Agent skill

Cap Feature Building Workflow

by CapSoftware in CapSoftware/Cap

Builds a Cap feature in an isolated Git worktree with disposable dev resources, verification, a recorded demo and a neutral pull request, started with /building.

Custom licenceAuto-check: warningsDevelopment

Install Cap Feature Building Workflow

The automated check flagged lines worth reading first. See the safety section below.

skills CLI
$ npx skills add CapSoftware/Cap --skill building -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install CapSoftware/Cap building --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/CapSoftware/Cap.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/building .claude/skills/building && rm -rf skills-src

Use ~/.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/

Facts

Skill name
building
GitHub stars
23k
Token cost
~2.5k tokens
SKILL.md length
1,314 words
Files
15 (incl. scripts, references)
Skills in repo
3
Repo updated
First seen
Licence
Custom licence

At a glance

Builds a Cap feature in an isolated Git worktree with disposable dev resources, verification, a recorded demo and a neutral pull request, started with /building.

  • Building a Cap feature end to end and opening a pull request
  • SKILL.md covers Publication privacy, Prepare and resume, Implement and verify and Publish, plus 1 more section
  • Runs JavaScript scripts from its folder; calls npm, node and gh
  • Resuming an existing building session

What it does

Typing `/building` in Cursor or Claude Code, or `$building` in Codex, authorizes the agent to implement the feature in a new worktree, provision disposable development resources such as PlanetScale development branches, run verification, record and upload a demonstration to your Cap folder and open a pull request. Merging and production deployment stay separate, and the original checkout, branches, running services and recordings are left alone. The helper is `scripts/building.mjs`, installed with `npm ci` when its dependencies are missing.

A privacy section requires neutral GitHub metadata: branch names use a `building/` prefix with conventional commit titles, and nothing in commits, PR text, comments or demo titles may mention AI tools, model names or automated authorship. Secrets and real people's personal data must never appear in committed content, PR text, attachments or demos, so the agent uses synthetic fixtures and example domains. Reference files cover desktop, editors, environment and recording, and ordinary coding requests do not trigger this workflow.

When your agent uses it

  • Building a Cap feature end to end and opening a pull request
  • Resuming an existing building session
  • Recording a feature demonstration to attach to a PR

Example prompts

  • “/building add a keyboard shortcut for pausing a recording.”
  • “Resume my building session for the export dialog and finish the PR.”
  • “Use building to implement the thumbnail change in a fresh worktree with a PlanetScale branch.”

Requirements

  • Git, Node and npm
  • A PlanetScale account for development branches
  • A Cap account for the recorded demos
  • GitHub access to open pull requests

What it can do on your machine

Read from SKILL.md and the folder at commit d327051. 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 7 files in scripts/ (JavaScript), which the agent can run.

    Shell commands in SKILL.md call:

    • npm
    • node
    • gh

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use npm and gh, 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

Cap Feature Building Workflow loads about 2.5k tokens when it runs, and up to ~6.9k if it reads all its reference files. Until then it costs about 85 tokens; SKILL.md has 1,314 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~85
When it runs · the whole SKILL.md, loaded when a task matches
~2.5k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~6.9k

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: warnings

The automated check found patterns that need a careful read before installing.

  • WarningMentions a credentials file (SSH keys, cloud or package-manager tokens)SKILL.md:40
    browsing: each session gets a separate Chrome profile, preventing cookies and local storage from colliding across ports

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

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 1,314 words (~2,482 tokens).

“Use /building in Cursor or Claude Code, or $building in Codex. Each invocation authorizes implementing the feature in a new worktree, provisioning its disposable development resources, running verification, recording and uploading a demonstration into the user's PR's Cap folder, and…”

— opening of SKILL.md by CapSoftware, Custom licence
name
building

Read the full SKILL.md on GitHub

Files

SKILL.md and 14 other files (scripts, references) in .agents/skills/building of CapSoftware/Cap.

  • SKILL.md
  • agents/openai.yaml
  • package-lock.json
  • package.json
  • references/desktop.md
  • references/editors.md
  • references/environment.md
  • references/recording.md
  • scripts/building.mjs
  • scripts/capture.mjs
  • scripts/core.mjs
  • scripts/core.test.mjs
  • scripts/database.mjs
  • scripts/lifecycle.test.mjs
  • scripts/preview.mjs

Open the folder on GitHubat commit d327051

Compare with similar skills

Cap Feature Building Workflow 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.

Cap Feature Building Workflow compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Cap Feature Building Workflow this skillCapSoftware/Cap23k—~2.5kAutomated safety check: WarnCustom licence
Finishing a Development Branchobra/superpowers296k5 repos~1.9kAutomated safety check: PassMIT
Pre-Release PR Triagejamiepine/voicebox57k—~3.1kAutomated safety check: PassMIT
Clean Complete Branchesjtenniswood/espcontrol1.1k—~820Automated safety check: PassCustom licence
BackportDependencyTrack/frontend172—~1.9kAutomated safety check: NotesApache-2.0
Swampswamp-club/swamp642—~1.9kAutomated safety check: PassCustom licence

Similar skills

  • Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.

