Categories
Indexed Skills (52)
absorb
Analyze one or more external projects (git URL or local path) to extract AI-harness practices, agent patterns, or instruction logic and contrast them against this repository's harness. Not for application code review.
adr
Trigger: ADR, architecture decision record, technical decision. Create ADRs that document context, options, rationale, consequences, and trade-offs.
anki-vocab
Trigger: anki, vocab, vocabulary cards, vocabulario, tarjetas anki, learn vocab. Anki-importable vocabulary batches for any target language: situation-driven natural phrases built preferentially from already-learned vocabulary, translated into the learner's native language (Spanish by default), exported as ;-separated txt.
architecture-ideation
Trigger: architecture refactor ideas, target architecture, modular monolith, architecture patterns, restructure the system. Question-driven architecture refactor ideation producing an ADR plus a ready-for-sdd OpenSpec bundle.
architecture-map
Trigger: architecture map, C4 diagram, container diagram, flow map, visual architecture docs, architecture drift refresh. Generate compact C4-lite Mermaid architecture docs from code evidence and refresh them on re-run.
architecture-state
Trigger: architecture review, project state, toolchain detection, architecture style, architecture gaps, fitness functions. Detect language/toolchain with evidence, identify the architecture style, and produce a gap analysis with fitness-function proposals.
buildable-issue
Creates agent-ready GitHub issues that are ready to build. Formerly framed as sdd-issue / SDD-ready issue creation. Use when creating a buildable issue, implementation-ready ticket, SDD-ready issue, preparing work for an orchestrator, or when the user says "create an issue", "write a ticket", or "I need to build X". Also use when the user references an existing issue and wants it enriched with scope, constraints, acceptance scenarios, and technical context.
characterization-test-scoping
Trigger: characterization tests, seams, high-risk refactor planning, test safety planning. Scope high-risk refactor work around tests, seams, containment, and rollback.
code-conventions
Trigger: writing or planning production code or tests, defining test naming/assert style, extracting constants, placing DTOs or characterization tests. Andres's personal code and test conventions.
cognitive-doc-design
Design docs that reduce cognitive load. Trigger: writing guides, READMEs, RFCs, onboarding, architecture, or review-facing docs.
cognitive-output-refiner
Trigger: refine output, summarize output, compact logs, reduce cognitive load, remove duplicates. Refines heavy textual output into a concise, faithful, non-duplicative version.
cornell-notes
Trigger: cornell note, cornell notes, nota cornell, learning lesson capture. Markdown Cornell note format for micro-lessons: cue questions + notes + learner-voiced summary; cues feed quizzes and the spaced-repetition queue.
dependency-security-audit
Trigger: security audit, dependency audit, CVE scan, vulnerable libraries, outdated dependencies, logging posture. Audit dependency vulnerabilities and logging/observability posture with read-only commands, degrading to manifest inspection when tooling is unavailable.
design-patterns-pragmatic
Trigger: design patterns, GoF patterns, Java patterns, strategy, adapter, factory, builder, decorator, observer. Choose patterns only when they solve real design forces.
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.
english-tutor
Trigger: explicit English tutoring, correction, practice, or /english. Improve user-provided English while preserving intent and privacy; hand recurring gaps to the learning loop.
fable-planning
Trigger: deep plan, plan like Fable, planificar a fondo, fable plan. Fable-5-style planning: evidence before opinion, outcome-first selectivity, minimal calibrated questions, explicit edge-case validation, end-to-end verification plan.
feynman-teachback
Trigger: feynman, teach back, teach-back, explicamelo, metodo feynman, learn teach. Feynman-technique teach-back sessions: the learner explains a concept in simple terms to a naive-student mentor; gaps demote recall cards and drive re-study.
grill
Trigger: grill me, grill with docs, grill me sdd, grill code, grill docs open, entrevistame, entrevistame sdd. Router for relentless interview modes: plain, docs, or SDD planning.
java-api-design
Trigger: Java API design, public API, encapsulation, modules, visibility, contracts, binary compatibility. Design Java APIs with clear boundaries.
java-exception-robustness
Trigger: Java exceptions, error handling, try-with-resources, resource cleanup, checked exceptions, robustness. Design Java failure handling safely.
java-immutability-modeling
Trigger: Java immutability, records, value objects, defensive copies, mutable collections, DTO modeling. Model Java data safely and clearly.
java-secure-coding
Trigger: Java secure coding, Oracle Secure Coding Guidelines, input validation, trust boundaries, deserialization, least privilege, sensitive data. Review Java code for secure implementation practices.
