language-specialists

---

LIBRARY-FIRST PROTOCOL (MANDATORY)

Before writing ANY code, you MUST check:

Step 1: Library Catalog

• Location: .claude/library/catalog.json
• If match >70%: REUSE or ADAPT

Step 2: Patterns Guide

• Location: .claude/docs/inventories/LIBRARY-PATTERNS-GUIDE.md
• If pattern exists: FOLLOW documented approach

Step 3: Existing Projects

• Location: D:\Projects\*
• If found: EXTRACT and adapt

Decision Matrix

Match	Action
Library >90%	REUSE directly
Library 70-90%	ADAPT minimally
Pattern exists	FOLLOW pattern
In project	EXTRACT
No match	BUILD (add to library after)

---

STANDARD OPERATING PROCEDURE

Purpose

Identify language-specific needs, select the correct specialist (Python or TypeScript), and ensure playbooks/examples/tests stay current.

Triggers

• Positive: Requests that specify a target language stack or need language-tailored guidance.
• Negative: Framework-agnostic prompts (use prompt-architect) or non-language-specific architecture (system-design-architect).

Guardrails

• Structure-first: maintain SKILL.md, readme, examples/, tests/, resources/; ensure child specialists mirror this structure.
• Constraint hygiene: extract HARD/SOFT/INFERRED needs (runtime, frameworks, tooling, quality gates).
• Routing safety: only assign to specialists with intact docs; flag missing artifacts.
• Confidence ceiling on routing decisions (inference/report 0.70; research 0.85; observation/definition 0.95).

Execution Phases

1. Intake: Capture language, framework, runtime, and constraints (quality, performance, deployment targets).
2. Routing: Choose python-specialist or typescript-specialist; include backup and escalation path.
3. Handoff: Provide context, constraints, and existing examples/tests relevant to the stack.
4. Validation: Confirm outputs meet language-specific standards (formatters, linters, test matrices).

Output Format

• Routing decision with constraints (HARD/SOFT/INFERRED).
• Selected specialist + reasoning and validation checks.
• Confidence statement with ceiling.

Validation Checklist

• Constraints captured and confirmed.
• Specialist selected from registry with healthy docs.
• Examples/tests referenced or gaps flagged.
• Confidence ceiling stated.

VCL COMPLIANCE APPENDIX (Internal)

[[HON:teineigo]] [[MOR:root:D-L]] [[COM:Dil+Yonetim]] [[CLS:ge_meta_skill]] [[EVD:-DI<gozlem>]] [[ASP:nesov.]] [[SPC:path:/skills/specialists/language-specialists]]

[[HON:teineigo]] [[MOR:root:E-P-S]] [[COM:Epistemik+Tavan]] [[CLS:ge_rule]] [[EVD:-DI<gozlem>]] [[ASP:nesov.]] [[SPC:coord:EVD-CONF]]

Confidence: 0.71 (ceiling: inference 0.70) - SOP rebuilt using prompt-architect routing clarity and skill-forge structure-first rules.