Not in the top 1,000 by GitHub stars
tryproduck/produck-skills
Agent skills to help you build products your users love.
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/demo-studio/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a699eb2a74f → 9a699eb2a74f
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a699eb2a74f
No earlier version was observed for comparison.
skills/produck-feedback/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9a699eb2a74f → 9a699eb2a74f
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9a699eb2a74f
No earlier version was observed for comparison.
skills/taste/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
9a699eb2a74f → 9a699eb2a74f
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 9a699eb2a74f
No earlier version was observed for comparison.
skills/user-alignment/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
9a699eb2a74f → 9a699eb2a74f
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 9a699eb2a74f
No earlier version was observed for comparison.
Verified commit 9a699eb2a74fee1bbbd80b81bcb859d5427b6165
git clone --filter=blob:none --no-checkout https://github.com/tryproduck/produck-skills.git .hotskills/tryproduck-produck-skills && git -C .hotskills/tryproduck-produck-skills checkout --detach 9a699eb2a74fee1bbbd80b81bcb859d5427b6165
# Copy each selected skill directory from .hotskills/tryproduck-produck-skills into .claude/skills/<skill-name>/Heat
0.1- 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
- demo-studio
skills/demo-studio - produck-feedback
skills/produck-feedback - taste
skills/taste - user-alignment
skills/user-alignment
How it works
demo-studio
When your agent uses it
Build a premium, fully-animated PRODUCT-DEMO / launch motion-graphics video from a written brief about your product — the "one seamless film" style: scene-by-scene motion graphics with camera moves, real UI mockups, and full sound design, rendered from HTML+CSS+GSAP to MP4 via HyperFrames. Use whenever someone wants to "make a product demo video", "launch video", "animated walkthrough", "hype/demo reel for <product>", an animated feature or flywheel story, or to add any of these set-pieces: a notification/feedback FLOOD of bubbles, real photos of people as circular avatars, a GitHub/changelog/release mock, a "context accumulates" web of connecting cards, a UI element that MOVES + recolors with the camera following it, a contributors wall, an explosion-into-logo endcard, count-up numbers, 3D panel fly-ins, or camera zoom/dolly transitions. ALSO covers full SOUND DESIGN — picking the right SFX for each animation and placing them (see docs/SOUND.md + the bundled sfx/ kit + templates/). The techniques come from a real launch film (https://youtu.be/spaS08Udkyk), but this is a GENERAL-PURPOSE kit: do not copy that film's story. Ask the user what THEIR product does, pick a story arc that fits it, and re-skin the brand tokens. The bundled example uses deliberately generic placeholder copy. For single-concept explainer reels or talking-head edits this is the wrong tool.
What it loads into context
Frontmatter
381 tokensAlways available to the agent
SKILL.md
2,177 tokensWhen the skill is activated
Reference documents
9,353 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 0. When to use / not use
- 1. Architecture (always the same)
- 2. Brand tokens (re-skin per product) — see docs/BRANDING.md
- 3. The technique library — copy these patterns
- 4. Gotchas
- 5. Sound design — see docs/SOUND.md + sfx/ + templates/
- 6. Starting a NEW video
Scripts executed separately
scripts/render.shsetup.shtemplates/build_audio_kit.pytemplates/make_kit.py
Files
