tt-a1i
@tt-a1i
Public Skills
loop-me
by tt-a1i
Grill me about specs for the workflows I want to build, within this workspace.
setup-ts-deep-modules
by tt-a1i
Wire dependency-cruiser into a TypeScript repo so each package is a deep module — implementation hidden in subfolders, reachable only through its entry-point files. User-invoked.
research
by tt-a1i
Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to a background agent.
writing-fragments
by tt-a1i
Writing, explore — mine raw fragments, no structure yet.
writing-shape
by tt-a1i
Writing, exploit — shape raw material into an article, paragraph by paragraph.
writing-beats
by tt-a1i
Writing, exploit — assemble raw material into a journey of beats, grounding each term before a beat leans on it.
teach
by tt-a1i
Teach the user a new skill or concept, within this workspace.
domain-modeling
by tt-a1i
Build and sharpen a project's domain model. Use when the user wants to pin down domain terminology or a ubiquitous language, record an architectural decision, or when another skill needs to maintain the domain model.
codebase-design
by tt-a1i
Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.
grill-me
by tt-a1i
A relentless interview to sharpen a plan or design.
grill-with-docs
by tt-a1i
A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.
git-guardrails-claude-code
by tt-a1i
Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code.
setup-pre-commit
by tt-a1i
Set up Husky pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo. Use when user wants to add pre-commit hooks, set up Husky, configure lint-staged, or add commit-time formatting/typechecking/testing.
skillroster
by tt-a1i
Route tasks to specialized local Core and On-demand Skills, and govern the local Skill roster. Before reading or changing the workspace for a task that may need instructions not already visible, preserve the complete user message verbatim as TASK. For non-English or mixed input, run skillroster find --hint "ONE FAITHFUL ENGLISH CAPABILITY PARAPHRASE" --load --limit 1 --json -- "TASK"; for English input omit --hint. Follow the complete verified SKILL.md in result.loaded_skill.content.text. Also use for inventory, usage evidence, duplicates, broken links, Core/On-demand recommendations, Plans, Receipts, Apply, and Undo. Not for installing third-party Skills or migrating, distributing, synchronizing, or repairing shared Skill-manager directories.