skillZs
★ LIVE SKILL TAGS ★
>>> LIVE SKILLS INDEX <<<
* OPEN SOURCE *
NO LOGIN, NO TRACKING
※ REAL INSTALL DATA ※
← back to all skills
arthurzakirov/systemsmith175 installs

engineer-agentic-ai

Translate natural-language requests about AI-agent behavior, skills, MCP tools/servers, prompts, routing, context loading, memory, hooks, plugins, permissions, delegation, portability, or other agentic-system behavior into the concrete runtime mechanism and change surface. Use when a request is phrased as what the AI should understand/do rather than how the target harness actually observes, triggers, routes, persists, or enforces that behavior.

How do I install this agent skill?

npx skills add https://github.com/arthurzakirov/systemsmith --skill engineer-agentic-ai
view source ↗

Is this agent skill safe to install?

  • Gen Agent Trust Hubpass

    The skill provides a comprehensive engineering framework and documentation for designing and implementing agentic AI systems. It covers runtime models, interaction layers, and implementation procedures for platforms like OpenAI Codex and Anthropic Claude Code. No security risks or malicious behaviors were identified.

  • Socketpass

    No alerts

  • Snykwarn

    Risk: MEDIUM · 1 issue

What does this agent skill do?

🛠️ Engineer Agentic AI

Translate desired agent behavior into mechanisms the target runtime can observe, trigger, execute, persist, and verify.

🗂️ Contents

<a id="purpose"></a>

🎯 Purpose and applicability

Use this skill when a request describes what an agent should understand, decide, remember, trigger, prevent, or accomplish, but the concrete runtime mechanism is missing or uncertain. It applies to instructions, skills, routing, tools, MCP servers, hooks, permissions, plugins, automations, persistence, delegation, and related agent-system behavior.

The outcome is an implemented and behaviorally verified mechanism—or an explicitly retained problem-space requirement when the runtime chain cannot yet be closed.

<a id="framework"></a>

🧭 Engineering framework

Use this as the single end-to-end process:

  1. Preserve the problem-space intent. State the observable outcome without prematurely turning it into prompt wording or a provider feature.
  2. Route the investigation. Load only the narrowest references required by the current uncertainty using Reference routing.
  3. Operationalize the behavior. Connect observable signal and evidence → trigger/lifecycle event → decision rule → actuator → persistence → verification. When the target runtime actually involves cooperating agents or surfaces, map each participant's available context, instructions, authority, and actions; design the required handoffs and truthful result attribution. Do not turn one application's workflow steps into universal agent behavior. Include reliability and miss-cost requirements. If a required link is unavailable, keep the outcome in the problem space rather than calling it implemented.
  4. Choose the mechanism and surface. Select the lightest available mechanism that can meet the required reliability; verify current provider capabilities when the choice depends on them.
  5. Implement canonically. Change the authoritative instruction, skill, hook, tool, permission, plugin, script, automation, or configuration surface and validate its propagation path.
  6. Validate real behavior. Exercise the mechanism through a representative agent interaction or runtime event. Test the observable outcome, not only syntax, file presence, or plausible prose.
  7. Diagnose and iterate. On failure, trace guidance freshness, trigger match, visible evidence, rule specification, routing/selection, actuation, permissions, persistence, and propagation; adjust the mechanism or test and run it again. Use positive, negative, boundary, and repeated cases when behavior is model-mediated or routing-dependent.
  8. Promote and hand off. Promote only after the required behavioral evidence exists. Refresh deployed/generated copies, record remaining unknowns and tested scope, and retire or mark any superseded wishlist item.

The detailed operationalization, validation, debugging, and promotion methods live in the Agent engineering process; do not recreate parallel procedures in this file.

<a id="reference-routing"></a>

📚 Reference routing

Load a reference only when its condition matches the current decision or failure.

WhenReadUse it for
Translating, validating, debugging, or promoting an agent behaviorAgent engineering processOperationalization, mechanism selection, behavioral testing, failure diagnosis, and wishlist promotion.
Establishing how context, tools, hooks, state, sessions, compaction, or delegation behaveAgent runtime modelRuntime mechanics and Codex-specific lifecycle evidence.
Diagnosing selection, metadata, interface boundaries, or missing enforcementInterface, routing, and control designPre-selection routing versus post-selection execution and control strength.
Reasoning about interaction surfaces, cooperation among distinct agents, permissions/approvals, interruptions, background work, or result deliveryInteraction runtime modelMap the actual participating actors, their capabilities and handoff contracts, action attribution, lifecycle, and return paths; keep example workflows non-normative.
Designing a reusable artifact across identities, machines, operating systems, or providersPortability and provider mappingConcept-first portability and provider-neutral wording.
Needing an exact provider filename, directory, manifest, or settings locationProvider path referenceCurrent provider-specific path mappings and sources.
Analyzing context size, tokens, caching, compaction cost, allowances, credits, or billingToken usage and cost modelUsage evidence, cache mechanics, product accounting, and optimization.

<a id="quality-gates"></a>

✅ Quality gates

A change is ready only when:

  • the operationalization chain is complete, or the missing link is explicitly retained as an unresolved requirement;
  • the chosen mechanism and routed references support the required reliability without competing canonical rules;
  • each instruction targets an agent with the required observations and actuator, or explicitly tells the recipient to request another agent's action; user-visible claims truthfully attribute the actor and distinguish requests, attempts, and verified outcomes;
  • concrete task sequences (such as editor navigation or user checkpoints) are required only when the specific outcome calls for them, not inherited from unrelated examples;
  • behavior validation proves the intended outcome on the stated surface and scope;
  • the canonical source, propagation path, and deployed/generated state are verified; and
  • the handoff names remaining unknowns and completes the applicable wishlist-to-production lifecycle.

Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.

<a href="https://skillzs.dev/skills/arthurzakirov/systemsmith/engineer-agentic-ai">View engineer-agentic-ai on skillZs</a>