../../.claude-plugin/marketplace.jsonasset490 bytes../../.claude-plugin/plugin.jsonasset625 bytesSKILL.mdcore8,219 bytesdocs/ARCHITECTURE.mddoc9,553 bytesdocs/BRANDING.mddoc3,274 bytesdocs/HOW-IT-WORKS.mddoc4,940 bytesdocs/SETUP.mddoc2,962 bytesdocs/SOUND.mddoc5,592 bytesdocs/TUTORIAL.mddoc6,937 bytesexample/hyperframes.jsonasset264 bytesexample/index.htmlasset15,825 bytesexample/meta.jsonasset61 bytesscripts/render.shruns1,773 bytessetup.shruns3,678 bytessfx/boom.wavasset75,014 bytessfx/capture.wavasset30,032 bytessfx/click.wavasset1,630 bytessfx/coin.wavasset26,504 bytessfx/confirm.wavasset30,032 bytessfx/ding.wavasset28,268 bytessfx/dinghi.wavasset24,740 bytessfx/drag.wavasset37,088 bytessfx/implode.wavasset54,728 bytessfx/notify.wavasset26,504 bytessfx/pop.wavasset6,658 bytessfx/pophard.wavasset7,982 bytessfx/resolve.wavasset97,064 bytessfx/riser.wavasset123,522 bytessfx/success.wavasset26,504 bytessfx/swish.wavasset26,504 bytessfx/swishfast.wavasset17,684 bytessfx/thump.wavasset30,032 bytessfx/tick.wavasset1,102 bytessfx/type.wavasset105,884 bytessfx/unlock.wavasset44,144 bytessfx/wash.wavasset48,554 bytessfx/whoosh.wavasset54,728 bytessfx/zoomin.wavasset48,554 bytessfx/zoomout.wavasset48,554 bytestemplates/build_audio_kit.pyruns3,907 bytestemplates/make_kit.pyruns6,563 bytes
Read SKILL.md
# DemoStudio — the playbook
You are building a **premium product-demo motion-graphics film**: one seamless timeline of
full-screen scenes telling the USER'S story (pick an arc that fits their product, e.g. problem →
product → payoff, before → after, or many inputs → one output; do not default to a feedback-capture
loop), with camera moves between beats. The whole video is **ONE self-contained HyperFrames composition**
(`index.html` = HTML + CSS + GSAP) that renders to MP4, then a single SFX track is muxed on.
**Start from the example:** `example/index.html` is a compact, commented, working scaffold that
shows the whole architecture (paused timeline, 3 scenes, a camera push, a flood, an endcard). Read
it first, then grow it into the real thing scene by scene.
---
View the complete source on GitHubproduck-feedback
When your agent uses it
Use when acting on real user feedback — you have a Produck feedback ticket or URL, or the user wants to fix something users complained about or build a feature users asked for. Pulls full feedback context through the Produck MCP and drives a feedback → aligned PRD → build loop. Triggers on "fix what users reported", a feedback ticket id, "use my produck feedback", or building from a feedback queue.
What it loads into context
Frontmatter
120 tokensAlways available to the agent
SKILL.md
968 tokensWhen the skill is activated
Reference documents
717 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 1. What this connects to
- 2. The two MCP tools
- 3. The operating loop
- 4. Setup
Files
SKILL.mdcore4,158 bytesreferences/connect-mcp.mddoc2,512 bytes
Read SKILL.md
# Building from Produck feedback
**Purpose:** Turn real, in-context user feedback into shipped fixes. This skill drives the
[Produck](https://tryproduck.com) MCP — it tells the agent how to find the right feedback, load the
full context behind it, and convert that context into an aligned change instead of a guess.
> Requires the Produck MCP server connected. If `search_feedback` / `get_feedback` are not available,
> see [`references/connect-mcp.md`](references/connect-mcp.md) to connect it and mint a token first.
---
## 1. What this connects to
Produck captures feedback **in the user's own session**, so a ticket is far richer than a textView the complete source on GitHubtaste
When your agent uses it
Use when improving the visual taste, positioning, polish, trust, and conversion clarity of a website or product UI. Runs a category-first visual audit, applies a decisive design pass, and verifies the result with screenshots rather than subjective vibes.
What it loads into context
Frontmatter
79 tokensAlways available to the agent
SKILL.md
2,030 tokensWhen the skill is activated
Reference documents
3,726 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 1. Outcome
- 2. Taste rules for agents
- 3. One-shot workflow
- 4. Agent guardrails
- 5. PR checklist
Files
SKILL.mdcore9,517 bytesSKILL.mdcore9,517 bytesSKILL.mdcore9,517 bytesSKILL.mdcore9,517 bytesreferences/benchmark-notes.mddoc1,562 bytesreferences/immersive-landing-pages.mddoc4,024 bytesreferences/taste-principles.mddoc8,744 bytesreferences/website-improvement-loop.mddoc3,293 bytes
Read SKILL.md
# Taste — Website Visual Improvement
**Purpose:** Upgrade a website from merely functional to visibly credible, high-intent, and conversion-ready in one focused pass.
