2 Commits

Author	SHA1	Message	Date
freemo	85ac059489	docs(skill): remove CleverAgents-specific content and finish tool generalisation ... Remove from SKILL.md and all reference files: - 'Am I choosing between Legacy and v3 plan workflow?' decision tree - LangChain/LangGraph sections (write-code tree, testing tree, code-style README, testing README) - FakeListLLM / MemorySaver / TypedDict LangGraph references - Backwards-compat pre-v3.0.0 policy block (project-version-specific) - v3 ULID format and Backwards-compat-starts rows from Key Numbers table - v3 Plan Lifecycle vs Legacy table from code-style README - Master-tree branch pointing to the v3/legacy workflow tree Generalise across all reference files: - commits/README: pre-commit checklist uses 'task runner session (e.g. nox -s X)' - pull-requests/README: fix approval count 2->1 with self-approval permitted; remove 'neither approver may be original author' (project allows self-approval); generalise automated-checks table command column - testing/README: remove LangChain/LangGraph Testing section; generalise all bare nox commands with task-runner framing and language note at top - code-style/README: rewrite General Principles to language-agnostic tooling guidance; generalise Import Guidelines with Python/Java/TS examples; rename and generalise Type Safety section; remove entire LangChain/LangGraph Best Practices section; remove entire v3 Plan Lifecycle vs Legacy section - security/README: generalise bare nox -s security_scan reference - issue-tracking/README: generalise subtask examples (Behave/nox) ISSUES CLOSED: #0	2026-04-15 18:32:33 +00:00
freemo	8193545fb5	feat(skills): add cleverthis-guidelines agent skill ... Adds a comprehensive opencode skill under .opencode/skills/cleverthis-guidelines/ covering every rule, regulation, directive, and guideline governing CleverThis projects and company operations. Synthesized from CONTRIBUTING.md and the CleverThis Operations Code (C.O.C. v0.4, 70 pages). - 12 files, 2,384 lines across 11 reference categories - 1,059-line SKILL.md with 16 exhaustive decision trees covering every procedural situation: writing code, committing, submitting PRs, code review, creating issues, applying labels, ticket state transitions, sprint planning, triaging, point estimation, definition of done, authoring documents, confidentiality classification, security/credentials, FOSS, bug fixes (TDD), architectural decisions, and escalation paths Reference files cover: commits/ — Conventional Changelog format, atomic commit rules, pre-commit pull-requests/ — all 12 PR requirements, review process, merge criteria testing/ — BDD/Behave (unit), Robot Framework (integration), 97% coverage threshold (project-specific), TDD bug fix workflow, mocking rules issue-tracking/ — ticket hierarchy (Issue→Epic→Legendary), all quality criteria, mandatory issue sections, full label system (State/Type/Priority/ MoSCoW/Special), lifecycle flow, dependency direction rules sprints/ — DSDM, 6-stage triaging, MoSCoW, poker point estimation, all 4 sprint ceremonies with complete rule sets code-style/ — SOLID, design patterns, import rules, error handling, type safety, LangChain/LangGraph guidelines, v3 vs legacy plan lifecycle security/ — gopass-only password management, Yubikey rules, encryption policy information/ — 5 confidentiality stamp levels, document authoring, email conventions organizational/ — C-level hierarchy, ELB, OCRB, all 12 committees, personnel review project-tools/ — nox commands, CI/CD, release process, Hatch, Commitizen setup open-source/ — FOSS governance, open standards mandate, POSIX compliance Key project-specific facts documented: - Coverage threshold: 97% (overrides C.O.C. baseline of 85%) - BDD framework: Behave (not pytest alone) - Type checker: Pyright (never disabled, no type: ignore) - Bug fixes: mandatory TDD workflow with @tdd_expected_fail tagging	2026-04-15 17:51:07 +00:00