- Skills
- 55
- 仓库
- 1
- 职业覆盖
- 0
- 场景覆盖
- 0
- Stars
- ★ 1
Matias 的 Skills 55
yun-write-wizard
Generate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don't invoke this for steps the agent can perform itself.
yun-write-spec
Write the spec — consolidate a large task's settled decisions into one durable document before it is sliced into tickets. Use when the decisions are settled and the user wants them written up, or says "write the spec" / "escribí el spec". Declines small fixes that need no spec.
yun-write-pr
Write a pull request title and body that show the change — its ticket, its shape, the evidence it works, and how dangerous it is to merge.
yun-write-handoff
Compact the current session into a disposable handoff baton for the next agent, pointing at durable memory instead of duplicating it.
yun-write-agent-docs
Use when authoring or editing a document an agent reads in this workspace — a skill, a `skills/_shared/` contract, `AGENTS.md` or `skills/README.md` — deciding how it is invoked, what lives in it versus a linked file, naming it, or diagnosing why a skill misfires, bloats, or fires unreliably.
yun-tdd
Test-driven development — the red → green loop, tests written only at pre-agreed seams. Use when the user wants to build a feature or fix a bug test-first, or mentions TDD or red-green. Reached by the implement flow to drive a build at a seam.
yun-sync-repo
Bring an external repo into the workspace as work material — cloned into repos/<name>/, gitignored, with its own .git.
yun-spawn-worktree
Spawn an isolated git worktree for a synced repo so parallel work never collides. Use when the user wants to parallelize, work a task in isolation, or run one of several tickets on its own branch — or when another skill (e.g. yun-implement) needs an isolated worktree to build in. Creates .worktrees/<repo>/<task>/ on its own branch.
yun-slice-plan
Slice an approved plan or spec into tracer-bullet tickets. Use when the user has a plan, spec, or decision ready and wants it broken into executable tickets to build.
yun-show-me
Re-pitch what did not land — a little context, plain words in the domain's own language, and the smallest view that shows it.
yun-scan-architecture
Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
yun-review-work
Use when the user wants to adversarially stress-test a decision, plan, spec, design, skill, or code change before acting — e.g. "review this work", "revisá esto", "revisá este trabajo". Runs two blind independent reviewers and synthesizes a verdict.
yun-retro
Conduct a retrospective on a coding session — candidate improvements to the harness and the target repo, by severity.
yun-research
Investigate a question against primary sources and leave a cited Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, a claim verified, or reading legwork delegated while they keep working.
yun-model-domain
Build and sharpen a project's domain model — its ubiquitous language and the decisions behind its shape. Use when the user wants to pin down or resolve a fuzzy, overloaded, or conflicting domain term, agree on canonical vocabulary, or record a hard-to-reverse decision about the domain's shape (an ADR); or when another skill needs to maintain the domain model. This skill writes the glossary and ADRs — reading them for vocabulary is a one-liner any skill does through domain-convention.
yun-implement
Build the work — write the code for a feature or fix (from a spec, tickets, or a described task), test-first at the agreed seams, then review and land it when asked. Use when the next step is writing code, or the user says "implement" / "implementá" / "buildeá". Declines large or unplanned work, routing it back to planning.
yun-grill-plan
Use when the user wants to stress-test a plan, decision, design, or idea before acting — or uses any "grill" trigger ("grill me", "grillame", "cuestioname", "desafiame", "poné a prueba esto"). Front-loads the open decisions into one relentless interview so the settled decisions are airtight enough to execute autonomously.
yun-diagnose-bug
Diagnosis loop for hard bugs and performance regressions — build a tight feedback loop that goes red on the bug before theorising about it. Use when the user says "diagnose this bug" / "diagnosticá" / "no entiendo por qué falla" / "está lento", when a bug resisted the obvious fix, when its repro will not hold still, or when something got slower.