Agent skill

Bm Skill Builder

by buildermethods in buildermethods/bm-skills

Build a new agent skill (or restructure an existing one) following Builder Methods conventions.

MITAuto-check passedAgent Workflows

Install Bm Skill Builder

skills CLI
$ npx skills add buildermethods/bm-skills --skill bm-skill-builder -a claude-code

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

GitHub CLI
$ gh skill install buildermethods/bm-skills bm-skill-builder --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/buildermethods/bm-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/bm-skill-builder .claude/skills/bm-skill-builder && 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
bm-skill-builder
GitHub stars
146
Token cost
~735 tokens
SKILL.md length
375 words
Files
9
Skills in repo
4
Repo updated
First seen
Licence
MIT

At a glance

Build a new agent skill (or restructure an existing one) following Builder Methods conventions.

  • Works in 6 steps: Understand the process —… → Interview the user — steps/interview.md:… → Design the shape — steps/design.md:… → …
  • The user wants to create a skill
  • SKILL.md covers The process and Hard rules
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Bm Skill Builder is an agent skill from buildermethods/bm-skills. Build a new agent skill (or restructure an existing one) following Builder Methods conventions. Use when the user wants to create a skill, turn a repeatable process into a skill, or restructure a skill that has outgrown its shape — "create a skill", "make this a skill", "turn my proposal process into a skill", "restructure this skill".

Its SKILL.md is about 740 tokens, which your agent loads only when the skill is triggered. The skill folder holds 10 other files (for example `reference/conventions.md`, `reference/example-structures.md` and `steps/build.md`).

It sits in Agent Workflows, covering Skill authoring. The repository describes itself as: A collection of public open-source tools for builders, by Brian Casel @ Builder Methods (buildermethods.com). The licence is MIT.

When your agent uses it

  • The user wants to create a skill
  • Turn a repeatable process into a skill
  • Restructure a skill that has outgrown its shape — create a skill
  • Make this a skill

Example prompts

  • “create a skill”
  • “make this a skill”
  • “turn my proposal process into a skill”
  • “/bm-skill-builder”

Requirements

  • Python 3

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Understand the process — steps/understand.md: ask the user to describe the process the skill is for, then infer what you can — job…
  2. Interview the user — steps/interview.md: design the skill with the user — description, name, inputs (if any), its own interview (if any)…
  3. Design the shape — steps/design.md: simple or structured, per the conventions.
  4. Build it — steps/build.md: write the files against the conventions checklist.
  5. Save it — steps/save.md: ask where the skill should live — this repo's .agents/skills/, global ~/.agents/skills/, or a .claude alternate…
  6. Verify & hand off — steps/verify.md: run it from its saved location, then teach the user the improvement loop.

What it can do on your machine

Read from SKILL.md and the folder at commit b6b6a72. 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

    No scripts in the folder and no shell commands in SKILL.md.

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

  • Network

    No URLs in SKILL.md.

    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

Bm Skill Builder loads about 735 tokens when it runs. Until then it costs about 89 tokens; SKILL.md has 375 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~89
When it runs · the whole SKILL.md, loaded when a task matches
~735

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from buildermethods/bm-skills at commit b6b6a72, republished under its MIT licence (© buildermethods). 375 words, ~735 tokens.

Download SKILL.mdSave it as .claude/skills/bm-skill-builder/SKILL.md (or your agent's skills folder). This skill also uses 8 other files; get the full folder from GitHub.
name
bm-skill-builder
description
Build a new agent skill (or restructure an existing one) following Builder Methods conventions. Use when the user wants to create a skill, turn a repeatable process into a skill, or restructure a skill that has outgrown its shape — "create a skill", "make this a skill", "turn my proposal process into a skill", "restructure this skill".

bm-skill-builder

Turns a repeatable process into a well-built agent skill: instructions in plain markdown and folders, portable across any agent harness. Works for brand-new skills and for restructuring existing ones that have outgrown a single SKILL.md.

The process

  1. Understand the process — steps/understand.md: ask the user to describe the process the skill is for, then infer what you can — job, inputs, artifact, raw material.
  2. Interview the user — steps/interview.md: design the skill with the user — description, name, inputs (if any), its own interview (if any), realistic examples (if applicable), and the step plan. Recommend-then-confirm format throughout.
  3. Design the shape — steps/design.md: simple or structured, per the conventions.
  4. Build it — steps/build.md: write the files against the conventions checklist.
  5. Save it — steps/save.md: ask where the skill should live — this repo's .agents/skills/, global ~/.agents/skills/, or a .claude alternate — and place it there.
  6. Verify & hand off — steps/verify.md: run it from its saved location, then teach the user the improvement loop.

Hard rules

  • At the start of every invocation of a multi-step skill, present a simple numbered overview of the process with one very short sentence per item, then immediately begin the first step without asking permission or pausing.
  • A skill's instructions are plain markdown. SKILL.md and every instruction file (steps, phases, shared, reference docs) are .md — no formats a harness has to interpret. Bundled scripts/ and reference material can be whatever the job needs (a Python script, a JSON schema, a template file). Nothing harness-specific in the skill's core — it must work anywhere.
  • Start as simple as the process allows. Structure (steps/, phases/, shared/) must be earned by real complexity, never added on spec.
  • Order lives in the orchestrator, never in the steps. SKILL.md (or a phase's own file) carries the numbering and points at each step file; step files are topic-named, order-agnostic, and say nothing about their position in the sequence.
  • Removal means gone. When removing or reversing anything in a skill, delete it and every reference to it, as if it never existed — no "don't do X" replacements, notes about what changed, legacy fallbacks, or leftover examples. A skill describes only its current process.
  • The full conventions live in reference/conventions.md — read them before designing, and check the finished skill against them before handing off.