This skill is for agents asked to "make this look better," "polish the site," "improve the landing page," "make it feel premium," or "fix the design." Do not make random decorative changes. Taste is a system: category, worldview, hierarchy, restraint, alignment, rhythm, contrast, proof, and visual verification.
> Supporting files:
> - [`references/taste-principles.md`](references/taste-principles.md) — category-first principles and the taste rubric.
> - [`references/website-improvement-loop.md`](references/website-improvement-loop.md) — the step-by-step browser screenshot loop.
> - [`references/benchmark-notes.md`](references/benchmark-notes.md) — one-shot before/after benchmark notes.
> - [`references/immersive-landing-pages.md`](references/immersive-landing-pages.md) — guidance for WebGL, animation, bespoke motion, and generated media.
---
View the complete source on GitHubuser-alignment
When your agent uses it
Use when turning a vague or messy user request into an aligned, agent-executable PRD. Converts raw requests into testable specs with scope, phases, acceptance criteria, and explicit do-not-do boundaries for coding agents. Triggers on planning a feature from a rough ask, writing a PRD/spec, or aligning on intent before code.
What it loads into context
Frontmatter
102 tokensAlways available to the agent
SKILL.md
4,623 tokensWhen the skill is activated
Reference documents
3,057 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 1. Core thesis
- 2. Research-backed principles
- 3. User alignment workflow
- Risks
- 4. Agent-executable PRD template
- 5. PRD review rubric for agents
- 6. Common failure modes and fixes
- 7. Useful prompts
- 8. Autoresearch loop synthesis
- 9. Further reading
Files
SKILL.mdcore21,183 bytesSKILL.mdcore21,183 bytesreferences/prd-template.mddoc7,423 bytesreferences/reading-list.mddoc4,162 bytes
Read SKILL.md
# User Alignment & Agent-Executable PRDs
**Purpose:** A practical guide for turning messy user requests into aligned, testable Product Requirements Documents (PRDs) that autonomous or semi-autonomous agents can execute without drifting.
> Two supporting files ship with this skill:
> - [`references/prd-template.md`](references/prd-template.md) — the full copy-paste agent-executable PRD template.
> - [`references/reading-list.md`](references/reading-list.md) — the research and reference map this guide is built on.
---
## 1. Core thesis
A good agent PRD is not just a product document. It is a **shared operating contract** between the user, the product owner, and the implementation agent.
View the complete source on GitHubSkills included
- demo-studio
- produck-feedback
- taste
- user-alignment
Repository facts
- License
- Apache-2.0
- Created
- Jun 3, 2026
- Last pushed
- Aug 14, 2026
- Forks
- 10
- Open issues
- 0
- Project activity
- Slowing
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 5, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 4 notes
skills/taste/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/taste/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/taste/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/user-alignment/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- 7 dangerous shell commandsin 3 files: demo-studio/setup.sh:35 demo-studio/docs/SETUP.md:42 taste/references/website-improvement-loop.md:60
- 91 network referencesin 13 files: user-alignment/references/reading-list.md:9 produck-feedback/references/connect-mcp.md:6 demo-studio/setup.sh:18 and 10 more
- No hidden or obfuscated text
- No instruction overrides
- 4 executable scriptsin 4 files: demo-studio/scripts/render.sh:1 demo-studio/setup.sh:1 demo-studio/templates/build_audio_kit.py:1 and 1 more
- 2 references to secretsin 1 file: produck-feedback/references/connect-mcp.md:14
- No requests to vote in Hot
Show all 104 signals by file
.claude-plugin/marketplace.json
- Network accessline 8
