TAN Qimin
Community@tanqimin · Guangzhou,China
TAN Qimin maintains a registry of 37 Claude Code skills covering spec-driven development, deep-module TypeScript architecture, git safety hooks, and agent handoff patterns.
Agent Skills by TAN Qimin
Showing 37 vetted skills indexed across 1 GitHub repositories.
tanqiminresearch
Investigates questions against primary sources and writes cited findings to Markdown files.
tanqimindomain-modeling
Builds and maintains project domain glossaries and architecture decision records.
tanqiminsetup-pre-commit
Configures Husky pre-commit hooks with lint-staged, Prettier, typecheck, and tests.
tanqiminwayfinder
Plans large efforts as decision tickets tracked on an issue tracker.
tanqiminsetup-matt-pocock-skills
Configures a repository's issue tracker, triage labels, and domain doc layout for engineering skills.
tanqiminsetup-ts-deep-modules
Configures dependency-cruiser to enforce deep-module package boundaries in TypeScript repositories.
tanqiminwriting-for-agents
Write skills, AGENTS.md, and CLAUDE.md documents that agents follow predictably.
tanqiminwait-what
Rephrases the previous AI response in ASD-STE100 Simplified Technical English with project context.
tanqiminloop-me
Interviews users to write workflow specifications for recurring life loops.
tanqiminhandoff
Summarizes the current conversation into a handoff document for another agent.
tanqimindiagnosing-bugs
Diagnose hard bugs and performance regressions through a structured feedback-loop workflow.
tanqimingit-guardrails-claude-code
Configures Claude Code hooks to block dangerous git commands before execution.
tanqimincode-review
Reviews a git diff against coding standards and the originating spec in parallel sub-agents.
tanqiminto-tickets
Breaks plans and specs into tracer-bullet tickets with declared blocking dependencies.
tanqiminask-matt
Routes user situations to the appropriate skill or workflow in the repository.
tanqiminwizard
Generate interactive bash wizards that walk humans through manual setup procedures.
tanqiminimprove-codebase-architecture
Scan a codebase for shallow modules and present deepening refactors as a visual HTML report.
tanqiminto-questionnaire
Generates a Markdown questionnaire document for a recipient to answer asynchronously.
tanqiminto-spec
Synthesizes conversation context into a structured spec published to the project issue tracker.
tanqimincodebase-design
Designs deep modules with small interfaces, clean seams, and testable adapters.
tanqimintriage
Move GitHub issues and external PRs through a triage state machine with agent-ready briefs.
tanqiminprototype
Build throwaway HTML or UI prototypes to answer design questions.
tanqiminwriting-fragments
Collects raw writing fragments into a single markdown file through conversational interviews.
tanqiminresolving-merge-conflicts
Resolves in-progress git merge and rebase conflicts by analyzing commit history and intent.
Frequently Asked Questions About TAN Qimin
FAQPage SchemaWhat tasks can I accomplish with TAN Qimin's skill registry?▼
You can run spec-to-ticket breakdowns, parallel standards-and-spec code reviews, TDD red-green-refactor cycles, bug diagnosis loops, merge conflict resolution, domain modeling with ADRs, and codebase architecture scans that produce visual HTML reports of deepening opportunities.
Who are these skills designed for?▼
TypeScript engineers and teams practicing spec-driven development with Claude Code. The skills target developers managing issue trackers, enforcing deep-module package boundaries, writing ADRs and CONTEXT.md files, and coordinating multi-session agent work through handoff documents.
How do I install and run these skills?▼
Start with setup-matt-pocock-skills, which configures the repo's issue tracker, triage label vocabulary, and domain doc layout. Individual skills then run inside Claude Code sessions; many are user-invoked only (disable-model-invocation) and accept argument hints like a spec or workflow description.
What prerequisites and dependencies do these skills require?▼
A Claude Code environment and a git repository are required. Specific skills add dependencies: setup-pre-commit needs Husky, lint-staged, and Prettier; setup-ts-deep-modules needs dependency-cruiser; migrate-to-shoehorn requires @total-typescript/shoehorn for replacing `as` assertions in tests.
Do the skills support code review and testing practices?▼
Yes. The code-review skill runs parallel sub-agent reviews against documented standards and the originating spec since any commit, branch, or merge-base. The tdd skill drives red-green-refactor cycles with integration tests, and diagnosing-bugs provides a diagnosis loop for failures and performance regressions.