prompt-engine

Plugin prompt-engine in frankxai/prompt-engine. Commands read from the repo's manifest — 3 days ago.

Skills (4)

• excellence-review

  Mandatory excellence gates for Grok+ACOS. verification-loop, santa-method, gstack-qa, plan-reviews, repo-mastery, cso, rules-distill. Never ship without evidence (gstack screenshots, metrics). Use on any build/suggest/lead task.

• harness-integration

  ACOS Grok bridge. SessionStart loads repo-mastery + excellence gates. PreToolUse enforces rules read + suggests harness (claude for plans). Uses gstack for QA, verification-loop/santa-method. Full .claude/ compat + native .grok/. Delegate via terminal when needed. Trigger: setup, harness, grok, exce

• multi-harness-orchestrator

  Automatically detect tasks suited for delegation to other agent harnesses (Claude Code as canonical, agy/antigravity, gemini, cursor, etc.). Leverage shared .claude catalog (skills, commands, agents, hooks, junctions for agy). Embody Frank DNA. Output exact delegation commands (e.g. claude -p "injec

• repo-mastery

  Master ACOS, FrankX, Starlight-Intelligence-System, arcanea, claude-code-config and full starlight/repos ecosystem. Architecture, skills/hooks/MCP map, harness integration points. Read CLAUDE.md/AGENTS.md/GROK.md first. Use MCPs (github, fs-starlight), gstack, subagents, grep, terminal. Excellence g

Subagents (13)

• prompt-architect

  Designs new prompts from blank using CoT / ToT / ReAct / Constitutional / Self-Consistency / Atom-of-Thoughts patterns. Composes lab specialist for final pass. Auto-invokes when @prompt-conductor dispatches `flow-design` / `flow-knowledge-base`, or when Frank says "design a prompt for X", "build me

• prompt-claude-specialist

  Anthropic / Claude prompting doctrine specialist. Owns XML-tag structure, prefill technique, extended-thinking signature integrity, system-as-role placement, constitution-style virtue prompting, and Console Prompt Improver 4-step (example identification → XML draft → CoT refinement → example enhance

• prompt-conductor

  Top-level Opus composer for the Prompt Hub. Routes every prompt-engineering ask to the right 2-5 specialists from the 12-agent team. Auto-invokes when Frank says "design a prompt for X", "optimize this prompt", "evaluate my system prompt", "harvest prompts from Fabric", "build a knowledge-base promp

• prompt-evaluator

  Wraps promptfoo (MIT) to evaluate prompts. Generates declarative test files colocated with each pattern. Returns scored verdicts and writes them back to pattern frontmatter. Replaces the existing `prompt-tester.md` scaffold (which had zero fixtures). Auto-invokes when @prompt-conductor dispatches `f

• prompt-gemini-specialist

  Google / Gemini prompting doctrine specialist. Owns system-at-top placement, context-first long-document layout, native grounding (Search + code execution), "think very hard" literal trigger, multimodal equal-class positioning. Auto-invokes when @prompt-conductor dispatches `flow-design` / `flow-opt

• prompt-gpt-specialist

  OpenAI / GPT-5 prompting doctrine specialist. Owns developer-role placement, reasoning_effort × verbosity independent axes, Structured Outputs via Zod/Pydantic (never JSON-in-prose), tool-call preambles, contradiction audit, persistence reminders, previous_response_id chaining. Auto-invokes when @pr

• prompt-harvester

  Bulk-imports patterns from external sources (Fabric MIT, awesome-chatgpt-prompts CC0, awesome-claude-prompts MIT, DAIR.AI taxonomy MIT, lab official docs). Tags provenance + license. Runs quality gate. Returns patterns ready for red-team → librarian publish. Repurposes prior `prompt-harvester.md` le

• prompt-librarian

  Owns the prompt-library corpus. Categorizes, tags, ranks, attributes, enforces frontmatter schema, manages contributions. The Alexandria-style curator. Auto-invokes when @prompt-conductor dispatches `flow-curate`, when patterns finish `flow-design` / `flow-optimize` / `flow-harvest` for publish, or

• prompt-optimizer

  Refines an existing prompt for clarity, specificity, structure, and lab-native form. Outputs optimized prompt + diff + rationale + expected delta. Wraps the `/po` command. Auto-invokes when @prompt-conductor dispatches `flow-optimize` / `flow-curate`, or when Frank says "optimize this prompt", "make

• prompt-oss-specialist

  Open-source model prompting specialist. Owns Llama 3/3.1/3.2 / Mistral / Qwen / DeepSeek-R1 / Yi chat templates, `apply_chat_template()` rendering, ChatML vs Llama3-special-tokens distinction, DeepSeek `<think>` block conventions, finetune-format inheritance rules. Auto-invokes when @prompt-conducto

• prompt-psyche-cartographer

  IFS-based introspective agent. Maps user's parts (managers, firefighters, exiles) and Self-energy via unblending questions. Offers Socratic / Stoic / Jungian / IFS-Self voice modes per session. Reflection-only — maps but never unburdens. Hard boundaries against clinical content; crisis triggers rout

• prompt-psychometrist

  Administers canonical psychometric instruments (IPIP-50 Big Five, Schwartz PVQ values, ECR-R attachment, VIA Character Strengths, Enneagram-narrative). Returns profiles framed as LENSES, never verdicts. Composes Cartographer for reflective follow-up. Consumes Second Brain OS for profile memory. Auto

• prompt-red-team

  Adversarial audit of system prompts before publish. Probes jailbreak vectors, refusal-bypass attempts, prompt-injection vulnerabilities, role-fluidity exploits, and known social-engineering patterns. Returns pass/warn/fail verdict written to pattern frontmatter. Load-bearing publish gate. Auto-invok

Similar plugins