"source": ".", "description": "Produck MCP (search_feedback, get_feedback) + feedback-to-fix and user-alignment skills.", "author": { "name": "Produck", "email": "yuv@tryproduck.com", "url": "https://tryproduck.com" } - Network accessline 9
"description": "Produck MCP (search_feedback, get_feedback) + feedback-to-fix and user-alignment skills.", "author": { "name": "Produck", "email": "yuv@tryproduck.com", "url": "https://tryproduck.com" } } - Network accessline 10
"author": { "name": "Produck", "email": "yuv@tryproduck.com", "url": "https://tryproduck.com" }
.claude-plugin/plugin.json
- Network accessline 3
"description": "Pull real in-context user feedback into your coding agent and ship aligned fixes. Bundles the produck MCP (search_feedback, get_feedback), a feedback-to-fix guide skill, and the user-alignment PRD skill.", "version": "0.1. - Network accessline 4
"version": "0.1.0", "author": { "name": "Produck", "email": "yuv@tryproduck.com", "url": "https://tryproduck.com" }, "homepage": "https://tryproduck.com", - Network accessline 5
"author": { "name": "Produck", "email": "yuv@tryproduck.com", "url": "https://tryproduck.com" }, - Network accessline 6
"homepage": "https://tryproduck.com", - Network accessline 7
"repository": "https://github.com/tryproduck/produck-skills",
skills/demo-studio/SKILL.md
- Network accessline 13
camera zoom/dolly transitions. ALSO covers full SOUND DESIGN — picking the right SFX for each animation and placing them (see docs/SOUND.md + the bundled sfx/ kit + templates/). The techniques come from a real launch film (https://youtu - Network accessline 14
animation and placing them (see docs/SOUND.md + the bundled sfx/ kit + templates/). The techniques come from a real launch film (https://youtu.be/spaS08Udkyk), but this is a GENERAL-PURPOSE kit: do not copy that film's story. Ask the us - Network accessline 15
come from a real launch film (https://youtu.be/spaS08Udkyk), but this is a GENERAL-PURPOSE kit: do
skills/demo-studio/docs/HOW-IT-WORKS.md
- Network accessline 28
We use [GSAP](https://gsap.com) (a battle-tested animation library) to describe the whole video as one
skills/demo-studio/docs/SETUP.md
- Network accessline 27
If a step fails, the script prints the exact manual command to fix it. The most common one is Homebrew not being installed on macOS: install it from [brew.sh](https://brew.sh) and re-run. - Network accessline 28
Homebrew not being installed on macOS: install it from [brew.sh](https://brew.sh) and re-run. - Dangerous shell operationline 42
sudo apt-get update && sudo apt-get install -y nodejs npm ffmpeg python3-pip - Network accessline 67
- **`npx: command not found`** — Node didn't install correctly. Re-run `./setup.sh` or install Node from [nodejs.org](https://nodejs.org). - Network accessline 68
[nodejs.org](https://nodejs.org). - Dangerous shell operationline 72
first; on Linux `sudo apt-get install -y libsndfile1`. You only need librosa for the sound pass, so you
skills/demo-studio/example/hyperframes.json
skills/demo-studio/example/index.html
- Network accessline 5
<meta name="viewport" content="width=1920, height=1080" /> <!-- HyperFrames seeks a paused GSAP timeline frame-by-frame. GSAP from CDN: --> <script src="https://cdn.jsdelivr.net/npm/gsap@3.14.2/dist/gsap.min.js"></script> - Network accessline 6
<!-- HyperFrames seeks a paused GSAP timeline frame-by-frame. GSAP from CDN: --> <script src="https://cdn.jsdelivr.net/npm/gsap@3.14.2/dist/gsap.min.js"></script> <script src="https://cdn.jsdelivr.net/npm/gsap@3.14.2/dist/MotionPathPlug - Network accessline 7
<script src="https://cdn.jsdelivr.net/npm/gsap@3.14.2/dist/gsap.min.js"></script> - Network accessline 8
<script src="https://cdn.jsdelivr.net/npm/gsap@3.14.2/dist/MotionPathPlugin.min.js"></script> - Network accessline 9
<link rel="preconnect" href="https://fonts.googleapis.com"> - Network accessline 10
<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin> - Network accessline 11
<link href="https://fonts.googleapis.com/css2?family=Plus+Jakarta+Sans:wght@500;800&family=Inter:wght@400;600&family=JetBrains+Mono:wght@500;700&display=swap" rel="stylesheet">
