with one click
morpheus-docs
morpheus-docs contains 52 collected skills from HewlettPackard, with repository-level occupation coverage and site-owned skill detail pages.
Skills in this repository
Behavioral rules that make AI coding agents more reliable — verification, self-correction, and scope discipline.
Debugging guidance and structured report template for thorough bug investigation, evidence gathering, and root cause documentation.
Cold-audit a completed delivery — verify the spec was actually delivered, challenge performative claims, and produce a what-landed report.
Guidelines for generating self-contained HTML mockups that look professional and are easy to iterate on.
Shared implementation guidance for making minimal, correct, maintainable code changes that fit existing systems.
The doctrine for `/roadmap-review` — interactive triage of roadmap-shape drift, walked one item at a time, with paste-ready resolution phrasing for the active sizing lens.
When work would produce 2+ related specs, prefer initiative-first composition over `/design` × N siblings. Carries the canonical "multiple related specs" phrasing that both interactive triage (`/roadmap-review`) and design-time routing (`/design`) quote.
Defines the spec document structure and conventions for feature designs and bug diagnoses in the hero workflow.
The shared 6-tier size ladder, per-type bands, and the nudge protocol delivery leads use to surface promotion recommendations on oversized specs.
Detect the language, framework, and tooling stack of a project or set of files to load the right engineering skills.
Generate native SwiftUI mockups, compile them, and capture real screenshots — no HTML approximation.
API guidance for contract design, boundary validation, compatibility, versioning, and consumer-safe changes.
Shared software architecture principles focused on right-tool decisions, scale-readiness, and avoiding unnecessary distributed complexity.
How agents automatically detect and persist learnings at the end of major workflows.
Protocol for challenging and revising a bug diagnosis — layer vs reject modes, investigation history format, re-diagnosis instructions.
Methodology and rules for scrubbing codebases — removing dead code, weak types, duplication, bad comments, defensive programming, and legacy cruft.
How delivery leads use hero relevant output to equip specialist agents with relevant conventions, past work, decisions, and known risks.
How to analyze a codebase for recurring patterns and write effective convention specs that standardize them.
How agents pick the right cross-repo interaction mode (advisory call / spec-out call / async handoff / convention import) and compose well-shaped peer-call prompts. Load when a session touches a sibling Hero workspace's surface.
Database implementation guidance for schema design, migrations, queries, indexing, and rollout safety.
Guide for running deep code scanning with LLM-generated symbol descriptions.
How to evaluate libraries for health, security, license compatibility, and size impact before adopting or continuing to use them.
Operational guidance for CI/CD, deployments, runtime configuration, environment parity, and observability-aware system delivery.
Documentation guidance for writing accurate, concrete, and operationally useful technical docs.
Generate a comprehensive project intelligence report — the thing managers actually read.
Go implementation guidance for package design, explicit error handling, concurrency, and operational simplicity.
Bootstrap a new project's Hero workspace with stack-appropriate conventions, decisions, and initial specs.
Groovy implementation guidance for application code, Gradle logic, DSLs, and Spock-oriented testing.
Production incident handling covering triage, evidence gathering, mitigation, communication, and post-mortem practices.
Guidance for external integrations, service boundaries, webhooks, retries, idempotency, and failure-aware interface design.
Create a well-formatted local report for a provided list of issues.
Java implementation guidance covering service structure, strong typing, testing, and common JVM application concerns.
JavaScript and Node implementation guidance for modules, async behavior, data validation, and runtime safety.
Format and quality bar for the `## Kickoff` section that lives in every spec. Defines a paste-ready cold-start prompt the user can drop into a fresh session.
Analyze captured knowledge for patterns — detect repeated decisions, suggest conventions, surface "you keep running into X" insights.
Safe migration patterns for databases, APIs, libraries, and data transformations with zero-downtime techniques and mandatory rollback planning.
When and how to emit handoff state (UserAsk / NextSuggestion / SessionReflection) to the graph during work, so the projected NEXT.md and per-user handoff stay current without agent discipline on a tracked file.
Format and quality bar for the handoff briefing the agent maintains across sessions. Supports solo and team modes. Legacy mode — when next.projected is enabled, see skills/next-handoff-emit.md instead.
How agents detect and self-heal git merge-conflict markers in the projected NEXT files (`.hero/NEXT.md`, `.hero/next/*.md`) without resorting to hand-resolution.
How agents capture conversations, brainstorms, and thinking as notes in the Hero knowledge base.