artifactor

Solid

Classifies raw pilot request → structured request with routing and an explicit unresolved strategic-basis gate. Keyword-fast (<200ms) or Haiku fallback (<60s). Does NOT create WP or call executor.

AI & Automation 61 stars 152 forks Updated today MIT

Install

View on GitHub

Quality Score: 83/100

Stars 20%
60
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

# /artifactor — Артефактор-Постановщик > **Роль:** DP.ROLE.058 Артефактор-Постановщик > **Триггер:** запрос без routing-tag (Маршрутизатор → Артефактор) или `/artifactor "текст"` > **Service Clause:** DP.SC.160 ## When to use Classifies raw pilot request → structured JSON with routing. The later WP Gate must also resolve how the work relates to a hypothesis; Artifactor does not invent that relation from keywords. Does NOT create WP or call executor. ## Обещание (контракт) **Вход:** сырой текст запроса пилота (любой длины, без routing-tag) **Выход:** JSON 7 полей → stdout: ```json { "task_type": "string", "class": "trivial | closed-loop | open-loop | problem-framing", "artifact": "string (одна строка на русском — существительное-результат)", "budget_estimate": "~Xh | ?", "confidence": "high | low", "routing_tag": "string", "resolution_path": "keyword | llm" } ``` **Инвариант:** - НЕ создаёт РП, НЕ вызывает исполнителя, НЕ задаёт уточняющих вопросов - `confidence=high` только при keyword-пути; `confidence=low` при LLM-пути - При запросе <5 слов: вернуть `{"error": "INSUFFICIENT_INPUT"}`, стоп - `budget_estimate: "?"` только при `problem-framing` или полной неопределённости - В handoff к WP Gate передать `hypothesis_relation: "unclassified"`. До выбора `tests | enables | responds | researches | operational` РП остаётся pending, а не запускается в работу. ## Стратегическое основание РП Артефактор не вправе приписать РП гипотезу без решения пилота....

Details

Author
TserenTserenov
Repository
TserenTserenov/FMT-exocortex-template
Created
7 months ago
Last Updated
today
Language
Shell
License
MIT

Integrates with

Similar Skills

Semantically similar based on skill content — not just same category

AI & Automation Listed

add-artefact-graph

Use when a command, skill or agent needs to ask what an artefact relates to — resolving a stated question to the verb that answers it, the eleven verbs, the two interfaces that answer them identically, the case of an agent with no route at all, and the standing list of what the graph still cannot see.

9 Updated today
brabos-ai
Data & Documents Listed

artifact-formalizer

Use BEFORE authoring a specification (TASK, ARCHITECTURE, PLAN, task files, issue records), a CHANGELOG entry or release notes, and AFTER to audit one that reads as an essay: long sentences, evaluative words, maxims, personification, metaphors, reasoning inside requirements, emoji as severity. Self-probing scanner; never changes the document's language. Triggers: «формализуй задачу», «проверь регистр», «напиши CHANGELOG», "formalize this spec", "reads like an essay", "write the spec", "release notes".

6 Updated 4 days ago
MatrixFounder
AI & Automation Listed

ai-work-assetization-diagnoser

AI 工作资产化诊断器 / Assetization Router:当用户提供 AI 协作会话、重复任务、prompt、工作流描述、 团队 AI 使用场景或一次成功交付过程,并要求判断应该沉淀成 Prompt、Context Pack、Workflow、Skill、 Loop、System,或根本不值得沉淀时使用。它只做诊断、分层和下一步资产建议,不替代具体 Skill 创建、 PRD 起草、调研、实现或自动化执行。不用于普通事实查询、一次性文案、trace 根因分析或高责任专业判断。

13 Updated 3 weeks ago
PANGKAIFENG