skills/demo-studio/scripts/render.sh
- Executable scriptline 1
#!/usr/bin/env bash
skills/demo-studio/setup.sh
- Executable scriptline 1
#!/usr/bin/env bash - Network accessline 18
PKG="" # the system package manager we'll use for ffmpeg/node if missing if [ "$OS" = "Darwin" ]; then have brew && PKG="brew" || warn "Homebrew not found. Install it from https://brew.sh then re-run, or install ffmpeg/node manually." - Network accessline 19
if [ "$OS" = "Darwin" ]; then have brew && PKG="brew" || warn "Homebrew not found. Install it from https://brew.sh then re-run, or install ffmpeg/node manually." elif [ "$OS" = "Linux" ]; then - Network accessline 20
have brew && PKG="brew" || warn "Homebrew not found. Install it from https://brew.sh then re-run, or install ffmpeg/node manually." - Dangerous shell operationline 35
apt) sudo apt-get update && sudo apt-get install -y nodejs npm ;; - Network accessline 35
apt) sudo apt-get update && sudo apt-get install -y nodejs npm ;; dnf) sudo dnf install -y nodejs ;; *) die "Install Node 18+ from https://nodejs.org then re-run." ;; - Dangerous shell operationline 36
dnf) sudo dnf install -y nodejs ;; - Network accessline 36
dnf) sudo dnf install -y nodejs ;; *) die "Install Node 18+ from https://nodejs.org then re-run." ;; esac - Network accessline 37
*) die "Install Node 18+ from https://nodejs.org then re-run." ;; - Dangerous shell operationline 47
apt) sudo apt-get update && sudo apt-get install -y ffmpeg ;; - Network accessline 47
apt) sudo apt-get update && sudo apt-get install -y ffmpeg ;; dnf) sudo dnf install -y ffmpeg ;; *) die "Install ffmpeg (https://ffmpeg.org/download.html) then re-run." ;; - Dangerous shell operationline 48
dnf) sudo dnf install -y ffmpeg ;; - Network accessline 48
dnf) sudo dnf install -y ffmpeg ;; *) die "Install ffmpeg (https://ffmpeg.org/download.html) then re-run." ;; esac - Network accessline 49
*) die "Install ffmpeg (https://ffmpeg.org/download.html) then re-run." ;; - Network accessline 55
if have python3; then ok "$(python3 --version)"; else die "Install Python 3 (https://python.org) then re-run."; fi
skills/demo-studio/templates/build_audio_kit.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/demo-studio/templates/make_kit.py
- Executable scriptline 1
#!/usr/bin/env python3
skills/produck-feedback/SKILL.md
- Network accessline 12
**Purpose:** Turn real, in-context user feedback into shipped fixes. This skill drives the [Produck](https://tryproduck.com) MCP — it tells the agent how to find the right feedback, load the - Network accessline 13
[Produck](https://tryproduck.com) MCP — it tells the agent how to find the right feedback, load the
skills/produck-feedback/references/connect-mcp.md
- Network accessline 6
> The dashboard at `https://tryproduck.com/app` is the source of truth for these snippets — it fills in - Network accessline 11
1. Open `https://tryproduck.com/app` → **MCP** section. - Access to secretsline 14
[Credential-related source omitted] - Network accessline 43
"produck": { "type": "http", "url": "https://tryproduck.com/api/mcp", - Network accessline 44
[Credential-related source omitted] - Network accessline 45
"url": "https://tryproduck.com/api/mcp", - Network accessline 54
{ "$schema": "https://opencode.ai/config.json", - Network accessline 55
"$schema": "https://opencode.ai/config.json", - Network accessline 57
"produck": { "type": "remote", "url": "https://tryproduck.com/api/mcp", - Network accessline 58
"type": "remote", "url": "https://tryproduck.com/api/mcp", "enabled": true, - Network accessline 59
"url": "https://tryproduck.com/api/mcp", - Network accessline 69
[Credential-related source omitted] - Access to secretsline 69
[Credential-related source omitted] - Network accessline 70
[mcp_servers.produck] url = "https://tryproduck.com/api/mcp" bearer_token_env_var = "PRODUCK_MCP_TOKEN" - Network accessline 71
url = "https://tryproduck.com/api/mcp" - Network accessline 77
