github.com/JaviMontano/jm-adk-beta
| Skill | Added | Review |
|---|---|---|
persistent-memory-design skills/persistent-memory-design/SKILL.md Disena un scratchpad persistente en disco (Hypotheses/Decisions/Findings/Open) con solo conclusiones validadas que sobrevive a /compact y reset, se lee una vez y luego se referencia para no romper el prompt cache. | — — — Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: fdad39c | |
plan-mode-workflow skills/plan-mode-workflow/SKILL.md Disenar un gate de dos modos: explorar un repo desconocido en Plan Mode read-only, firmar un plan.md por hash, y bloquear escritura via hook hasta que la firma habilite Execute Mode. | — — — Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: fdad39c | |
pm-delivery skills/pm-delivery/SKILL.md Project and delivery management router: budgets, estimation, capacity, roadmaps, OKRs, risks, stakeholders, vendors, SLAs, team topology, and retrospectives. Topics: budget-management, capacity-planning, cost-estimation, okr-design, product-roadmapping, retrospective-facilitation, risk-assessment, sla-definition, stakeholder-mapping, team-topology, vendor-evaluation. | — — — Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: fdad39c | |
pristino-calibration skills/pristino-calibration/SKILL.md Read deterministic persona/mode/optimizer signals injected by persona-calibrate.sh and execute the contract: declare the persona on line 1, run the adaptive prompt optimizer (original/optimized/response), apply precedence Veracidad>Seguridad>Objetivo>Formato>Estilo, use evidence tags, and consolidate substantive work in the Canvas output contract. | — — — Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: fdad39c | |
product-analytics skills/product-analytics/SKILL.md Product and business analytics router: event instrumentation, KPIs, A/B tests, cohorts, funnels, real-time pipelines, and data visualization. Topics: ab-testing, analytics-events, cohort-analysis, data-visualization, funnel-analytics, kpi-framework, metrics-instrumentation, real-time-analytics. | — — — Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: fdad39c | |
project-create skills/project-create/SKILL.md Scaffold a Jarvis OS project P-NNN-slug under 02_Proyectos/ with compliant CLAUDE.md, MEMORY.md and TAREAS.md (P07); missing-only, never clobbers local edits. | — — — Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: fdad39c | |
prompt-chaining-design skills/prompt-chaining-design/SKILL.md Descomponer tareas grandes en pase local tipado y pase de integracion sobre resumenes, con schemas de transicion entre pases. | — — — Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: fdad39c | |
prompting-and-meta-prompting skills/prompting-and-meta-prompting/SKILL.md Turn vague intentions into durable, eval-ready prompts, meta-prompts, acceptance criteria, and prompt systems with anti-drift and safety gates. | — — — Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: fdad39c | |
provenance-engineering skills/provenance-engineering/SKILL.md Disenar pipelines de extraccion/sintesis con provenance tipada: invariante no hay claim sin source, conflictos marcados y escalados a humano, nunca promediados ni resueltos en silencio. | — — — Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: fdad39c | |
qbr-quarterly skills/qbr-quarterly/SKILL.md Cadencia QBR (P13): audita el trimestre cerrado contra OKRs y planifica el proximo con evidencia trazable. | — — — Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: fdad39c | |
revisor-veracidad skills/revisor-veracidad/SKILL.md Audita un texto, etiqueta cada afirmacion no reproducible con un tag de veracidad y propone el siguiente paso concreto de verificacion. | — — — Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: fdad39c | |
runtime-routing skills/runtime-routing/SKILL.md Route agentic work across Claude, Codex, Gemini, Antigravity, VS Code, and local adapters, picking the lowest-permission runtime that has evidence for the task and labeling every unverified capability. | — — — Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: fdad39c | |
safe-scripting-and-bash skills/safe-scripting-and-bash/SKILL.md Design and review safe, portable, dry-run-first Bash scripts for local agentic workflows; gate writes, destructive commands, secrets, and offline validation. | — — — Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: fdad39c | |
sales-bizdev skills/sales-bizdev/SKILL.md Router for sales and business development in an ES/EN consulting context — prospecting, outreach, dossiers, proposals, pitches, and collateral. Topics: b2b-outreach, client-dossier, client-prospecting, executive-pitch, lead-generation, proposal-writing, sales-collateral. | — — — Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: fdad39c | |
security skills/security/SKILL.md Router for application security playbooks: auth, RBAC, input sanitization, headers/CORS, rate limiting, audits, security testing. Resolve one topic, load one reference. Topics: architecture, audit-security, auth-architecture, cors-configuration, dual-layer-verification, http-headers, input-sanitization, rate-limiting, rbac-patterns, testing. | — — — Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Version: fdad39c | |
self-correction-loops skills/self-correction-loops/SKILL.md Construir verificacion cruzada declarado-vs-calculado con mismatch flag tipado y escalada a humano; recomputo independiente, epsilon justificado, nunca corregir numeros en silencio. | — — — Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: fdad39c | |
seo-growth skills/seo-growth/SKILL.md SEO and conversion growth router: technical SEO, content SEO, landing pages, funnels, CRO, trust patterns. Topics: conversion-optimization, funnel-design, indexability-validator, landing-page-builder, landing-pages, seo-architecture, seo-content, social-proof. | — — — Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: fdad39c | |
session-lifecycle-management skills/session-lifecycle-management/SKILL.md Decidir resume vs fork vs fresh con summary tipado segun validez de contexto y deteccion de tool results stale. | — — — Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: fdad39c | |
session-workspace skills/session-workspace/SKILL.md Router for agent session lifecycle: bootstrap, protocol, state/context-window management, compaction preservation, notifications, end-cleanup. Topics: context-window-management, notification-handler, pre-compact-context, session-end-cleanup, session-manager, session-protocol, session-start-bootstrap. | — — — Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: fdad39c | |
skill-foundry skills/skill-foundry/SKILL.md Router for building/certifying agentic assets — skills, agents, commands, prompts, hooks, MCP servers, workflows. Topics: agent-creator, assembly-skill, auto-prompt-matching, benchmark-skill, certify-skill, design-skill, hook-creator, mcp-creator, meta-skill-creator, meta-skill-indexer, prompt-creator, prompt-forge, skill-search, workflow-creator, workflow-forge, x-ray-skill. | — — — Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: fdad39c |