メニュー
Analyzes project architecture and generates ASCII state machine and sequence diagrams. Use for explaining a project, analyzing architecture, tracing an entrypoint, showing a state machine, or generating a sequence diagram.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Stages the changes produced in this session, excludes junk and secrets, and generates a conventional commit. Triggered when the user runs /devx-git:ci or asks to commit.
Updates the current branch onto an origin branch via rebase, with a recoverable backup, safe conflict resolution, and recovery steps. Use when the user runs /rebase or asks to rebase/update their branch onto main (or another origin branch).
Audits an agent, tool loop, or inference request across six dimensions (prompt engineering, tools definition, context engineering, cache usage, evaluation, guardrails) and produces a scored gap analysis with severity ratings and concrete remediations. Framework-agnostic; recognizes patterns from Anthropic SDK, OpenAI SDK, Vercel AI SDK, and OpenAI Agents SDK. Triggers on: audit my agent, review tool loop, audit inference request, agentic engineering review, audit prompt, review agent code, check prompt caching, evaluate guardrails.
Rewrites a given prompt or agent definition by applying Anthropic prompt-engineering best practices — clarity and directness, context and motivation, XML structure, role assignment, long-context layout, output format control, communication-style calibration, and parallel-tool-call affordance. Produces a before/after with per-change rationale. Triggers on: optimize this prompt, improve my prompt, rewrite prompt, prompt optimization, refine system prompt, tune agent prompt, polish prompt for production.
Audits a project's agentic harness (CLAUDE.md, AGENTS.md, .claude/rules, .claude/settings.json) and refactors it into a layered, path-scoped configuration that loads only what is relevant. Rewrites CLAUDE.md and AGENTS.md as a thin critical-rules layer, segments domain rules with `paths:` frontmatter, and adds deny-first permission guardrails. Use for: fixing the harness, auditing claude.md, refactoring agentic configuration, improving agent rules, segmenting rules by path, reviewing settings.json, harness review, or when claude.md is too long.
Evaluate and improve a plugin's skills by applying Anthropic's skill authoring best practices. Use to fix, improve, or review skills for a specific plugin or agent team.
| name | explaining-architecture |
| description | Analyzes project architecture and generates ASCII state machine and sequence diagrams. Use for explaining a project, analyzing architecture, tracing an entrypoint, showing a state machine, or generating a sequence diagram. |
| disable-model-invocation | true |
Analyze project architecture and produce ASCII state machine and sequence diagrams for a given codebase or feature.
Target: $ARGUMENTS
Copy this checklist and track progress:
Architecture Analysis:
- [ ] Step 1: Analyze project composition
- [ ] Step 2: Find entrypoint
- [ ] Step 3: Build state machine graph
- [ ] Step 4: Generate sequence diagram
- [ ] Step 5: Output synthesis
Run language statistics: tokei || echo 'not installed'
If tokei is unavailable, use Glob to count files by extension and estimate composition.
Detect and read the first package manifest found (package.json, Cargo.toml, go.mod, pyproject.toml, requirements.txt, pom.xml, build.gradle). Identify framework from config files and directory structure.
If $ARGUMENTS is specified, locate that feature or module first.
Otherwise search for the main entrypoint: main field in manifest, common files (main.*, index.*, app.*, cmd/main.go), or framework-specific entries (pages/_app.tsx, src/main.rs, manage.py).
From the entrypoint, trace initialization, configuration loading, service bootstrapping, and main event loop or request handler.
Analyze the target for state variables, transition triggers, guards, side effects, and terminal states. Generate an ASCII acyclic graph using box-drawing characters (─ │ ┌ ┐ └ ┘ ├ ┤ ┬ ┴ ┼ ► ◄ ▲ ▼). Max 80 chars wide.
Identify actors (client, controllers, services, data layer, external APIs). Generate an ASCII sequence diagram showing control flow between them. Max 80 chars wide.
Present findings using this template:
╔════════════════════════════════════════╗
║ PROJECT: <name> ║
╠════════════════════════════════════════╣
║ Language: <primary> ║
║ Framework: <detected> ║
║ Type: <CLI/API/Web/Library> ║
╚════════════════════════════════════════╝
Then include in order: