2 Commits

Author	SHA1	Message	Date
freemo	47b4c5fbfb	docs(skill): final pass — 2 new trees, expanded trees, reference file completions ... SKILL.md (1,878 → 2,099 lines, 23 → 25 decision trees): New 'Is my work done?' tree — comprehensive Definition of Done checklist synthesising all requirements across implementation, three-level testing (unit/integration/benchmarks), coverage ≥ 97%, five CI quality checks, commit anatomy (atomic, body, footer), documentation (changelog, docstrings, CONTRIBUTORS.md), PR fields (description, dep direction, Epic scope, milestone, Type label), CI checks, and issue state transitions. New 'What design pattern should I use?' tree — all 24 patterns from CONTRIBUTING.md categorised across Creational (Factory, Abstract Factory, Builder, Prototype, Singleton, Object Pool, DI), Structural (Adapter, Bridge, Composite, Decorator, Facade, Flyweight, Proxy, Module), Behavioral (Chain of Responsibility, Command, Iterator, Mediator, Memento, Observer, State, Strategy, Template Method, Visitor, Null Object), and Architectural (Repository, Unit of Work, Service Layer, MVC, CQRS, Event Sourcing, Specification). Every pattern includes a when-to-use description and a CleverAgents-specific example. Expand 'Am I about to write code?' — link to new patterns tree. Expand 'Am I writing tests?' — add And/But/Outline Gherkin keywords with examples, add Scenario Outline explanation, add naming good/bad examples with anti-pattern list, expand integration test guidance with what good integration tests exercise (CLI, DB, filesystem, service layer), expand Hypothesis section with 6 specific use cases and recommended strategies to build. Expand 'Am I about to commit?' — improve commit body guidance with a worked example showing what to write (context, why this approach, risks, caveats). Expand 'Am I triaging?' — add Epic/Legendary triage rules (no point estimates, no milestone assignment, sign-off labels required for closure). Add two branches to master decision tree for new trees. Reference files: references/testing/README.md (187 → 296 lines): - Add Gherkin Quality Guidelines section: Given/When/Then semantics table, Scenario Outline explanation with example, naming rules with good/bad table, common anti-patterns (implementation details, multiple behaviors, missing Then) - Add Property-Based Testing (Hypothesis) section: when-to-use table with 6 specific CleverAgents use cases, recommended strategies to build, integration with Behave step definitions with worked example references/langchain-langgraph/README.md (307 → 375 lines): - Add RxPY Reactive Streams section: Subject vs BehaviorSubject vs ReplaySubject decision table with when-to-use and code examples, key operators table with use cases and code examples, backpressure management patterns (debounce vs throttle_first with examples), and clear list of what RxPY is NOT for references/toolchain/README.md (271 → 272 lines): - Add Hypothesis to tool table (property-based testing, nox -s unit_tests) references/ci-cd/README.md (124 → 131 lines): - Fix project-specific version number in release example (v3.6.0 → generic v<MAJOR>.<MINOR>.<PATCH>) - Add release failure recovery procedure (verify secrets → build locally → delete tag → fix → re-tag) ISSUES CLOSED: #0	2026-04-15 19:40:35 +00:00
freemo	82471f87f0	docs(skill): add cleveragents-contributing project-specific skill ... New skill covering all CONTRIBUTING.md project-specific rules that supplement or override the generic cleverthis-guidelines skill. Prominently declares override precedence at the top of SKILL.md and in every reference file — this skill's rules apply unconditionally when they conflict with the general skill. SKILL.md (839 lines) contains: - Override notice table comparing cleverthis-guidelines vs this project for 18 specific topics (framework, directories, tool names, etc.) - Master decision tree routing all project-specific situations - 9 detailed decision trees: file placement (exact directories), tests (Behave/Robot Framework rules), TDD bug fix workflow (full 6-step with branch naming), TDD issue-capture test (exact three-tag system with AssertionError enforcement), nox session reference (all sessions + CI job mappings + required-for-merge), CI failure diagnosis (per-job remediation), plan CLI (v3 vs legacy, ULID, storage backends), LangChain/LangGraph code (TypedDict, MemorySaver, BaseLanguageModel, FakeListLLM, canonical node pattern), Python imports (top-of-file, TYPE_CHECKING exception), dev env setup (complete tool inventory), and release process (backwards compat policy, Docker, secrets) - Key Numbers table with 33 project-specific values Reference files (1254 lines total): - testing/README.md: Behave rules, Robot Framework, TDD tag system with full examples and validation rules, AssertionError requirement, coverage threshold, mock placement, LangGraph testing, ASV benchmarks - ci-cd/README.md: all 13 CI jobs with nox session mappings, 3 workflow triggers, 5 required-for-merge checks, secrets table, caching policy, nightly quality sweep, branch protection - toolchain/README.md: complete nox session catalogue, Pyright prohibition on # type: ignore, ruff config, Hatch, pyproject.toml as single source, pre-commit setup, Commitizen, Python import rules with examples, error handling patterns with Python code - langchain-langgraph/README.md: TypedDict state, verb-based node naming, MemorySaver, conditional edges, BaseLanguageModel abstraction, prompt templates, sync+async requirement, output parsing, env var configuration, LangSmith disabled by default, retry decorators, canonical node template, FakeListLLM testing, state/workflow/streaming/memory test patterns - file-organization/README.md: exact directory map, per-directory rules and prohibitions, docs/specification.md authority, BDD step-file naming rules - cli-workflow/README.md: v3 vs legacy comparison table, ULID format, why mixing is impossible (separate storage backends), error diagnosis for common failure modes, manual migration steps, backwards compat policy ISSUES CLOSED: #0	2026-04-15 18:50:51 +00:00