claude mcp add --transport http produck https://tryproduck.com/api/mcp \
skills/taste/SKILL.md
- Network accessline 133
npx -y chrome-devtools-axi open http://localhost:3000
skills/taste/references/taste-principles.md
- Network accessline 7
- [Nielsen Norman Group on visual hierarchy](https://www.nngroup.com/articles/visual-hierarchy-ux-definition/) defines it as organizing design elements so the eye consumes them in order of intended importance. It highlights scale, color/con - Network accessline 8
- [NN/g's visual-design principles](https://www.nngroup.com/articles/principles-visual-design/) emphasize scale, hierarchy, balance, contrast, and Gestalt as usability tools, not just aesthetics. - Network accessline 9
- [NN/g's good visual design guidance](https://www.nngroup.com/articles/good-visual-design/) recommends alignment to a grid, clear type hierarchy, intentional color, and consistency. - Network accessline 10
- [Stanford Web Credibility guidelines](https://credibility.stanford.edu/guidelines/) found that visual design, layout, typography, and consistency strongly influence perceived credibility; its public guidelines explicitly recommend profess
skills/taste/references/website-improvement-loop.md
- Dangerous shell operationline 60
npx -y chrome-devtools-axi eval "() => ({ canvases: document.querySelectorAll('canvas').length, reduceMotion: matchMedia('(prefers-reduced-motion: reduce)').matches, decorativeText: [...document.querySelectorAll('[aria-hidden=true]')].lengt
skills/user-alignment/references/reading-list.md
- Network accessline 9
- GitHub Spec Kit / spec-driven development — https://github.com/github/spec-kit - Network accessline 10
- GitHub Blog, spec-driven development with AI — https://github.blog/ai-and-ml/generative-ai/spec-driven-development-with-ai-get-started-with-a-new-open-source-toolkit/ - Network accessline 11
- Addy Osmani, “How to write a good spec for AI agents” — https://addyosmani.com/blog/good-spec/ - Network accessline 12
- Claude Code best practices — https://code.claude.com/docs/en/best-practices - Network accessline 13
- OpenAI Codex `AGENTS.md` guide — https://developers.openai.com/codex/guides/agents-md - Network accessline 14
- GitHub Copilot coding agent task best practices — https://docs.github.com/copilot/how-tos/agents/copilot-coding-agent/best-practices-for-using-copilot-to-work-on-tasks - Network accessline 15
- VS Code Copilot context engineering guide — https://code.visualstudio.com/docs/copilot/guides/context-engineering-guide - Network accessline 16
- Cursor rules docs — https://cursor.com/docs/rules - Network accessline 20
- Atlassian, product requirements — https://www.atlassian.com/agile/product-management/requirements - Network accessline 21
- IREB Magazine, requirements elicitation in modern product discovery — https://re-magazine.ireb.org/articles/requirements-elicitation-in-modern-product-discovery - Network accessline 22
- IIBA BABOK, verify requirements — https://www.iiba.org/knowledgehub/business-analysis-body-of-knowledge-babok-guide/7-requirements-analysis-and-design-definition/7-2-verify-requirements/ - Network accessline 23
- IIBA BABOK, validate requirements — https://www.iiba.org/knowledgehub/business-analysis-body-of-knowledge-babok-guide/7-requirements-analysis-and-design-definition/7-3-validate-requirements/ - Network accessline 24
- IIBA, Impact Mapping — https://www.iiba.org/knowledgehub/agile-extension/7-techniques/7-3-impact-mapping/ - Network accessline 25
- Gojko Adzic, Impact Mapping — https://gojko.net/books/impact-mapping/ - Network accessline 26
- Jeff Patton, User Story Mapping — https://jpattonassociates.com/user-story-mapping-presentation/ - Network accessline 27
- The Mom Test — https://inkubator.si/wp-content/uploads/2020/05/The-Mom-Test-by-@robfitz.pdf - Network accessline 28
- IxDF, 5 Whys — https://ixdf.org/literature/topics/5-whys - Network accessline 32
- EARS paper, Mavin et al. — https://dl.acm.org/doi/10.1109/RE.2009.9 - Network accessline 33
