feat: complete uk companies house handler v2a (#220)

[Areen-09]

Description

Completes Phase v2a of the UK Companies House skill upgrade.

• Context/State tracking: The skill now extracts and expects a strict 5-key context schema to carry forward company_number, company_name, last_action, officer_filter, and selected_transaction_id between steps without forcing the LLM to repeatedly extract and pass them. _get_officers safely falls back on company_name via context to save API calls.
• Partial/Pipeline support: Added partial envelope status and pipeline parameter schema in preparation for the upcoming Phase v2b orchestration.
• Examples Update: Modernized gemini_uk_companies_house_handler.py to be a fully interactive chat loop, and updated uk_companies_house_handler_common.py to natively demonstrate context passing across actions.

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

New or updated skill

Skip unless this PR adds or changes files under skills/.

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

Logic, cognition, tests

• Deterministic skill.py (no ad-hoc LLM-generated execution paths)
• instructions.md explains when and how to use the skill
• card.json issuer matches manifest when present
• test_skill.py 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)

No safety or constitution changes. The skill remains strictly read-only for public company data.

Related Issues

Completes #220 v2a

[rosspeili]

Hey @Areen-09, thanks for this, looks clean and good as always!

A few small things before merge:

1. Update docstring in gemini_uk_companies_house_handler.py, still says "non-interactive" but it's now an interactive REPL
2. Clarify pipeline / partial, both are v2b prep but not used yet. Add a quick note in instructions.md so agents don't expect them, or if you will work on v2b right after, maybe ignore this and patch in next pr?
3. Add a couple new tests:
   • get_officers with context-only company_number
   • officer company_name fallback via profile fetch

After this merges, you can tackle v2b (pipeline) and v2f (agent playbook) in follow-up PRs or a signle PR, up to you.

Nice work keeping it focused. Merge once those small fixes are in <3

[Areen-09]

Thanks so much for the detailed review @rosspeili ! <3

I've addressed all the requested changes:

• Updated the docstring to reflect the interactive REPL.

• Added a note in instructions.md clarifying that pipeline/partial are v2b preparation and aren't used yet.

• Added the new tests for:

  • get_officers with context-only company_number
  • company_name fallback via profile fetch

Once this PR is merged, I'll start working on the next phases (v2b pipeline and then v2f agent playbook). Thanks again for the review!