跳到正文
cccskills
免费在 GitHub 公开

bmad-toolsmith

Build and maintain BMad skills, agents, and modules through a guided conversation. Turn prompts or session logs into reusable skills, review existing tools, and prepare modules for distribution, with approval before files are written.

中文简介正在准备中。当前显示英语简介。

原文查看原文说明

Smithy the Toolsmith builds and maintains BMad skills, agents and modules. Use when the user asks for Smithy or says "build a skill", "make an agent", "scaffold a skill", "turn my session logs into a skill", "fix this skill", "convert this prompt to a skill", "review this skill", "optimize this skill", "cut this skill down", "make this skill BMad compliant", "package a module", "validate my module" or "migrate my old module". Not for running evals (`bmad-eval`) or overriding an installed skill (`bmad-customize`).

查看安装方法

适用场景

  • Create a skill from a prompt or session logs
  • Build an agent with a defined persona
  • Fix or review an existing skill
  • Package, validate, or migrate a module

包含的文件(97)

  • SKILL.md3.6 KB
  • approaches/eval-first.md1.4 KB
  • approaches/eval-loop.md2.7 KB
  • approaches/from-logs.md1.8 KB
  • approaches/lean.md1.9 KB
  • approaches/scaffold.md1.3 KB
  • approaches/skill-creator-loop.md1.3 KB
  • bmod.toml118 B
  • canon.md10.0 KB
  • customize.toml4.8 KB
  • discover.md7.0 KB
  • ecosystem.md1.7 KB
  • evals/triggers.json3.3 KB
  • lenses/lens-architecture.md2.9 KB
  • lenses/lens-contract.md1.3 KB
  • lenses/lens-customization.md2.4 KB
  • lenses/lens-determinism.md1.8 KB
  • lenses/lens-leanness.md2.6 KB
  • lenses/lens-trigger.md2.4 KB
  • lenses/standards.md5.2 KB
  • modes/convert.md2.4 KB
  • modes/cut-roles.md3.0 KB
  • modes/cut.md3.5 KB
  • modes/edit.md1.4 KB
  • modes/migrate.md3.8 KB
  • modes/package.md2.7 KB
  • modes/review.md1.6 KB
  • modes/validate.md1.9 KB
  • scripts/count_tokens.py3.6 KB
  • scripts/cut_check.py5.1 KB
  • scripts/init_skill.py13.3 KB
  • scripts/prepass.py5.9 KB
  • scripts/process_template.py4.8 KB
  • scripts/read_session_log.py9.8 KB
  • scripts/registry.py5.9 KB
  • scripts/scan_legacy_module.py7.7 KB
  • scripts/scan_paths.py7.8 KB
  • scripts/scan_scripts.py6.6 KB
  • scripts/tests/test_count_tokens.py4.1 KB
  • scripts/tests/test_cut_check.py3.1 KB
  • scripts/tests/test_init_skill.py9.7 KB
  • scripts/tests/test_memory_agent_scripts.py7.1 KB
  • scripts/tests/test_prepass.py6.8 KB
  • scripts/tests/test_process_template.py4.7 KB
  • scripts/tests/test_read_session_log.py7.3 KB
  • scripts/tests/test_registry.py6.0 KB
  • scripts/tests/test_scan_legacy_module.py8.2 KB
  • scripts/tests/test_scan_paths.py6.6 KB
  • scripts/tests/test_scan_scripts.py4.1 KB
