feat(linguistics): add korean_slang offline Gen-Z pack (#34)

[bd-c3]

Deterministic KB skill so host agents can interpret and generate modern Korean internet slang without wrapping an LLM.

Description

Fixes #34.

Adds linguistics/korean_slang: offline interpret / suggest / lookup over a September 2026 curated pack. Longest-first matching, honorific audience gates, constitution filters for slurs and appearance-policing slang. Also lands the new linguistics/ category (cat: linguistics, proposal dropdown, extras, catalog, example).

Criterion	Where
Interpret contract (translation, slang_breakdown, nuance, formality)	skills/linguistics/korean_slang/ + test_skill.py (issue example locked)
Deterministic offline execute(), curated kb/	lexicon.py, kb/*.json
Toxic-term filter; elders/work register	kb/constitution.json, suggest() audience templates
Catalog + five-provider snippets	docs/skills/korean_slang.md, Skill Library row
Example	examples/korean_slang_demo.py

Type of Change

• New Skill — new registry bundle under skills/
• Skill Upgrade — changes to an existing skill under skills/
• Bug Fix — incorrect runtime or framework behavior
• Documentation — docs, README, CONTRIBUTING only
• Framework Feature — skillware/core/ loader, env, adapters
• CLI — skillware/cli.py, docs/usage/cli.md
• Examples — examples/*.py, agent loops, examples/README.md
• Packaging — PyPI wheel, pyproject.toml, MANIFEST.in
• RFC / meta — templates, labels, CI, or large design doc

Checklist (all PRs)

• Linked GitHub issue (Fixes #… or Refs #…)
• Scope matches the issue — no unrelated refactors
• python -m black --check . and flake8 pass locally (or CI-equivalent subset)
• pytest skills/ and pytest tests/ pass locally when relevant
• CHANGELOG.md updated under [Unreleased] when user-visible behavior changes
• examples/README.md updated if this PR adds, renames, or removes a runnable script
• Ran pytest tests/test_registry_docs.py when skills, examples index, or agent-loops matrix changed
• Ran pytest tests/test_skill_docs.py when catalog Usage Examples or provider snippets changed

New or updated skill

Bundle and metadata

• Skill at skills/<category>/<skill_name>/ (from templates/python_skill/ or equivalent)
• manifest.yaml: name (full ID), version, description, parameters, constitution, real issuer
• Optional: short_description, issuer.github, issuer.org, requirements, env_vars

Effect, Directive, Assurance

• Deterministic skill.py (Effect; no ad-hoc LLM-generated execution paths)
• instructions.md (Directive) explains when and how to use the skill
• card.json (Presentation) issuer matches manifest when present
• test_skill.py (Assurance) covers execution and schema expectations
• SkillLoader.load_skill("<category>/<skill_name>") succeeds (or deps documented)

Documentation and catalog

• docs/skills/<skill_name>.md and row in docs/skills/README.md
• Usage Examples for Gemini, Claude, OpenAI, DeepSeek, Ollama per skill usage template

Constitution and safety (skills only)

Offline curated lexicon only, no network, no model calls, no invented 줄임말. Slurs and appearance-policing terms are omitted from glosses and never generated. audience=elders suppresses 반말 slang. Vulgar items are interpret-only unless vulgar_ok. Pack is a 2026-09 snapshot, not a living native speaker.

Related Issues

Fixes #34

[rosspeili]

LGTM! Outstanding work on this PR @bd-c3.

This is an exemplary new skill contribution that ticks every repository standard:

• Contract & Scope: Flawlessly delivers on Issue [New Skill]: Korean Pack S26 Small #34 with exact field parity (translation, slang_breakdown, nuance, formality) and clean canonical naming (linguistics/korean_slang).
• Constitutional Invariants: 100% deterministic, offline stdlib implementation (requirements: []), with robust slur/appearance-policing filtering and honorific register gating (audience="elders" / "work").
• Comprehensive Ecosystem Wiring: Lands the new linguistics/ category across GitHub labels, issue templates, CONTRIBUTING.md, extras, examples index, and automated label synchronization tests.
• Documentation & Verification: All 5 provider loops (Gemini, Claude, OpenAI, DeepSeek, Ollama) validated, 118 pack entries and 50+ stress simulations pass, full repository test suite (846 tests) is completely green alongside Black and Flake8.

No changes needed. Merging after CI finishes!

[bd-c3]

Ty @rosspeili, I am thinking of taking similar skill next #74 about GDPR module which involves heavy KB like MiCA, and want to propose similar EU AI Act skill if that is fine.