© buildermethods, 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 8 other files in skills/bm-skill-builder of buildermethods/bm-skills.

  • SKILL.md
  • reference/conventions.md
  • reference/example-structures.md
  • steps/build.md
  • steps/design.md
  • steps/interview.md
  • steps/save.md
  • steps/understand.md
  • steps/verify.md

Open the folder on GitHubat commit b6b6a72

Compare with similar skills

Bm Skill Builder 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.

Bm Skill Builder compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Bm Skill Builder this skillbuildermethods/bm-skills146—~735Automated safety check: PassMIT
Skill CreatorAzure/azqr79589 repos~8.2kAutomated safety check: PassApache-2.0
Claude Code Skill Developer Guidediet103/claude-code-infrastructure-showcase10k11 repos~3.5kAutomated safety check: PassMIT
Darwin Skill Optimizeralchaincyf/darwin-skill6.2k1 repos~4.7kAutomated safety check: PassMIT
Claude Code Command Developmentanthropics/claude-plugins-official38k10 repos~4.8kAutomated safety check: PassApache-2.0
Claude Code Plugin Structureanthropics/claude-plugins-official38k10 repos~3.4kAutomated safety check: PassApache-2.0

Similar skills

  • Skill Creator

    Azure/azqr

    Official

    Create new skills, modify and improve existing skills, and measure skill performance.

    795 GitHub starsUsed in 89 repos~8.2k tokens
    Agent WorkflowsAuto-check passed
  • Claude Code Skill Developer Guide

    diet103/claude-code-infrastructure-showcase

    A guide to creating and managing Claude Code skills with auto-activation: skill-rules.json triggers, hooks, enforcement levels, YAML frontmatter and progressive disclosure.

    10k GitHub starsUsed in 11 repos~3.5k tokens
    Agent WorkflowsAuto-check passed
  • Darwin Skill Optimizer

    alchaincyf/darwin-skill

    Scores SKILL.md files on a nine-dimension rubric, then improves them in a keep-or-revert loop with independent judge agents, test prompts, git history and human checkpoints.

    6.2k GitHub starsUsed in 1 repo~4.7k tokens
    Agent WorkflowsAuto-check passed
  • Claude Code Command Development

    anthropics/claude-plugins-official

    Official

    Explains how to write Claude Code slash commands: Markdown files with YAML frontmatter, arguments, file references, bash context and interactive prompts.

    38k GitHub starsUsed in 10 repos~4.8k tokens
    Agent WorkflowsAuto-check passed
  • Claude Code Plugin Structure

    anthropics/claude-plugins-official

    Official

    Explains the directory layout, plugin.json manifest and component organization of a Claude Code plugin, including auto-discovery and portable paths.

    38k GitHub starsUsed in 10 repos~3.4k tokens
    Agent WorkflowsAuto-check passed
  • Skill Release Gate

    rohitg00/ai-engineering-from-scratch

    Evaluates an Agent Skill bundle before release for structure, trigger quality, artifact improvement, script correctness, safety, installed-tree integrity and host portability.

    66k GitHub stars~1k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

More from buildermethods/bm-skills

  • Bm Favicon Creator

    buildermethods/bm-skills

    Generate a complete favicon set (SVG, PNGs, multi-resolution .ico, Apple touch icon) from a Lucide icon (default) or another source SVG, then wire the favicon meta tags into the codebase.

    146 GitHub stars~2.4k tokensUpdated today
    Auto-check passed
  • Bm Design System

    buildermethods/bm-skills

    Guides you through creating and implementing a design system for your application.

    146 GitHub stars~6.5k tokensUpdated today
    Auto-check passed
  • Bm Prd Creator

    buildermethods/bm-skills

    A skill your agent uses when the user wants to create a Product Requirements Document (PRD) for a new app, feature, or project.

    146 GitHub stars~1.5k tokensUpdated today
    Auto-check passed

Categories

Questions about Bm Skill Builder

What does Bm Skill Builder do?

Build a new agent skill (or restructure an existing one) following Builder Methods conventions. Bm Skill Builder is an agent skill from buildermethods/bm-skills. Build a new agent skill (or restructure an existing one) following Builder Methods conventions.

When should I use Bm Skill Builder?

Bm Skill Builder fits situations like: the user wants to create a skill; turn a repeatable process into a skill; restructure a skill that has outgrown its shape — create a skill; make this a skill.

How do I install Bm Skill Builder in Claude Code?

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

How do I install Bm Skill Builder in Codex?

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

Can I use Bm Skill Builder 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 buildermethods/bm-skills --skill bm-skill-builder -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/bm-skill-builder, .gemini/skills/bm-skill-builder, .github/skills/bm-skill-builder and .opencode/skills/bm-skill-builder in your project.

What does Bm Skill Builder need to run?

SKILL.md names no scripts, command-line tools or credentials: Bm Skill Builder is instructions for the agent only. Our summary lists: Python 3.

Does Bm Skill Builder access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Bm Skill Builder 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. Review the folder before installing.

What licence does Bm Skill Builder use?

Bm Skill Builder 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 Bm Skill Builder use?

About 735 tokens (SKILL.md is roughly 2.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Bm Skill Builder?

Skills that share tags, products or a category with Bm Skill Builder: Skill Creator (Azure/azqr, 795 stars), Claude Code Skill Developer Guide (diet103/claude-code-infrastructure-showcase, 10k stars), Darwin Skill Optimizer (alchaincyf/darwin-skill, 6.2k stars) and Claude Code Command Development (anthropics/claude-plugins-official, 38k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Bm Skill Builder?

buildermethods (a GitHub organization) maintains it in buildermethods/bm-skills, which has 146 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on October 8, 2026.

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