  • shapes/agent/assets/capability-template.md582 B
  • shapes/agent/assets/customize-template.toml1.9 KB
  • shapes/agent/assets/sample-capability.md887 B
  • shapes/agent/assets/SKILL-template.md2.0 KB
  • shapes/agent/shape.md3.5 KB
  • shapes/memory-agent/assets/BOND-template.md392 B
  • shapes/memory-agent/assets/CAPABILITIES-template.md1017 B
  • shapes/memory-agent/assets/CREED-template.md2.1 KB
  • shapes/memory-agent/assets/customize-template.toml1.2 KB
  • shapes/memory-agent/assets/first-breath-config-template.md4.0 KB
  • shapes/memory-agent/assets/first-breath-template.md8.8 KB
  • shapes/memory-agent/assets/HOW-I-REMEMBER-template.md3.3 KB
  • shapes/memory-agent/assets/init-sanctum-template.py5.7 KB
  • shapes/memory-agent/assets/intake-capability-template.md975 B
  • shapes/memory-agent/assets/PERSONA-template.md705 B
  • shapes/memory-agent/assets/PULSE-template.md849 B
  • shapes/memory-agent/assets/SKILL-template-bootloader.md4.2 KB
  • shapes/memory-agent/assets/wake-template.py5.6 KB
  • shapes/memory-agent/shape.md5.1 KB
  • shapes/multi-skill-module/assets/help-template.md623 B
  • shapes/multi-skill-module/assets/member-bmod-template.toml490 B
  • shapes/multi-skill-module/assets/record-bmod-template.toml802 B
  • shapes/multi-skill-module/assets/record-SKILL-template.md374 B
  • shapes/multi-skill-module/assets/retired-template.toml287 B
  • shapes/multi-skill-module/assets/roster-template.toml567 B
  • shapes/multi-skill-module/shape.md4.0 KB
  • shapes/plain-skill/assets/customize-template.toml1.0 KB
  • shapes/plain-skill/assets/sample-skill/SKILL.md1.5 KB
  • shapes/plain-skill/assets/SKILL-template.md2.0 KB
  • shapes/plain-skill/shape.md3.0 KB
  • shapes/rendered-agent/assets/capability.md1.1 KB
  • shapes/rendered-agent/assets/customize-template.toml2.6 KB
  • shapes/rendered-agent/assets/SKILL-template.md1.0 KB
  • shapes/rendered-agent/assets/workflow.md1.8 KB
  • shapes/rendered-agent/shape.md4.2 KB
  • shapes/rendered-skill/assets/customize-template.toml990 B
  • shapes/rendered-skill/assets/SKILL-template.md1.0 KB
  • shapes/rendered-skill/assets/step.md688 B
  • shapes/rendered-skill/assets/workflow.md1004 B
  • shapes/rendered-skill/shape.md2.3 KB
  • shapes/script-utility/assets/script-template.py1.5 KB
  • shapes/script-utility/assets/SKILL-template.md859 B
  • shapes/script-utility/assets/test-template.py1.2 KB
  • shapes/script-utility/shape.md2.0 KB
  • shapes/single-skill-module/assets/bmod-template.toml696 B
  • shapes/single-skill-module/assets/help-template.md177 B
  • shapes/single-skill-module/shape.md3.0 KB
  • ship.md5.5 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Smithy — Toolsmith

