better/SKILL.md
- Network accessline 13
A craft layer for any coding agent generating or reviewing UI. Style is owned by `docs/design.md`; this skill owns the timeless UX/UI craft heuristics — drawn from Nielsen Norman Group, the [Laws of UX](https://lawsofux.com/), Shneiderman, - Network accessline 19
- **`docs/design.md`** — the style layer (recommended, not required). When present, reference its tokens by name for every visual decision. When absent, this skill still applies: fall back to the codebase's existing design conventions (them - Network accessline 174
The 50 heuristics above are the actionable checklist; the Laws of UX below are the psychological principles behind them — drawn from [lawsofux.com](https://lawsofux.com/). Apply them where relevant, especially the ones with no direct heuris
skills/design-system/SKILL.md
- Network accessline 5
mockups, Figma URLs, live websites) into two mirrored design-system artifacts: `docs/design.md` (YAML tokens + prose, following Google's open [design.md](https://github.com/google-labs-code/design.md) format, for the - Network accessline 6
artifacts: `docs/design.md` (YAML tokens + prose, following Google's open [design.md](https://github.com/google-labs-code/design.md) format, for the coding agent) and `docs/design.html` (a self-contained, token-driven style - Network accessline 7
[design.md](https://github.com/google-labs-code/design.md) format, for the - Network accessline 28
- **`docs/design.md`** — a YAML token block in [Google's open design.md format](https://github.com/google-labs-code/design.md) that gives a coding agent exact implementation values, plus prose rationale explaining the *why*. This is the **s - Network accessline 293
If the Product Planner skill isn't installed, mention that it's part of BuilderOS: https://github.com/BuildGreatProducts/builder-os.
skills/idea-generator/SKILL.md
- Network accessline 225
> "Both skills are part of BuilderOS: https://github.com/BuildGreatProducts/builder-os"
skills/idea-validator/SKILL.md
- Network accessline 309
> "Both skills are part of BuilderOS: https://github.com/BuildGreatProducts/builder-os"
skills/product-planner/SKILL.md
- Network accessline 48
**Validation nudge:** If `docs/product-idea.md` exists but `docs/validation-report.md` does not, gently mention the **Idea Validator** skill as a recommended pre-step before the founder commits to the full vision intake — but do not block. - Network accessline 259
If any of those skills aren't installed, note they're all part of BuilderOS: https://github.com/BuildGreatProducts/builder-os.
skills/product-planner/resources/PRD-GENERATION.md
- Access to secretsline 420
[Credential-related source omitted]
skills/product-planner/resources/ROADMAP-GENERATION.md
- Network accessline 255
The PR should be reviewed by an automated review agent before merging. Recommend [CodeRabbit](https://coderabbit.ai) as the default — it's free for open-source and provides automated code review on every PR. Other options (GitHub Copilot co - Network accessline 281
3. **Let it work:** The agent reads the roadmap, finds the first unchecked task, implements it, and marks it complete. 4. **One session = one phase (ideally):** Try to complete a full phase in one session for best continuity. If you need to - Network accessline 282
4. **One session = one phase (ideally):** Try to complete a full phase in one session for best continuity. If you need to stop, the agent can resume from the last unchecked task. 5. **Push a PR for review:** When a phase is complete, push t - Network accessline 283
5. **Push a PR for review:** When a phase is complete, push the work as a PR and let a review agent (e.g. [CodeRabbit](https://coderabbit.ai)) review it before starting the next phase. See the Phase Review section below.
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
Signal confidence: 18 facts
- Network access in prose of the SKILL.mdbuild-mvp/SKILL.md:16Low confidence
- Network access in prose of the SKILL.mddesign-better/SKILL.md:13Low confidence
- Network access in prose of the SKILL.mddesign-better/SKILL.md:19Low confidence
- Network access in prose of the SKILL.mddesign-better/SKILL.md:174Low confidence
- Network access in the frontmatter of the SKILL.mddesign-system/SKILL.md:5Low confidence
- Network access in the frontmatter of the SKILL.mddesign-system/SKILL.md:6Low confidence
- Network access in the frontmatter of the SKILL.mddesign-system/SKILL.md:7Low confidence
- Network access in prose of the SKILL.mddesign-system/SKILL.md:28Low confidence
- Network access in prose of the SKILL.mddesign-system/SKILL.md:293Low confidence
- Network access in prose of the SKILL.mdidea-generator/SKILL.md:225Low confidence
- Network access in prose of the SKILL.mdidea-validator/SKILL.md:309Low confidence
- Network access in prose of the SKILL.mdproduct-planner/SKILL.md:48Low confidence
- Network access in prose of the SKILL.mdproduct-planner/SKILL.md:259Low confidence
- Access to secrets in prose of documentation: a variable, placeholder or call, not a stored valueproduct-planner/resources/PRD-GENERATION.md:420Low confidence
- Network access in prose of documentationproduct-planner/resources/ROADMAP-GENERATION.md:255Low confidence
- Network access in code of documentationproduct-planner/resources/ROADMAP-GENERATION.md:281Low confidence
- Network access in code of documentationproduct-planner/resources/ROADMAP-GENERATION.md:282Low confidence
- Network access in code of documentationproduct-planner/resources/ROADMAP-GENERATION.md:283Low confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Compatible | Standard SKILL.md skills/build-loop-claude-code/SKILL.md | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md skills/build-loop-claude-code/SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md skills/build-loop-claude-code/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md skills/build-loop-claude-code/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md skills/build-loop-claude-code/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md skills/build-loop-claude-code/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.