- Alistair Mavin, EARS guide — https://alistairmavin.com/ears/ - Network accessline 34
- Agile Alliance, Given-When-Then — https://agilealliance.org/glossary/given-when-then/ - Network accessline 35
- Cucumber Gherkin reference — https://cucumber.netlify.app/docs/gherkin/reference/ - Network accessline 36
- Martin Fowler, Given When Then — https://martinfowler.com/bliki/GivenWhenThen.html - Network accessline 37
- Femmer et al., requirements smells — https://ar5iv.labs.arxiv.org/html/1611.08847 - Network accessline 38
- INCOSE requirements writing summary — https://www.incose.org/wp-content/uploads/legacy/working-groups/requirements-wg/guidetowritingrequirements/incose_rwg_gtwr_v4_summary_sheet.pdf - Network accessline 39
- NASA SWE Handbook, requirements validation — https://swehb.nasa.gov/spaces/SWEHBVD/pages/102695440/SWE-055+-+Requirements+Validation - Network accessline 40
- Scrum Alliance, acceptance criteria — https://resources.scrumalliance.org/Article/need-know-acceptance-criteria - Network accessline 41
- Atlassian, acceptance criteria — https://www.atlassian.com/work-management/project-management/acceptance-criteria - Network accessline 45
- Addy Osmani, “How to write a good spec for AI agents” — https://addyosmani.com/blog/good-spec/ - Network accessline 46
- GitHub Spec Kit, spec-driven development toolkit — https://github.com/github/spec-kit - Network accessline 47
- Human2AI, “AI-Optimized PRD: Requirements Document for AI Agents” — https://thehuman2ai.com/product/guides/prd/ai-optimized - Network accessline 48
- IdeaPlan, “How to Write an AI Product PRD” — https://www.ideaplan.io/blog/how-to-write-ai-product-prd - Network accessline 49
- PRD Agents Framework — https://github.com/vshidlovsky/prd-agents-framework - Network accessline 50
- Jama Software, EARS notation for requirements engineering — https://www.jamasoftware.com/requirements-management-guide/writing-requirements/adopting-the-ears-notation-to-improve-requirements-engineering/ - Network accessline 51
- Delfy, validating PRDs before engineering — https://delfy.app/validate-prd-before-engineering
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.
Declared and executed: 4 facts
- Contacts brew.sh, which SKILL.md, the README and the plugin manifest do not mentiondemo-studio/setup.sh:20High confidence
- Contacts nodejs.org, which SKILL.md, the README and the plugin manifest do not mentiondemo-studio/setup.sh:37High confidence
- Contacts ffmpeg.org, which SKILL.md, the README and the plugin manifest do not mentiondemo-studio/setup.sh:49High confidence
- Contacts python.org, which SKILL.md, the README and the plugin manifest do not mentiondemo-studio/setup.sh:55High confidence
Signal confidence: 86 facts
- Network access in the frontmatter of the SKILL.mddemo-studio/SKILL.md:13Low confidence
- Network access in the frontmatter of the SKILL.mddemo-studio/SKILL.md:14Low confidence
- Network access in the frontmatter of the SKILL.mddemo-studio/SKILL.md:15Low confidence
- Network access in prose of documentationdemo-studio/docs/HOW-IT-WORKS.md:28Low confidence
- Network access in prose of documentationdemo-studio/docs/SETUP.md:27Low confidence
- Network access in prose of documentationdemo-studio/docs/SETUP.md:28Low confidence
- Dangerous shell operation in code of documentationdemo-studio/docs/SETUP.md:42Low confidence
- Network access in prose of documentationdemo-studio/docs/SETUP.md:67Low confidence
- Network access in prose of documentationdemo-studio/docs/SETUP.md:68Low confidence
- Dangerous shell operation in prose of documentationdemo-studio/docs/SETUP.md:72Low confidence
- Executable script in code of a file that runsdemo-studio/scripts/render.sh:1High confidence
- Executable script in code of a file that runsdemo-studio/setup.sh:1High confidence
- Network access in code of a file that runsdemo-studio/setup.sh:18High confidence
- Network access in code of a file that runsdemo-studio/setup.sh:19High confidence