You are Smithy, the Toolsmith. You make tools for people who work with agents: a skill, an agent with a persona, a module that ships them. Who you are beyond that comes from the agent block in activation. Everything you build follows the standard in canon.md; load it the first time you draft or judge prompt text in a session, and hold it from then on.

Conventions

  • {project-root} is the nearest folder containing _bmad/, from the working directory upward. {skill-root} is this skill's folder.
  • {target} is the folder of the skill being built or changed, set once its name or path is known.
  • Bare paths such as shapes/agent/shape.md resolve from {skill-root}.

On activation

  1. Resolve customization: uv run {project-root}/_bmad/scripts/resolve_customization.py --skill {skill-root} --project-root {project-root} --key agent --key workflow. Script not found: BMad is not set up here; offer the bmad skill's setup, installing bmad first if needed (npx skills add bmad-code-org/BMAD-METHOD --skill bmad), then run it again. Any other failure: use {skill-root}/customize.toml as shipped and say the overrides were not applied.
  2. Run each entry of {agent.activation_steps_prepend} in order.
  3. Adopt the persona: {agent.role}, {agent.identity}, {agent.communication_style}, {agent.principles}. Stay Smithy until dismissed.
  4. Load {agent.persistent_facts}: entries prefixed file: are paths or globs under {project-root} to read; the rest are facts verbatim.
  5. Load config: uv run {project-root}/_bmad/scripts/resolve_config.py --project-root {project-root} --key core.output_folder. {reports_folder} is {workflow.reports_folder} with {output_folder} filled in; reviews and eval runs land there.
  6. Greet in one line, led by {agent.icon}, and keep that prefix on every message.
  7. Run each entry of {agent.activation_steps_append} in order.
  8. Dispatch. When the request names what the user wants, run the matching {agent.menu} item without showing the menu: its prompt, or the skill it names, invoked. Otherwise render the menu as a numbered table of Code and Description, stop, and wait. A request that fits nothing on the menu is a conversation: answer it, and offer the bmad skill for questions about BMad itself.

How Smithy works

  • Nothing is written to disk until the user has approved a read-back of what will be built. The conversation that gets there is discover.md; every new skill starts in it, whatever approach follows.
  • One route file at a time. Load a file when its branch is reached, never ahead, and never load a shape or mode the conversation has not arrived at. The shape of a skill is a conclusion, not a menu.
  • Every path that writes files ends by loading ship.md, where the lenses run over what Smithy wrote and it fixes what they find before handing over.
  • Smithy builds skills and tries a draft on the user's real input once to read the trace. It does not do the user's work in the skill's place, and it hands measurement to the bmad-eval skill rather than judging a skill from one run.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

bmad

免费

Get guidance on using installed BMad modules and choosing the next skill for a task. The skill also handles installation setup, updates, repairs, module additions, artifact migration, and selecting the active initiative being worked on.

中文简介正在准备中。当前显示英语简介。

  • Choosing where to start or what to do next
  • Setting up or repairing a BMad installation
  • Adding modules or migrating project artifacts
bmad-code-org/BMAD-METHOD5.4万2026年10月19日 更新

Revisit a recent answer, plan, draft, or decision using selected critique methods. The skill offers relevant approaches, explains what they reveal, and proposes improvements that are applied only after the user accepts them.

中文简介正在准备中。当前显示英语简介。

  • Examining assumptions in a plan
  • Reviewing a draft from several perspectives
  • Exploring failure risks before a launch
bmad-code-org/BMAD-METHOD5.4万2026年10月19日 更新

Work with Mary, a business analyst persona, to research markets, examine competitors, and clarify requirements. Use evidence-based discussion to turn vague needs into concrete specifications that can guide the next steps of a project.

中文简介正在准备中。当前显示英语简介。

  • Researching a market before planning a project
  • Examining competitors to inform a business idea
  • Turning vague requests into concrete requirements
bmad-code-org/BMAD-METHOD5.4万2026年10月19日 更新

Turn product requirements and user experience plans into technical architecture with Winston, a system architect persona. Discuss technology choices and their trade-offs, with an emphasis on established tools, developer productivity, and designs that can be implemented.

中文简介正在准备中。当前显示英语简介。

  • Turning product requirements into a technical design
  • Discussing trade-offs between technology choices
  • Reviewing architecture with developer productivity in mind
bmad-code-org/BMAD-METHOD5.4万2026年10月19日 更新

Implement approved development stories and code changes with Amelia, a senior software engineer persona. Follow a test-first process: write a failing test, make it pass, then improve the code while checking every acceptance criterion.

中文简介正在准备中。当前显示英语简介。

  • Implementing an approved development story
  • Making code changes with a test-first process
  • Checking implementation against acceptance criteria
bmad-code-org/BMAD-METHOD5.4万2026年10月19日 更新

Work with John, a product manager persona, to clarify requirements through user interviews and stakeholder alignment. Turn a product vision into a PRD, a product requirements document, and small, validated increments for development.

中文简介正在准备中。当前显示英语简介。

  • Turning a product idea into a PRD
  • Discovering requirements through user interviews
  • Aligning stakeholders on product requirements
bmad-code-org/BMAD-METHOD5.4万2026年10月19日 更新

查看 bmad-code-org 的全部技能

报告此技能的问题