Skip to content

m3taz-ahmed/aizee / skills/bmad-toolsmith

bmad-toolsmith

Verified

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`).

FileKindSize
SKILL.mdskill md3.6 KB
approaches/eval-first.mdmarkdown1.3 KB
approaches/eval-loop.mdmarkdown2.4 KB
approaches/from-logs.mdmarkdown1.7 KB
approaches/lean.mdmarkdown1.7 KB
approaches/scaffold.mdmarkdown1.3 KB
approaches/skill-creator-loop.mdmarkdown1.2 KB
bmod.tomlconfig118 B
canon.mdmarkdown10.5 KB
customize.tomlconfig4.8 KB
discover.mdmarkdown5.5 KB
evals/triggers.jsonconfig3.3 KB
lenses/lens-architecture.mdmarkdown2.9 KB
lenses/lens-contract.mdmarkdown1.4 KB
lenses/lens-customization.mdmarkdown2.4 KB
lenses/lens-determinism.mdmarkdown1.8 KB
lenses/lens-leanness.mdmarkdown3.1 KB
lenses/lens-trigger.mdmarkdown2.4 KB
lenses/standards.mdmarkdown5.2 KB
modes/convert.mdmarkdown2.1 KB
modes/cut-roles.mdmarkdown3.3 KB
modes/cut.mdmarkdown3.3 KB
modes/edit.mdmarkdown1.3 KB
modes/migrate.mdmarkdown3.3 KB
modes/package.mdmarkdown2.6 KB
modes/review.mdmarkdown1.3 KB
modes/validate.mdmarkdown1.8 KB
scripts/count_tokens.pyscript3.6 KB
scripts/cut_check.pyscript5.1 KB
scripts/init_skill.pyscript13.3 KB
scripts/prepass.pyscript7.5 KB
scripts/process_template.pyscript4.8 KB
scripts/read_session_log.pyscript9.8 KB
scripts/registry.pyscript5.9 KB
scripts/scan_legacy_module.pyscript7.7 KB
scripts/scan_paths.pyscript9.2 KB
scripts/scan_scripts.pyscript6.6 KB
scripts/tests/test_count_tokens.pyscript4.1 KB
scripts/tests/test_cut_check.pyscript3.1 KB
scripts/tests/test_init_skill.pyscript9.7 KB
scripts/tests/test_memory_agent_scripts.pyscript8.6 KB
scripts/tests/test_prepass.pyscript8.3 KB
scripts/tests/test_process_template.pyscript4.7 KB
scripts/tests/test_read_session_log.pyscript7.3 KB
scripts/tests/test_registry.pyscript6.0 KB
scripts/tests/test_scan_legacy_module.pyscript8.2 KB
scripts/tests/test_scan_paths.pyscript7.7 KB
scripts/tests/test_scan_scripts.pyscript4.1 KB
shapes/agent/assets/SKILL-template.mdmarkdown2.0 KB
shapes/agent/assets/capability-template.mdmarkdown582 B
shapes/agent/assets/customize-template.tomlconfig1.9 KB
shapes/agent/assets/sample-capability.mdmarkdown887 B
shapes/agent/shape.mdmarkdown3.2 KB
shapes/memory-agent/assets/BOND-template.mdmarkdown392 B
shapes/memory-agent/assets/CAPABILITIES-template.mdmarkdown1017 B
shapes/memory-agent/assets/CREED-template.mdmarkdown2.1 KB
shapes/memory-agent/assets/HOW-I-REMEMBER-template.mdmarkdown3.3 KB
shapes/memory-agent/assets/PERSONA-template.mdmarkdown705 B
shapes/memory-agent/assets/PULSE-template.mdmarkdown849 B
shapes/memory-agent/assets/SKILL-template-bootloader.mdmarkdown4.2 KB
shapes/memory-agent/assets/customize-template.tomlconfig1.2 KB
shapes/memory-agent/assets/first-breath-config-template.mdmarkdown4.5 KB
shapes/memory-agent/assets/first-breath-template.mdmarkdown9.3 KB
shapes/memory-agent/assets/init-sanctum-template.pyscript5.7 KB
shapes/memory-agent/assets/intake-capability-template.mdmarkdown975 B
shapes/memory-agent/assets/wake-template.pyscript6.8 KB
shapes/memory-agent/shape.mdmarkdown5.0 KB
shapes/multi-skill-module/assets/help-template.mdmarkdown623 B
shapes/multi-skill-module/assets/member-bmod-template.tomlconfig490 B
shapes/multi-skill-module/assets/record-SKILL-template.mdmarkdown374 B
shapes/multi-skill-module/assets/record-bmod-template.tomlconfig802 B
shapes/multi-skill-module/assets/retired-template.tomlconfig287 B
shapes/multi-skill-module/assets/roster-template.tomlconfig567 B
shapes/multi-skill-module/shape.mdmarkdown4.3 KB
shapes/plain-skill/assets/SKILL-template.mdmarkdown2.0 KB
shapes/plain-skill/assets/customize-template.tomlconfig1.0 KB
shapes/plain-skill/shape.mdmarkdown2.9 KB
shapes/rendered-agent/assets/SKILL-template.mdmarkdown1.0 KB
shapes/rendered-agent/assets/capability.mdmarkdown1.1 KB
shapes/rendered-agent/assets/customize-template.tomlconfig2.6 KB
shapes/rendered-agent/assets/workflow.mdmarkdown1.8 KB
shapes/rendered-agent/shape.mdmarkdown3.8 KB
shapes/rendered-skill/assets/SKILL-template.mdmarkdown1.0 KB
shapes/rendered-skill/assets/customize-template.tomlconfig990 B
shapes/rendered-skill/assets/step.mdmarkdown688 B
shapes/rendered-skill/assets/workflow.mdmarkdown1004 B
shapes/rendered-skill/shape.mdmarkdown2.2 KB
shapes/script-utility/assets/SKILL-template.mdmarkdown859 B
shapes/script-utility/assets/script-template.pyscript1.5 KB
shapes/script-utility/assets/test-template.pyscript1.2 KB
shapes/script-utility/shape.mdmarkdown1.6 KB
shapes/single-skill-module/assets/bmod-template.tomlconfig696 B
shapes/single-skill-module/assets/help-template.mdmarkdown177 B
shapes/single-skill-module/shape.mdmarkdown2.5 KB
ship.mdmarkdown6.4 KB

