guillermomurillo
- 29 skills
- 0 followers
- 17 hours ago last updated
- ▌ Tdd · guillermomurillo bundleTest-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.
- ▌ Ship · guillermomurilloTake a finished feature branch from "I think I'm done" to "PR open with the right body that will close the parent PRD on merge." Verifies the branch is shippable, inventories slice commits and their parent PRD via `## Parent` walks, runs `/code-review` as a gate, drafts a PR body with `Closes
- ▌ To Prd · guillermomurilloTurn the current conversation into a PRD and publish it to the project issue tracker — no interview, just synthesis of what you've already discussed.
- ▌ Triage · guillermomurillo bundleMove issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs.
- ▌ Pager · guillermomurilloFormat replies for tiny screens like smart glasses, phones, and watches. Short headline first, more on ask. Also a no-device concise mode that strips filler while keeping full technical accuracy. Use when user says "pager mode", "on my phone", "on glasses", "on the watch", "small screen", "be brief", "less tokens", "concise mode", or invokes /pager.
- ▌
- ▌ Afk Cook · guillermomurillo bundleBash-loop runner for unattended, fresh-context execution of ready-for-agent issues. Each iteration starts empty, reads the spec from the issue body, applies TDD, commits, advances. Use when the user wants to walk away and let a batch of ready-for-agent slices ship overnight, or asks how to install/use the AFK runner.
- ▌ Ask Memo · guillermomurilloAsk which skill or flow fits your situation. A router over the skills in this repo.
- ▌ Critique · guillermomurillo bundleAdversarial code review of a diff for a human to triage. Advisory, never blocks. Owns the axes that /code-review and /review-tests do not cover - scope creep, dead and half-finished code, error-handling slop, naming and readability lies, and an AI-slop-pattern sweep. Emits graded findings (must-fix / should-fix / nit) plus a verdict. Use when the user says critique this, tear this apart, be harsh, what is wrong with this code, review this like you hate it, wants a brutal or adversarial pass before a PR, suspects too many looks-fine-to-me verdicts on their own work, or invokes /critique. Also offered as an optional pass inside /ship.
- ▌ Handoff · guillermomurilloCompact the current conversation into a handoff document for another agent to pick up.
- ▌
- ▌ Memo Flow · guillermomurillo bundleUnified entry point for the memo-flow base tier. Detects install state and routes to the right flow: fresh install for new projects, status + health checks for healthy installs, diagnose and repair for broken installs. Use when the user invokes /memo-flow, wants to set up engineering skills on a new project, check project health, repair a broken install, or run a cross-project health survey.
- ▌ Prototype · guillermomurillo bundleBuild 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.
- ▌ To Issues · guillermomurilloBreak a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet vertical slices.
- ▌
- ▌ Grilling · guillermomurilloGrill the user relentlessly about a plan or design. Use when the user wants to stress-test a plan before building, or uses any 'grill' trigger phrases.
- ▌ Memo Hooks · guillermomurillo bundleUnified entry point for the memo-flow hooks tier. Detects install state and routes to the right flow: fresh install + per-hook opt-in for new projects, management menu for healthy installs, repair flow for broken installs. Use when the user invokes /memo-hooks, wants to configure hooks, change context-monitor mode/threshold, check the skill leaderboard, or install the hooks tier on a fresh project.
- ▌ Code Review · guillermomurilloReview the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/PRD asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X". Also invoke when running as the review gate inside `/ship`, when confirming a branch is ready to merge, before opening a PR, or when the user says "review this branch", "check the diff", "is this ready to ship", or "gate-check this".
- ▌ Review Tests · guillermomurilloTest-sufficiency review of a diff. Asks whether existing tests cover the change, not whether tests exist (test-gate's job) and not whether they pass (the runner's job). Read-only, reports in five sections (M1-M4 Missing, C Consider). Use when the user wants to review tests, check test coverage of a branch, asks "did we test enough", "are the tests sufficient", or wants a Tests axis alongside /code-review's Standards and Spec before opening a PR.
- ▌ Write A Hook · guillermomurilloInternal authoring tool for new memo-flow bundle hooks. Interrogates the author, then scaffolds the hook script, config.json block, settings.json entry, and README row — ensuring all four outputs are consistent before any file is written.
- ▌ Codebase Design · guillermomurillo bundleShared 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.
- ▌ Diagnosing Bugs · guillermomurillo bundleDiagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.
- ▌ Domain Modeling · guillermomurillo bundleBuild 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.
- ▌ Grill With Docs · guillermomurilloA relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.
- ▌ Uninstall Memo Flow · guillermomurillo bundleReverses every base-tier memo-flow mutation in the current project and removes its entry from the user registry. Refuses to run if the hooks tier is still installed — instruct the user to run /uninstall-memo-hooks first. Fenced regions with no inner content are removed silently; regions with user-edited content prompt before destroying (non-interactive default: preserve content, strip fences).
- ▌ Uninstall Memo Hooks · guillermomurillo bundleReverse every hooks-tier memo-flow mutation in the current project. Removes hook scripts, config.json, settings entries, and gitignore entries. Drops "hooks" from the registry tier while leaving the base tier and base mutations intact. Non-interactive default for fenced content: preserve + strip fences.
- ▌ Writing Great Skills · guillermomurillo bundleReference for writing and editing skills well — the vocabulary and principles that make a skill predictable.
- ▌ Resolving Merge Conflicts · guillermomurilloUse when you need to resolve an in-progress git merge/rebase conflict.
- ▌ Improve Codebase Architecture · guillermomurillo bundleScan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.