java-testing
Trigger: Java tests, JUnit, Mockito, AssertJ, legacy code, characterization tests, seams. Generate and retrofit Java tests safely.
jira-spike
Create or refine Jira Spike tickets in Jira Markup. Use when the user wants a Spike, research ticket, investigation ticket, technical exploration, discovery work, research question, or SDD-ready Spike input.
jira-task
Create or refine Jira Task tickets in Jira Markup. Use when the user wants a Jira Task, technical task, implementation task, maintenance task, operational work item, developer-ready task, acceptance criteria for a task, or SDD-ready Task input.
jira-user-story
Create or refine Jira User Story tickets in Jira Markup. Use when the user wants a user story, story ticket, product capability, end-user outcome, acceptance criteria for a story, developer-ready story, or SDD-ready User Story input.
judgment-day
Parallel adversarial review protocol that launches two independent blind judge sub-agents simultaneously to review the same target, synthesizes their findings, applies fixes, and re-judges until both pass or escalates after 2 iterations. Trigger: When user says "judgment day", "judgment-day", "review adversarial", "dual review", "doble review", "juzgar", "que lo juzguen".
learning-loop
Trigger: /learn, learn topic, learning path, teach me, ensename, aprender, ruta de aprendizaje. Mission-grounded 70-20-10 learning loop: Mermaid roadmaps, Cornell micro-lessons, real-repo exercises, Socratic debriefs, and spaced-repetition hand-off.
legacy-code-safety
Trigger: legacy code safety, safe refactor. Make untested code safe to change.
native-question-ux
Trigger: native question ux, portable question presentation. Route bounded decisions through the runtime's native question UX and open-ended questions through plain chat.
prd-light
Trigger: PRD light, quick PRD, lightweight PRD, MVP requirements. Create lightweight PRDs for small features, internal tools, and early ideas.
prd
Trigger: PRD, product requirements, technical product spec. Create rigorous PRDs for high-stakes, cross-team, regulated, or security-sensitive work.
bidirectional-translation
Trigger: BDT, bidirectional translation, retraduccion, traduccion inversa, /learn drill, language-loop active wave. Delayed retranslation drill: native → target from memory, compare vs the original, notice differences.
language-loop
Trigger: language-learning topics inside /learn (learn english, aprender ingles, language path, target language in mission). Input-first two-wave session flow: bilingual dialogue units, delayed retranslation, gap-inbox adoption.
architecture-impact-review
Trigger: architecture impact review, layer boundaries. Decide whether legacy risk is local or architectural.
behavior-characterization
Trigger: behavior characterization, observable behavior. Record what legacy code does today.
chained-pr
Compatibility contract for splitting oversized work into chained or stacked PR review slices. Trigger: A workflow names chained-pr or needs a chained PR strategy for review-size risk.
cohesion-coupling
Trigger: cohesion, coupling, circular dependency, layer mixing. Detect low cohesion and excessive coupling.
complexity-big-o
Trigger: complexity, Big O, cyclomatic, nested loops, queries in loops. Evaluate control and algorithmic complexity where it matters.
dependency-inversion
Trigger: dependency inversion, DIP, ports, interfaces, adapters. Detect concrete dependency risks at boundaries.
dependency-seam-detection
Trigger: dependency seam detection, hard dependencies. Find seams that make legacy code testable.
dry-business-knowledge
Trigger: DRY, duplicated business knowledge, duplication. Distinguish harmful knowledge duplication from harmless similarity.
general-naming-readability
Trigger: naming, readability, identifiers, intent, clarity. Evaluate naming and readability with language-neutral principles.
god-object-detection
Trigger: God Object, Large Class, too many collaborators. Detect oversized objects with too many responsibilities.
grilling
Interview 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.
input-validation-preconditions
Trigger: input validation, preconditions, boundary validation. Detect missing or duplicated preconditions.
java-naming-readability
Trigger: Java naming, readability, test names. Evaluate Java naming and readability with domain language.
kiss-yagni
Trigger: KISS, YAGNI, overengineering, speculative abstraction. Keep refactor plans simple and non-speculative.
logging-observability
Trigger: logging, observability, metrics, traces. Evaluate operationally useful logging for safe refactors.
null-safety
Trigger: null safety, nullability, Optional, NPE. Detect null hazards and conservative Java null-safety refactors.
open-closed-principle
Trigger: open closed principle, OCP, strategy, policy, polymorphism. Detect extension pressure without speculative patterns.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.