Login
bmad-code-org/bmad-method88 files

Bmad Toolsmith

Smithy the Toolsmith builds, converts, reviews, packages, validates and migrates BMad skills, agents and modules. Use when the user wants a skill, agent, persona, command or module made, changed, reviewed or packaged; a prompt or rule from another tool turned into a skill; a skill mined from session logs; an old module migrated; or asks for Smithy. Not for running evals (`bmad-eval`), overriding an installed skill (`bmad-customize`), app code (`bmad-build`) or questions about BMad (`bmad`).

Use this skillView repositoryView on skills.sh
Specification
Skill ID
bmad-code-org/bmad-method/bmad-toolsmith
Publisher
bmad-code-org
Repository
bmad-method
Installs
242
Files
88
Synced
Oct 23, 2026
How to use it

Open any RiverX project, open the Skills panel in the chat, and search for this identifier. The files are fetched from the source repository at install time.

bmad-code-org/bmad-method/bmad-toolsmithInstalls these files
  • SKILL.md
  • approaches/eval-first.md
  • approaches/eval-loop.md
  • approaches/from-logs.md
  • approaches/lean.md
  • approaches/scaffold.md
  • approaches/skill-creator-loop.md
  • bmod.toml
  • canon.md
  • customize.toml
  • discover.md
  • ecosystem.md
  • evals/triggers.json
  • lenses/lens-architecture.md
  • lenses/lens-contract.md
  • lenses/lens-customization.md
  • lenses/lens-determinism.md
  • lenses/lens-leanness.md
  • lenses/lens-trigger.md
  • lenses/standards.md
  • modes/convert.md
  • modes/edit.md
  • modes/migrate.md
  • modes/package.md
  • modes/review.md
  • modes/validate.md
  • scripts/count_tokens.py
  • scripts/init_skill.py
  • scripts/prepass.py
  • scripts/process_template.py
  • scripts/read_session_log.py
  • scripts/registry.py
  • scripts/scan_legacy_module.py
  • scripts/scan_paths.py
  • scripts/scan_scripts.py
  • scripts/tests/test_count_tokens.py
  • scripts/tests/test_init_skill.py
  • scripts/tests/test_memory_agent_scripts.py
  • scripts/tests/test_prepass.py
  • scripts/tests/test_process_template.py
  • scripts/tests/test_read_session_log.py
  • scripts/tests/test_registry.py
  • scripts/tests/test_scan_legacy_module.py
  • scripts/tests/test_scan_paths.py
  • scripts/tests/test_scan_scripts.py
  • shapes/agent/assets/SKILL-template.md
  • shapes/agent/assets/capability-template.md
  • shapes/agent/assets/customize-template.toml
  • shapes/agent/assets/sample-capability.md
  • shapes/agent/shape.md
  • shapes/memory-agent/assets/BOND-template.md
  • shapes/memory-agent/assets/CAPABILITIES-template.md
  • shapes/memory-agent/assets/CREED-template.md
  • shapes/memory-agent/assets/HOW-I-REMEMBER-template.md
  • shapes/memory-agent/assets/PERSONA-template.md
  • shapes/memory-agent/assets/PULSE-template.md
  • shapes/memory-agent/assets/SKILL-template-bootloader.md
  • shapes/memory-agent/assets/customize-template.toml
  • shapes/memory-agent/assets/first-breath-config-template.md
  • shapes/memory-agent/assets/first-breath-template.md
  • shapes/memory-agent/assets/init-sanctum-template.py
  • shapes/memory-agent/assets/intake-capability-template.md
  • shapes/memory-agent/assets/wake-template.py
  • shapes/memory-agent/shape.md
  • shapes/multi-skill-module/assets/help-template.md
  • shapes/multi-skill-module/assets/member-bmod-template.toml
  • shapes/multi-skill-module/assets/record-SKILL-template.md
  • shapes/multi-skill-module/assets/record-bmod-template.toml
  • shapes/multi-skill-module/assets/retired-template.toml
  • shapes/multi-skill-module/assets/roster-template.toml
  • shapes/multi-skill-module/shape.md
  • shapes/plain-skill/assets/SKILL-template.md
  • shapes/plain-skill/assets/customize-template.toml
  • shapes/plain-skill/assets/sample-skill/SKILL.md
  • shapes/plain-skill/shape.md
  • shapes/rendered-skill/assets/SKILL-template.md
  • shapes/rendered-skill/assets/customize-template.toml
  • shapes/rendered-skill/assets/step.md
  • shapes/rendered-skill/assets/workflow.md
  • shapes/rendered-skill/shape.md
  • shapes/script-utility/assets/SKILL-template.md
  • shapes/script-utility/assets/script-template.py
  • shapes/script-utility/assets/test-template.py
  • shapes/script-utility/shape.md
  • shapes/single-skill-module/assets/bmod-template.toml
  • shapes/single-skill-module/assets/help-template.md
  • shapes/single-skill-module/shape.md
  • ship.md

What this skill tells the agent

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 --key core.communication_language. {reports_folder} is {workflow.reports_folder} with {output_folder} filled in; reviews and eval runs land there. Speak in {communication_language} when set.
  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.

More from bmad-code-org

bmad-code-org/bmad-method

Bmad Spec

Condense any input — an idea, brief, PRD, transcript, or mixed notes — into a short spec: SPEC.md plus supporting files that downstream skills build from. Also updates and validates existing specs, and can break a spec into stories. Use when the user says "create a spec", "distill this into a spec", "validate this spec", "update the spec", or "break this into stories"

bmad-code-org/bmad-method

Bmad Ticket

Create and manage tickets — initiatives, epics, stories, bugs. Use when the user says "create a new initiative", "slice this initiative", "split this epic up", "break this into stories", "incept this epic", "make a ticket", "refine this ticket", "what's ready", "status of a story", "publish ticket changes", "validate these tickets", "set up the ticket store".

bmad-code-org/bmad-method

Bmad Retrospective

Review a completed epic against the evidence it left behind — spec, stories, diffs, commits, sprint status — and produce a retrospective with sourced findings, action items, and an acceptance decision. Use when the user says "run a retrospective" or "lets retro the epic [epic]". Supports -H/--headless

Use this skill in a project

Open any RiverX project, search the Skills panel for bmad-code-org/bmad-method/bmad-toolsmith, and install it in one click.

Use this skill