Trellis Session Insight
mindfold-ai/Trellis
Reach into past AI conversation history through the trellis mem CLI.
Build a throwaway prototype to answer an unresolved product behavior or visual question before implementation.
Install Spec Prototype
$ npx skills add leo-kuang-ai/spec-first --skill spec-prototype -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install leo-kuang-ai/spec-first spec-prototype --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/leo-kuang-ai/spec-first.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/spec-prototype .claude/skills/spec-prototype && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "spec-prototype" agent skill from https://github.com/leo-kuang-ai/spec-first/tree/master/skills/spec-prototype into .claude/skills/spec-prototype/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "spec-prototype", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/leo-kuang-ai/spec-first/tree/master/skills/spec-prototypeType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add leo-kuang-ai/spec-first --skill spec-prototype -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install leo-kuang-ai/spec-first spec-prototype --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/leo-kuang-ai/spec-first.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/spec-prototype .agents/skills/spec-prototype && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "spec-prototype" agent skill from https://github.com/leo-kuang-ai/spec-first/tree/master/skills/spec-prototype into .agents/skills/spec-prototype/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "spec-prototype", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add leo-kuang-ai/spec-first --skill spec-prototype -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install leo-kuang-ai/spec-first spec-prototype --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/leo-kuang-ai/spec-first.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/spec-prototype .cursor/skills/spec-prototype && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "spec-prototype" agent skill from https://github.com/leo-kuang-ai/spec-first/tree/master/skills/spec-prototype into .cursor/skills/spec-prototype/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "spec-prototype", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/leo-kuang-ai/spec-first.git --path skills/spec-prototype--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add leo-kuang-ai/spec-first --skill spec-prototype -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install leo-kuang-ai/spec-first spec-prototype --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/leo-kuang-ai/spec-first.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/spec-prototype .gemini/skills/spec-prototype && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "spec-prototype" agent skill from https://github.com/leo-kuang-ai/spec-first/tree/master/skills/spec-prototype into .gemini/skills/spec-prototype/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "spec-prototype", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install leo-kuang-ai/spec-first spec-prototypeInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add leo-kuang-ai/spec-first --skill spec-prototype -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/leo-kuang-ai/spec-first.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/spec-prototype .github/skills/spec-prototype && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "spec-prototype" agent skill from https://github.com/leo-kuang-ai/spec-first/tree/master/skills/spec-prototype into .github/skills/spec-prototype/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "spec-prototype", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add leo-kuang-ai/spec-first --skill spec-prototype -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install leo-kuang-ai/spec-first spec-prototype --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/leo-kuang-ai/spec-first.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/spec-prototype .opencode/skills/spec-prototype && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "spec-prototype" agent skill from https://github.com/leo-kuang-ai/spec-first/tree/master/skills/spec-prototype into .opencode/skills/spec-prototype/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "spec-prototype", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
spec-prototype- GitHub stars
- 107
- Token cost
- ~1k tokens
- SKILL.md length
- 495 words
- Files
- 12 (incl. scripts, references)
- Skills in repo
- 35
- Repo updated
- First seen
- Licence
- MIT
At a glance
Build a throwaway prototype to answer an unresolved product behavior or visual question before implementation.
- The question needs a runnable artifact and a human must experience it
- SKILL.md covers Run-Local Phases, Boundaries and Output
- Runs Shell and JavaScript scripts from its folder; calls git
- Do not use for product discovery (route those to spec-ideate
What it does
Spec Prototype is an agent skill from leo-kuang-ai/spec-first. Build a throwaway prototype to answer an unresolved product behavior or visual question before implementation. Use when the question needs a runnable artifact and a human must experience it; do not use for product discovery (route those to spec-ideate or spec-brainstorm), routine polish, production implementation, or unattended runs.
Its SKILL.md is about 1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 17 other files, including scripts and reference files (for example `evals/cases/discovery-routes-out.yaml`, `evals/cases/go-ahead-before-build.yaml` and `evals/cases/headless-blocked.yaml`).
It sits in Development, covering Prototyping and Brainstorming. The repository describes itself as: 仓库原生 AI Coding Harness —— 把一次性 AI 对话变成可治理、可验证、可沉淀的工程闭环 · spec-first.cn. The licence is MIT.
When your agent uses it
- The question needs a runnable artifact and a human must experience it
- Do not use for product discovery (route those to spec-ideate
- Spec-brainstorm)
- Production implementation
Example prompts
- “/spec-prototype”
Requirements
- Node.js
- A Bash shell
What it can do on your machine
Read from SKILL.md and the folder at commit 74655dc. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 1 file in scripts/ (Shell and JavaScript), which the agent can run.
Shell commands in SKILL.md call:
git
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Spec Prototype loads about 1k tokens when it runs, and up to ~1.7k if it reads all its reference files. Until then it costs about 88 tokens; SKILL.md has 495 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
The full file from leo-kuang-ai/spec-first at commit 74655dc, republished under its MIT licence (© leo-kuang-ai). 495 words, ~1,022 tokens.
Download SKILL.mdSave it as
.claude/skills/spec-prototype/SKILL.md (or your agent's skills folder). This skill also uses 11 other files; get the full folder from GitHub.- name
- spec-prototype
- description
- Build a throwaway prototype to answer an unresolved product behavior or visual question before implementation. Use when the question needs a runnable artifact and a human must experience it; do not use for product discovery (route those to spec-ideate or spec-brainstorm), routine polish, production implementation, or unattended runs.
- argument-hint
- [question, brainstorm path, or plan path]
Prototype
Build the smallest runnable artifact that can honestly answer the named question, then hand the decision to the person who will use it.
Do not fake the dimension being tested. Modality, fidelity, and medium follow from that rule. A behavior question is settled by driving the artifact; a visual question is settled by seeing the rendered result. For visual questions, read references/craft-floor.md; a behavior question does not load that floor.
This is a throwaway exploration, never the production implementation. The web is the default substrate regardless of the product stack. Do not start when there is no human available to experience the result, when the question is undefined, or in unattended/pipeline mode; return blocked-human-experience-required. A direction-exploration request ("explore directions", "what should we build next") is product discovery, not an undefined prototype question: name spec-ideate or spec-brainstorm as the destination and route out instead of interviewing for a testable question.
Run-Local Phases
These labels describe the current invocation and its allowed exit; they are not a persisted workflow state machine.
| Phase | Allowed action and user-visible output | Exit condition |
|---|---|---|
entry | Resolve the named question and current owner. | Question is bounded enough to scope, otherwise unresolved. |
scoping | Choose behavior/visual modality, throwaway root, options and limitations. | Present the exact prototype question and requested side effects. |
awaiting-go-ahead | Ask before creating files or starting a server. | Explicit go-ahead, or abandoned. |
building | Create only the throwaway artifact; do not write production source. | Runnable focused artifact exists, or unresolved. |
preview-running | Serve only on explicit loopback and return the local URL. | Human can inspect it, then stop or move to decision. |
awaiting-human-decision | Report options and observed limitations without inferring a winner. | Human selects a direction, leaves it unresolved, or abandons it. |
decided | Write decisions.md and hand the decision to spec-brainstorm or spec-plan. | Decision artifact is written from the human choice. |
unresolved | Preserve the question, artifact path and limitation; do not write decisions.md. | Return to the current product owner. |
abandoned | Stop owned preview resources and report that no decision was recorded. | End without production write-back. |
Show full SKILL.md (159 more words)Show less
Boundaries
- Use an isolated directory under
.context/compound-engineering/ce-prototype/<date>-<slug>/only whengit check-ignoreand ownership/symlink checks pass; otherwise use a private OS temporary root. Never delete a kept prototype. - Ask for a go-ahead before creating or serving the artifact. Keep credentials out of files, arguments, logs, and handoff artifacts.
- Preview may bind only to
127.0.0.1or::1. CSP blocks external loads/connects; a stop request signals a process only after its PID, root, script and instance identity all match, otherwise it returns a blocked reason. - After the user experiences the artifact, write
decisions.mdonly when a choice is actually made. Include the question, prototype path, winner, rejected options, adjustments, and open questions. - On apply, hand off to the existing
spec-brainstormorspec-planowner. Do not createspec-proof, upload an external document, or write production code.
Output
Return the artifact path, the human decision state, the next owner, and limitations. A passing local check is not a user decision or a production outcome.
© leo-kuang-ai, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 11 other files (scripts, references) in skills/spec-prototype of leo-kuang-ai/spec-first.
- SKILL.md
- evals/cases/discovery-routes-out.yaml
- evals/cases/go-ahead-before-build.yaml
- evals/cases/headless-blocked.yaml
- evals/cases/undefined-question-gate.yaml
- evals/eval.yaml
- evals/fixtures/scripts/asks-a-question.sh
- evals/fixtures/scripts/routes-to-discovery.sh
- references/craft-floor.md
- references/preview.md
- references/write-back.md
- scripts/light-webserver.js
Open the folder on GitHubat commit 74655dc
Compare with similar skills
Spec Prototype next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Spec Prototype this skillleo-kuang-ai/spec-first | 107 | — | ~1k | Automated safety check: Pass | MIT | |
| Trellis Session Insightmindfold-ai/Trellis | 15k | 4 repos | ~1.7k | Automated safety check: Pass | AGPL-3.0 | |
| Compound Engineering PrototypeEveryInc/compound-engineering-plugin | 25k | — | ~1.9k | Automated safety check: Pass | MIT | |
| Audit Flowzebbern/claude-code-guide | 4.7k | — | ~4.2k | Automated safety check: Pass | MIT | |
| Context FieldsNeoVertex1/context-field | 147 | — | ~1.3k | Automated safety check: Pass | None | |
| Grounding A Designandrew-blake/melcloudhome | 142 | — | ~1.1k | Automated safety check: Pass | MIT |
Similar skills
Compound Engineering Prototype
EveryInc/compound-engineering-plugin
Builds a throwaway prototype at just the fidelity needed to settle a specific how-it-should-work-or-feel question, before committing to an approach other work will treat as fixed.
Audit Flow
zebbern/claude-code-guide
Interactive system flow tracing across CODE, API, AUTH, DATA, NETWORK layers with SQLite persistence and Mermaid export.
Context Fields
NeoVertex1/context-field
Apply cognitive constraints that reshape thinking. An agent skill from NeoVertex1/context-field.
Grounding A Design
andrew-blake/melcloudhome
A skill your agent uses when about to propose, brainstorm, review or revise a design, fix approach or plan for a feature or behaviour change in this repo, including "brief" or "quick" design…
Work Issue
joesaby/astro-mermaid
End-to-end workflow for resolving a GitHub issue in astro-mermaid — triages complexity, then runs brainstorm → TDD → implement → docs/spec → code review at the right depth.
More from leo-kuang-ai/spec-first
All 35 skills in this repoSpec App Consistency Audit
leo-kuang-ai/spec-first
Audit mobile App PRD/Figma/local-source consistency across page routes, KMP/Clean Architecture, components, analytics, i18n, engineering quality, and industry lenses before runtime validation; use…
Spec Handoff
leo-kuang-ai/spec-first
Create a durable cross-session handoff or resume from a user-selected continuity source.
Spec Pov
leo-kuang-ai/spec-first
Give a decisive, project-grounded verdict on an external input — judged against the current project, not in the abstract.
Spec Resolve PR Feedback
leo-kuang-ai/spec-first
Resolve PR review feedback by evaluating validity and fixing issues with conflict-aware resolver dispatch.
Spec Riffrec Feedback Analysis
leo-kuang-ai/spec-first
Analyze explicit Riffrec product-feedback captures, including riffrec-.zip, the Riffrec session.json + events.json + recording.webm + voice.webm bundle, or media/notes the user identifies as a…
Spec Compound
leo-kuang-ai/spec-first
Document a recently solved problem or durable project vocabulary in docs/solutions/ or CONCEPTS.md.
Related
Questions about Spec Prototype
What does Spec Prototype do?
Build a throwaway prototype to answer an unresolved product behavior or visual question before implementation. Spec Prototype is an agent skill from leo-kuang-ai/spec-first. Build a throwaway prototype to answer an unresolved product behavior or visual question before implementation.
When should I use Spec Prototype?
Spec Prototype fits situations like: the question needs a runnable artifact and a human must experience it; do not use for product discovery (route those to spec-ideate; spec-brainstorm); production implementation.
How do I install Spec Prototype in Claude Code?
Run `npx skills add leo-kuang-ai/spec-first --skill spec-prototype -a claude-code`. Or copy the skill folder (skills/spec-prototype in leo-kuang-ai/spec-first) into .claude/skills/spec-prototype in your project. Claude Code loads it when a task matches its description.
How do I install Spec Prototype in Codex?
Run `npx skills add leo-kuang-ai/spec-first --skill spec-prototype -a codex`. Or copy the skill folder (skills/spec-prototype in leo-kuang-ai/spec-first) into .agents/skills/spec-prototype in your project. Codex loads it when a task matches its description.
Can I use Spec Prototype in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add leo-kuang-ai/spec-first --skill spec-prototype -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/spec-prototype, .gemini/skills/spec-prototype, .github/skills/spec-prototype and .opencode/skills/spec-prototype in your project.
What does Spec Prototype need to run?
Going by SKILL.md and its folder, Spec Prototype needs a shell and JavaScript for the scripts in its folder and the command-line tools its instructions call (git). Our summary lists: Node.js; A Bash shell.
Does Spec Prototype access the network?
SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Spec Prototype safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Spec Prototype use?
Spec Prototype is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Spec Prototype use?
About 1k tokens (SKILL.md is roughly 4.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 645 tokens, read only when the agent opens those files.
What are the alternatives to Spec Prototype?
Skills that share tags, products or a category with Spec Prototype: Trellis Session Insight (mindfold-ai/Trellis, 15k stars), Compound Engineering Prototype (EveryInc/compound-engineering-plugin, 25k stars), Audit Flow (zebbern/claude-code-guide, 4.7k stars) and Context Fields (NeoVertex1/context-field, 147 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Spec Prototype?
leo-kuang-ai (a GitHub user) maintains it in leo-kuang-ai/spec-first, which has 107 GitHub stars. The repository holds 35 skills in this directory. The repository was last updated on October 8, 2026.
Source: leo-kuang-ai/spec-first on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.