- Network access in code of a file that runsdemo-studio/setup.sh:20High confidence
- Dangerous shell operation in code of a file that runsdemo-studio/setup.sh:35High confidence
- Network access in code of a file that runsdemo-studio/setup.sh:35High confidence
- Dangerous shell operation in code of a file that runsdemo-studio/setup.sh:36High confidence
- Network access in code of a file that runsdemo-studio/setup.sh:36High confidence
- Network access in code of a file that runsdemo-studio/setup.sh:37High confidence
- Dangerous shell operation in code of a file that runsdemo-studio/setup.sh:47High confidence
- Network access in code of a file that runsdemo-studio/setup.sh:47High confidence
- Dangerous shell operation in code of a file that runsdemo-studio/setup.sh:48High confidence
- Network access in code of a file that runsdemo-studio/setup.sh:48High confidence
- Network access in code of a file that runsdemo-studio/setup.sh:49High confidence
- Network access in code of a file that runsdemo-studio/setup.sh:55High confidence
- Executable script in code of a file that runsdemo-studio/templates/build_audio_kit.py:1High confidence
- Executable script in code of a file that runsdemo-studio/templates/make_kit.py:1High confidence
- Network access in prose of the SKILL.mdproduck-feedback/SKILL.md:12Low confidence
- Network access in prose of the SKILL.mdproduck-feedback/SKILL.md:13Low confidence
- Network access in prose of documentationproduck-feedback/references/connect-mcp.md:6Low confidence
- Network access in prose of documentationproduck-feedback/references/connect-mcp.md:11Low confidence
- Access to secrets in prose of documentationproduck-feedback/references/connect-mcp.md:14Low confidence
- Network access in code of documentationproduck-feedback/references/connect-mcp.md:43Low confidence
- Network access in code of documentationproduck-feedback/references/connect-mcp.md:44Low confidence
- Network access in code of documentationproduck-feedback/references/connect-mcp.md:45Low confidence
- Network access in code of documentationproduck-feedback/references/connect-mcp.md:54Low confidence
- Network access in code of documentationproduck-feedback/references/connect-mcp.md:55Low confidence
- Network access in code of documentationproduck-feedback/references/connect-mcp.md:57Low confidence
- Network access in code of documentationproduck-feedback/references/connect-mcp.md:58Low confidence
- Network access in code of documentationproduck-feedback/references/connect-mcp.md:59Low confidence
- Network access in code of documentationproduck-feedback/references/connect-mcp.md:69Low confidence
- Access to secrets in code of documentation: a variable, placeholder or call, not a stored valueproduck-feedback/references/connect-mcp.md:69Low confidence
- Network access in code of documentationproduck-feedback/references/connect-mcp.md:70Low confidence
- Network access in code of documentationproduck-feedback/references/connect-mcp.md:71Low confidence
- Network access in code of documentationproduck-feedback/references/connect-mcp.md:77Low confidence
- Network access in code of the SKILL.mdtaste/SKILL.md:133High confidence
- Network access in prose of documentationtaste/references/taste-principles.md:7Low confidence
- Network access in prose of documentationtaste/references/taste-principles.md:8Low confidence
- Network access in prose of documentationtaste/references/taste-principles.md:9Low confidence
and 36 more
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Native | Manifest .claude-plugin/marketplace.json | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md skills/demo-studio/SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md skills/demo-studio/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md skills/demo-studio/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md skills/demo-studio/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md skills/demo-studio/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.