vincenzo345
UserA meeting becomes a scope tree a build can run against. Agent skills for Claude Code and Codex.
Categories
Indexed Skills (21)
to-record
Turn a raw meeting export into a normalised transcript whose every word is preserved and whose defects are flagged.
to-scope
Turn a normalised transcript into a drafted scope tree, ready for the expert to correct in a review session.
implement
Implement an executable ticket or a fully specified one-session request test-first, preserving original criteria and producing truthful proof receipts before reporting completion.
improve-codebase-architecture
Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
to-spec
Synthesize the current conversation and repository evidence into a traceable, implementation-ready spec, without starting a fresh interview.
to-tickets
Convert a ready spec into traceable tracer-bullet implementation tickets with explicit blockers, proof contracts, and complete source-to-ticket coverage.
wayfinder
Plan a huge, foggy effort as a shared map of decision tickets, resolving one informed decision at a time until a traceable handoff to specification is ready.
claude-rigor
Install and inspect the correctness-focused Claude Code harness distributed with this skill.
codebase-design
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.
delivery-proof
Define and evaluate truthful completion evidence for specs, tickets, implementations, and reviews. Use when deciding what "done" means, tracing requirements to proof, or checking whether evidence is sufficient, independent, non-vacuous, and from the required environment.
domain-modeling
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.
grilling
Stress-test a plan, decision, or idea through an informed, one-question-at-a-time interview. Use when the user asks to be grilled or when another skill must resolve consequential choices without turning recommendations into accidental consent.
code-review
Review a branch or worktree since a fixed point along separate Standards and Spec axes, including uncommitted files and the sufficiency of delivery evidence. Use for PR, branch, or work-in-progress reviews.
diagnosing-bugs
Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.
prototype
Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.
tdd
Test-driven development at public seams. Use when building or fixing behavior test-first, applying red-green-refactor, or defining reliable integration evidence.
workbench
Coordinate explicitly requested or already-active durable Workbench items from persisted state. Use when the user names Workbench, supplies a Workbench ID, or asks to resume or advance existing .workbench work.
feature-planner
Create or review repository-grounded implementation plans for features. Use when a request needs acceptance criteria, affected interfaces, data or schema changes, rollout considerations, or an implementation-ready plan before coding.
openai-docs
Research current OpenAI product, API, model, and Codex behavior from official documentation. Use for OpenAI setup, capabilities, pricing, model choice or migration, prompting, SDKs, APIs, agents, evals, and product comparisons; skip generic software work that merely mentions OpenAI.
research
Investigate a question against high-trust primary sources. Use when the user needs documented facts, API or specification research, or evidence for a blocked decision.
resolving-merge-conflicts
Use when you need to resolve an in-progress git merge/rebase conflict.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.