scripts/tests/test_read_session_log.py

View on GitHub
"""Tests for read_session_log.py over a synthetic Claude Code transcript and a synthetic memlog."""

import json
import os
import subprocess
import sys
import tempfile
import unittest
from pathlib import Path

SCRIPT = Path(__file__).resolve().parents[1] / "read_session_log.py"


def user(text, **extra):
    return {"type": "user", "message": {"role": "user", "content": text}, **extra}


def tool_result():
    return {
        "type": "user",
        "message": {"role": "user", "content": [{"type": "tool_result", "tool_use_id": "t", "content": "x"}]},
    }


def assistant(*tool_uses):
    blocks = [{"type": "text", "text": "assistant prose never copied"}]
    blocks += [
        {"type": "tool_use", "id": f"t{i}", "name": name, "input": inp} for i, (name, inp) in enumerate(tool_uses)
    ]
    return {"type": "assistant", "message": {"role": "assistant", "content": blocks}}


TRANSCRIPT = [
    {"type": "last-prompt", "lastPrompt": "noise record without a message"},
    user("Build me a changelog skill that reads git history. " + "x" * 400),
    assistant(
        ("Read", {"file_path": "/repo/skills/bmad-x/SKILL.md"}),
        ("Bash", {"command": "ls"}),
        ("Bash", {"command": "pwd"}),
    ),
    tool_result(),
    assistant(("Edit", {"file_path": "/repo/skills/bmad-x/SKILL.md", "old_string": "a", "new_string": "b"})),
    user("No, don't touch SKILL.md, put it in references instead"),
    assistant(("Write", {"file_path": "/repo/skills/bmad-x/references/history.md"})),
    user("[Request interrupted by user for tool use]"),
    user("<command-name>/bmad-eval</command-name>\n<command-args></command-args>"),
    assistant(("Skill", {"skill": "bmad-eval"}), ("Read", {"file_path": "/repo/evals/cases.json"})),
    user("build me a changelog skill that reads git history. " + "x" * 400),
    user("secret meta content", isMeta=True),
    user("sidechain content", isSidechain=True),
    assistant(("Read", {"file_path": "/repo/skills/bmad-x/SKILL.md"}), ("Bash", {"command": "ls"})),
    "this line is not json",
]

MEMLOG = """---
topic: bmad-changelog
updated: 2026-06-07T14:22
---

- (note) user picked the lean approach
- (direction) keep the skill to one file
- (decision by user) name it bmad-changelog
- (gap) no eval cases yet
- (assumption) git is installed
- (idea by user) also read tags
- (note) wait, the folder was wrong
"""


def write_transcript(folder: Path, name="s1.jsonl"):
    path = folder / name
    path.write_text("\n".join(r if isinstance(r, str) else json.dumps(r) for r in TRANSCRIPT) + "\n", encoding="utf-8")
    return path


def run(*args, env=None):
    res = subprocess.run(
        [sys.executable, str(SCRIPT), *[str(a) for a in args]], capture_output=True, text=True, env=env
    )
    return res.returncode, json.loads(res.stdout) if res.stdout.strip() else None, res.stderr


class ReadSessionLogTest(unittest.TestCase):
    def test_claude_code_digest(self):
        with tempfile.TemporaryDirectory() as tmp:
            path = write_transcript(Path(tmp))
            code, data, err = run(path)
            self.assertEqual(code, 0, err)
            self.assertEqual(
                set(data),
                {"sources", "user_requests", "tool_sequences", "corrections", "files_touched", "skills_invoked"},
            )
            self.assertEqual(data["sources"], [{"path": str(path), "format": "claude-code", "entries": 14}])

            requests = data["user_requests"]
            self.assertEqual(requests[0]["count"], 2)
            self.assertTrue(requests[0]["text"].startswith("Build me a changelog skill"))
            self.assertEqual(len(requests[0]["text"]), 300)
            self.assertTrue(requests[0]["text"].endswith("..."))
            texts = " ".join(r["text"] for r in requests)
            self.assertNotIn("secret meta", texts)
            self.assertNotIn("sidechain", texts)
            self.assertNotIn("assistant prose", json.dumps(data))
            self.assertNotIn("<command-name>", texts)

            self.assertEqual(
                data["corrections"],
                [
                    "No, don't touch SKILL.md, put it in references instead",
                    "[Request interrupted by user for tool use]",
                ],
            )
            self.assertEqual(data["skills_invoked"], [{"name": "bmad-eval", "count": 2}])
            self.assertEqual(
                data["files_touched"],
                ["/repo/evals/cases.json", "/repo/skills/bmad-x/SKILL.md", "/repo/skills/bmad-x/references/history.md"],
            )
            sequences = {tuple(s["tools"]): s["count"] for s in data["tool_sequences"]}
            self.assertEqual(sequences[("Read", "Bash")], 1)
            self.assertEqual(sequences[("Read", "Bash", "Edit")], 1)
            self.assertEqual(sequences[("Write",)], 1)
            self.assertEqual(sequences[("Skill", "Read")], 1)

    def test_memlog_digest_and_max_items(self):
        with tempfile.TemporaryDirectory() as tmp:
            path = Path(tmp) / ".memlog.md"
            path.write_text(MEMLOG, encoding="utf-8")
            code, data, err = run(path, "--format", "memlog")
            self.assertEqual(code, 0, err)
            self.assertEqual(data["sources"][0]["entries"], 7)
            self.assertEqual(
                [r["text"] for r in data["user_requests"]],
                ["keep the skill to one file", "name it bmad-changelog", "also read tags"],
            )
            self.assertEqual(data["corrections"], ["no eval cases yet", "wait, the folder was wrong"])
            code, data, _ = run(path, "--max-items", "1")
            self.assertEqual(len(data["user_requests"]), 1)
            self.assertEqual(len(data["corrections"]), 1)

    def test_folder_and_project_resolution(self):
        with tempfile.TemporaryDirectory() as tmp:
            config = Path(tmp) / "config"
            project_dir = Path(tmp) / "work" / "my.repo"
            project_dir.mkdir(parents=True)
            encoded = str(project_dir.resolve()).replace("/", "-").replace(".", "-")
            folder = config / "projects" / encoded
            folder.mkdir(parents=True)
            write_transcript(folder, "a.jsonl")
            write_transcript(folder, "b.jsonl")
            (folder / ".memlog.md").write_text(MEMLOG, encoding="utf-8")
            env = dict(os.environ, CLAUDE_CONFIG_DIR=str(config))
            code, data, err = run("--project", project_dir, env=env)
            self.assertEqual(code, 0, err)
            self.assertEqual([s["format"] for s in data["sources"]], ["claude-code", "claude-code", "memlog"])
            self.assertEqual(data["skills_invoked"], [{"name": "bmad-eval", "count": 4}])
            code, _, err = run("--project", Path(tmp) / "nowhere", env=env)
            self.assertEqual(code, 2)

    def test_unknown_format_is_skipped_and_missing_path_errors(self):
        with tempfile.TemporaryDirectory() as tmp:
            other = Path(tmp) / "notes.txt"
            other.write_text("hello", encoding="utf-8")
            code, data, err = run(other)
            self.assertEqual(code, 0)
            self.assertEqual(data["sources"], [])
            self.assertIn("unknown format", err)
            code, _, _ = run(Path(tmp) / "missing.jsonl")
            self.assertEqual(code, 2)
            code, _, _ = run()
            self.assertEqual(code, 2)


if __name__ == "__main__":
    unittest.main()
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall