By vinhltt
Utility skills for TDK workflow: brainstorming, research, scouting, problem solving, and more
Use this agent when you need to conduct comprehensive research on software development topics, including investigating new technologies, finding documentation, exploring best practices, or gathering information about plugins, packages, and open source projects. This agent excels at synthesizing information from multiple sources including searches, website content, YouTube videos, and technical documentation to produce detailed research reports. <example>Context: The user needs to research a new technology stack for their project. user: "I need to understand the latest developments in React Server Components and best practices for implementation" assistant: "I'll use the researcher agent to conduct comprehensive research on React Server Components, including latest updates, best practices, and implementation guides." <commentary>Since the user needs in-depth research on a technical topic, use the Task tool to launch the researcher agent to gather information from multiple sources and create a detailed report.</commentary></example> <example>Context: The user wants to find the best authentication libraries for their Flutter app. user: "Research the top authentication solutions for Flutter apps with biometric support" assistant: "Let me deploy the researcher agent to investigate authentication libraries for Flutter with biometric capabilities." <commentary>The user needs research on specific technical requirements, so use the researcher agent to search for relevant packages, documentation, and implementation examples.</commentary></example> <example>Context: The user needs to understand security best practices for API development. user: "What are the current best practices for securing REST APIs in 2024?" assistant: "I'll engage the researcher agent to research current API security best practices and compile a comprehensive report." <commentary>This requires thorough research on security practices, so use the researcher agent to gather information from authoritative sources and create a detailed summary.</commentary></example>
Hostile reliability reviewer for /tdk-plan red-team workflow. Spawned in parallel with tdk-red-team-skeptic and tdk-red-team-security. Reads plan.md + phase-*.md, surfaces failure modes, rollback gaps, missing tests, deployment-order risks. Returns strict JSON findings; never writes files.
Hostile security reviewer for /tdk-plan red-team workflow. Spawned in parallel with tdk-red-team-skeptic and tdk-red-team-reliability. Reads plan.md + phase-*.md, surfaces OWASP-class vulnerabilities, auth/authz holes, data-exposure paths, supply-chain risks. Returns strict JSON findings; never writes files.
Hostile reviewer (assumption destroyer) for /tdk-plan red-team workflow. Spawned in parallel with tdk-red-team-security and tdk-red-team-reliability. Reads plan.md + phase-*.md, surfaces unstated assumptions, missing dependencies, integration gaps, and undefined error paths. Returns strict JSON findings; never writes files.
Codebase navigation specialist. Reads pre-processed Tier 1 structural JSON + samples a small file budget to produce a markdown navigation report. Use ONLY when caller has already run Tier 1 (the tdk-scout TS resolver) and provides tier1_json_path; do NOT invoke directly without that contract field. Typical caller: the tdk-scout skill orchestrator.
Pack repositories into AI-friendly files with Repomix (XML, Markdown, plain text). Use for codebase snapshots, LLM context preparation, security audits, third-party library analysis.
Research technical solutions, analyze architectures, gather requirements thoroughly. Use for technology evaluation, best practices research, solution design, scalability/security/maintainability analysis.
Split large markdown documents into smaller files by heading level. Replaces extracted sections with Obsidian [[wikilinks]] in the original. Use when: document exceeds 200+ lines, needs modularization, or sections should be independently navigable.
Load project configuration and resolve feature directory from validated TASK_ID. Called by: tdk-analyze, tdk-checklist, tdk-clarify, tdk-implement, tdk-plan, tdk-specify (supports --fast mode). NOT user-invocable.
Codebase navigation skill (S4 hierarchical 2-tier). Pre-process a repomix pack via deterministic TS Tier 1 parser, then dispatch the tdk-scout-runner agent (Tier 2) to produce a markdown navigation report (file list + descriptions + unresolved questions). Use for understanding unfamiliar codebases, locating task-relevant files, or pre-processing for downstream skills like tdk-sub-workspace-docs.
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
TDK (TiHon Development Kit) is a specification-driven coding workflow toolkit for Claude Code. It generates specs, plans, tasks, and code from natural language — shipped as a set of marketplace plugins + a TypeScript CLI.
