By vinhltt
Domain-based project memory: init, update, checksum, changelog, query, and preload context. Includes memory-guardian agent for business logic conflict detection.
Load relevant memory context before starting a new feature spec or plan. Claude MUST invoke this skill automatically at the start of: /tdk-specify, /tdk-plan, /tdk-clarify, /tdk-analyze. Identifies involved domains from feature description, loads business rules, data models, services, and known constraints. Returns structured Context Block. NOT user-invocable. Fails silently if memory not initialized.
Query .specify/memory/ knowledge base by natural language. Returns structured context: business rules, services, data models, flows matching the query. Use when asking 'what rules exist for X', 'what services does Y domain have', 'show data model for Z', or when other skills need memory context before implementing. Invocable by user (/tdk-memory-query) and by other skills/agents.
This skill should be used when the user asks to 'update memory', 'add service to domain', 'update business rules', 'add data model', 'modify domain knowledge', 'deprecate memory file', 'tdk-memory-update', or needs to route natural language updates to .specify/memory/ files. Reads memory-index.md for routing rules, applies section anchor updates (additive or replacement), and regenerates checksums. Only explicit flag: --deprecate [path].
Record staged .specify/memory/ changes in CHANGELOG.md via git diff --staged. Stage edits first with 'git add .specify/memory/', then run this skill before committing. Requires /tdk-memory-init first.
SHA256 integrity check of .specify/memory/ files against memory.yaml manifest. Detects modified, untracked, and missing files. Read-only — never modifies files. Optional --fix flag delegates repairs to tdk-memory-update.
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-memoryAPI test generation skills: test plan, testcase generation, Playwright TypeScript code generation from OpenAPI specs or codebase scouting
Utility skills for TDK workflow: brainstorming, research, scouting, problem solving, and more
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.
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.
Curate auto-memory, promote learnings to CLAUDE.md and rules, extract proven patterns into reusable skills.