    296k GitHub starsUsed in 5 repos~1.9k tokens
    DevelopmentAuto-check passed
  • Pre-Release PR Triage

    jamiepine/voicebox

    Sorts a backlog of open pull requests into must-merge, candidate, superseded and deferred, writes a triage doc and works the merge loop before a release.

    57k GitHub stars~3.1k tokensUpdated today
    DevelopmentAuto-check passed
  • Clean Complete Branches

    jtenniswood/espcontrol

    Clean up completed Git branches and worktrees for this repository both locally and on GitHub.

    1.1k GitHub stars~820 tokensUpdated today
    DevelopmentAuto-check passed
  • Backport

    DependencyTrack/frontend

    Backports a merged pull request from main onto a patch-release branch, e.g.

    172 GitHub stars~1.9k tokensUpdated 2 days ago
    DevelopmentAuto-check: notes
  • Swamp

    swamp-club/swamp

    Swamp CLI — create and run models, build and validate workflows, query and manage data, store and retrieve vault secrets, develop and publish extensions, initialize repos, run reports, file issues…

    642 GitHub stars~1.9k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Official

    Dev-first branching model for the Squad project: feature work branches from dev, issue branches follow a naming rule and parallel issues use git worktrees.

    1.4k GitHub starsUsed in 4 repos~1.5k tokens
    DevelopmentAuto-check passed

More from CapSoftware/Cap

  • Operates Cap, the screen recording and sharing tool, through its local MCP tools or cap command instead of browser automation: library, transcripts, comments and sharing.

    23k GitHub stars~1.7k tokensUpdated today
    Auto-check passed
  • Turns any URL into a short cinematic product-demo video on macOS, scouting the page, recording it with virtual input, then treating the clip with Cap's 3D camera and music.

    23k GitHub stars~2.4k tokensUpdated today
    Auto-check passed

Works with

Questions about Cap Feature Building Workflow

What does Cap Feature Building Workflow do?

Builds a Cap feature in an isolated Git worktree with disposable dev resources, verification, a recorded demo and a neutral pull request, started with /building. Typing `/building` in Cursor or Claude Code, or `$building` in Codex, authorizes the agent to implement the feature in a new worktree, provision disposable development resources such as PlanetScale development branches, run verification, record and upload a demonstration to your Cap folder and open a pull request. Merging and production deployment stay separate, and the original checkout, branches, running services and recordings are left alone.

When should I use Cap Feature Building Workflow?

Cap Feature Building Workflow fits situations like: building a Cap feature end to end and opening a pull request; resuming an existing building session; recording a feature demonstration to attach to a PR.

How do I install Cap Feature Building Workflow in Claude Code?

Run `npx skills add CapSoftware/Cap --skill building -a claude-code`. Or copy the skill folder (.agents/skills/building in CapSoftware/Cap) into .claude/skills/building in your project. Claude Code loads it when a task matches its description.

How do I install Cap Feature Building Workflow in Codex?

Run `npx skills add CapSoftware/Cap --skill building -a codex`. Or copy the skill folder (.agents/skills/building in CapSoftware/Cap) into .agents/skills/building in your project. Codex loads it when a task matches its description.

Can I use Cap Feature Building Workflow 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 CapSoftware/Cap --skill building -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/building, .gemini/skills/building, .github/skills/building and .opencode/skills/building in your project.

What does Cap Feature Building Workflow need to run?

Going by SKILL.md and its folder, Cap Feature Building Workflow needs JavaScript for the scripts in its folder and the command-line tools its instructions call (npm, node and gh). Our summary lists: Git, Node and npm; A PlanetScale account for development branches; A Cap account for the recorded demos; GitHub access to open pull requests.

Does Cap Feature Building Workflow access the network?

SKILL.md contains no URLs. Its commands use npm and gh, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Cap Feature Building Workflow safe to install?

Our automated static check of SKILL.md flagged 1 warning(s): mentions a credentials file (ssh keys, cloud or package-manager tokens). Read the flagged lines before installing; the check is not a guarantee either way. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Cap Feature Building Workflow use?

Cap Feature Building Workflow has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Cap Feature Building Workflow use?

About 2.5k tokens (SKILL.md is roughly 9.9k 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 4.5k tokens, read only when the agent opens those files.

What are the alternatives to Cap Feature Building Workflow?

Skills that share tags, products or a category with Cap Feature Building Workflow: Finishing a Development Branch (obra/superpowers, 296k stars), Pre-Release PR Triage (jamiepine/voicebox, 57k stars), Clean Complete Branches (jtenniswood/espcontrol, 1.1k stars) and Backport (DependencyTrack/frontend, 172 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Cap Feature Building Workflow?

CapSoftware (a GitHub organization) maintains it in CapSoftware/Cap, which has 23,093 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on October 7, 2026.

Source: CapSoftware/Cap on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.