Core philosophy: SDD (Specification-Driven Development) — every feature starts from a formal spec, flows through structured plans and tasks, and is verified against the spec before shipping.
TDK structures the full development loop:
/tdk:specify)/tdk:plan)/tdk-implement)/tdk:ut-backfill-auto)/tdk:status, /tdk:tasks)Additional workflows: config management, sub-workspace docs generation, scout (codebase analysis), memory management, API test generation.
# From the consumer project root:
bash /path/to/tdk/setup.sh
This installs TDK's marketplace plugins, templates, and configurations into the consumer project's .specify/ directory.
Install Claude harness artifacts explicitly after the substrate sync:
cd .specify/scripts/ts
bun src/index.ts harness install --harness claude --plugins tdk-core --dry-run
bun src/index.ts harness install --harness claude --plugins tdk-core --yes
cd .specify/scripts/ts
# Run integrated CLI
bun src/index.ts --help
# Run individual commands
bun src/commands/detect-config.ts
bun src/commands/manifest/compute.ts --root ../..
.specify/
├── plugins/ # Marketplace plugins (installed by setup.sh)
│ ├── tdk-core/ # Core workflow (17 skills)
│ ├── tdk-utils/ # Utilities: scout, research, problem solving (14 skills)
│ ├── tdk-memory/ # Domain memory management (6 skills)
│ └── tdk-test-api/ # API test generation (3 skills)
├── templates/ # 33 templates (spec, plan, task, test, memory, output, design, docs)
├── docs/ # 26 user guides (12 scenario guides + setup guides + reference)
├── configurations/ # Hook configs, sub-workspace configs
└── scripts/
├── ts/ # TypeScript CLI (@tdk/tdk) — primary
│ ├── src/
│ │ ├── index.ts # Unified CLI entry
│ │ ├── commands/ # 8 command groups + standalone scripts
│ │ ├── lib/ # Library modules (parsers, generators)
│ │ └── utils/ # Zod schemas, shared utilities
│ └── tests/ # Bun test suite (30+ test files)
├── bash/ # Legacy shell scripts (maintenance-only)
└── python/ # Legacy Python utilities (maintenance-only)
| Plugin | Skills | Purpose |
|---|---|---|
| tdk-core | 17 | Specify, plan, implement, fix, config, sub-workspace, ut-backfill |
| tdk-utils | 14 | Scout, research, brainstorming, docs-seeker, context-engineering, problem-solving |
| tdk-memory | 6 | Domain memory: init, update, checksum, changelog, query, preload |
| tdk-test-api | 3 | Test plan, testcase generation, Playwright code gen |
Integrated commands (via bun src/index.ts):
| Command | Description |
|---|---|
tdk config detect | Detect .specify.json configuration |
tdk config index | Index configuration files |
tdk config diff | Compare docs between workspace and sub-workspace |
tdk ut auto | Automated unit test backfill |
tdk ut plan | Plan unit test coverage |
tdk ut impl | Implement unit tests from plan |
tdk ut check-rules | Validate UT rules |
tdk ut create-rules | Generate UT rules |
tdk scout | Codebase analysis (repomix + tier-1 extraction) |
tdk harness install | Install selected TDK plugin artifacts into .claude/ with dry-run, ownership, collision, drift, and hook safety |
tdk sub-workspace docs | Generate sub-workspace documentation |
Standalone scripts (via bun src/commands/<path>.ts): manifest, feature, setup, changelog, util, test-api.
noUncheckedIndexedAccess).specify.jsonnpx claudepluginhub vinhltt/tdk --plugin tdk-utilsDomain-based project memory: init, update, checksum, changelog, query, and preload context. Includes memory-guardian agent for business logic conflict detection.
API test generation skills: test plan, testcase generation, Playwright TypeScript code generation from OpenAPI specs or codebase scouting
Core TDK workflow skills: specify, plan, implement, fix, review, analyze, config, tests
Retrospective learning loop: collect implementation feedback, propose learning deltas, and apply approved technical or memory updates
Architecture-aware scaffolding: recommend automations from project config + docs, then scaffold skill/agent files from approved recommendations
Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns
Multi-model consensus engine integrating OpenAI Codex CLI, Gemini CLI, and Claude CLI for collaborative code review and problem-solving.