Skills Directory
Claude Skills by the-vibey-project
github.com/the-vibey-projectOnion layers for vibey (domain, application, infrastructure, cli, tui), import-linter, where new code belongs, the workspace tenants, and how to file a sub-doctrine. Use before adding a module under src/ or writing a standing rule.
Phases, jobs, ledger, handoff, rotation, and the no-loss gate — the core domain types and invariants in vibey.
How vibey drives claudeloop, codexloop, and the local engines — gptossloop (the sovereign default), and the opt-in qwenloop and claudeloop-local — the engine adapter pattern, tiers, argv building, and the conformance suite.
The 7-gate CI sweep (ruff check, ruff format, mypy, per-layer coverage × 4, lint-imports, bandit, pip-audit), what each gate catches, the other CI jobs, and the workspace tenants' own checks.
The release flow — merge train into develop, vibey-gh promote to main, vibey-engine.yml and krypton-app.yml publishing (develop to TestPyPI, main to PyPI), github-release.yml tags, and release-surfaces.yml docs, book and paper. Read before cutting a release.
The 100% per-layer coverage gates, running tests locally, Postgres integration tests (never mocked), property testing for rotation and no-loss gate, the chaos test, the test tree, and markers.
google-antigravity Agent + LocalAgentConfig, never-block policies, harness retarget. Consult before editing infrastructure/agent/.
Onion layers for agyloop (domain, application, infrastructure, cli), import-linter, and where new code belongs. Use before adding a module under src/agyloop/.
Where content belongs (routers vs skills vs docs), MkDocs strict build, PyPI-safe absolute README links.
CapacityState, TurnSignals, completion verdicts, waiting, and the run loop. Consult before editing domain/classify.py, waiting.py, completion.py, or loop.py.
How to run and fix ruff, mypy --strict, pytest, lint-imports, bandit, pip-audit, mkdocs. Consult when a gate fails.
gitflow, Conventional Commits, release-please, Trusted Publishing. Consult before branching, committing, or cutting a release.
Generated agyloop api command tree from Gemini REST discovery, drift gate. Consult before hand-writing api commands.
Fakes over mocks, FakeClock/FakeSleeper, Hypothesis, pytest markers. Consult before adding tests or mocks.
Explains how claudeloop integrates with claude-agent-sdk (ClaudeAgentOptions, ClaudeSDKClient vs query(), RateLimitEvent, ResultMessage, AssistantMessage, session discovery via list_sessions()) and the never-block-on-a-human design (permission_mode, can_use_tool, AskUserQuestion handling, hooks). Use this whenever building or modifying src/claudeloop/infrastructure/agent/ (the M2+ agent gateway, options builder, message translation, session catalog, capacity probe), whenever the user asks abo...
Explains claudeloop's onion architecture — the four layers (domain, application, infrastructure, cli), the import-linter contract enforcing them, and exactly where new code belongs. Use this whenever adding a new file, class, or function to src/claudeloop/, whenever unsure which layer something belongs in, whenever import-linter or lint-imports fails, or when the user mentions "onion architecture", "layers", "ports and adapters", "bootstrap.py", "composition root", or asks "where should this ...
Explains where different kinds of content belong in this repo (CLAUDE.md vs .claude/skills/ vs docs/), how to build and strict-check the MkDocs Material site, and the writing conventions used throughout (Roadmap admonitions, relative links, ADR format). Use this whenever writing or editing any file under docs/, whenever deciding whether new content belongs in CLAUDE.md, a skill, or docs/, whenever the user asks about documentation structure, or before adding a page to mkdocs.yml's nav. Make s...
Explains every value object and ADT in src/claudeloop/domain/ — CapacityState (Available/WindowExhausted/CreditsExhausted/AuthenticationFailed/BackendMisconfigured), TurnSignals classification, CompletionVerdict (Done/Continue/Blocked), the wait-probe policy in waiting.py, Budget/BudgetLedger, and the run-loop state machine in loop.py. Use this whenever reading, modifying, or extending anything in src/claudeloop/domain/ or tests/domain/, whenever the user asks about rate-limit classification,...
Covers how to run and FIX every quality gate in this repo — ruff (lint + format), mypy --strict, pytest with per-layer coverage, import-linter (lint-imports), bandit, and pip-audit. Use this whenever a quality gate fails locally or in CI, whenever the user asks how to lint, format, type-check, or run security scans on this codebase, or before opening a PR to run the full gate set proactively. Make sure to consult this whenever a ruff, mypy, lint-imports, or bandit error appears in tool output...
Explains the gitflow branch model (feature/* -> develop -> main), Conventional Commits requirements and types, how release-please automates version bumps and changelog generation from commit history, and how PyPI Trusted Publishing (OIDC) works via publish-to-pypi.yml. Use this whenever creating a branch, writing a commit message, opening a PR, asking about versioning, releases, or publishing to PyPI, or when a commit-msg hook rejects a commit. Make sure to consult this before writing any com...
Explains the design of the generated `claudeloop api ...` command tree — introspecting the anthropic SDK's resource class tree, binding methods to Typer commands, the --raw/--stream/--provider modifiers, and the CI drift gate that enforces 1:1 parity with the SDK. Use this whenever building or modifying src/claudeloop/infrastructure/api/ (introspect.py, binder, gateway, providers) or the generated CLI sub-app, whenever the user asks about the REST API surface, the anthropic SDK's endpoints, o...
Explains claudeloop's testing philosophy and pytest layout — fakes over mocks for every port, FakeClock/FakeSleeper for simulating multi-day waits without real sleeping, mandatory Hypothesis property tests for numeric/time-based invariants, per-layer coverage gates (100% for domain and application), and the documented # pragma no cover policy. Use this whenever writing or modifying any test under tests/, whenever the user asks how to test something in this codebase, mentions coverage, Hypothe...
Explains how claudeloop integrates with claude-agent-sdk (ClaudeAgentOptions, ClaudeSDKClient vs query(), RateLimitEvent, ResultMessage, AssistantMessage, session discovery via list_sessions()) and the never-block-on-a-human design (permission_mode, can_use_tool, AskUserQuestion handling, hooks). Use this whenever building or modifying src/claudeloop/infrastructure/agent/ (the M2+ agent gateway, options builder, message translation, session catalog, capacity probe), whenever the user asks abo...
Explains claudeloop's onion architecture — the four layers (domain, application, infrastructure, cli), the import-linter contract enforcing them, and exactly where new code belongs. Use this whenever adding a new file, class, or function to src/claudeloop/, whenever unsure which layer something belongs in, whenever import-linter or lint-imports fails, or when the user mentions "onion architecture", "layers", "ports and adapters", "bootstrap.py", "composition root", or asks "where should this ...
Explains where different kinds of content belong in this repo (CLAUDE.md vs .claude/skills/ vs docs/), how to build and strict-check the MkDocs Material site, and the writing conventions used throughout (Roadmap admonitions, relative links, ADR format). Use this whenever writing or editing any file under docs/, whenever deciding whether new content belongs in CLAUDE.md, a skill, or docs/, whenever the user asks about documentation structure, or before adding a page to mkdocs.yml's nav. Make s...
Explains every value object and ADT in src/claudeloop/domain/ — CapacityState (Available/WindowExhausted/CreditsExhausted/AuthenticationFailed/BackendMisconfigured), TurnSignals classification, CompletionVerdict (Done/Continue/Blocked), the wait-probe policy in waiting.py, Budget/BudgetLedger, and the run-loop state machine in loop.py. Use this whenever reading, modifying, or extending anything in src/claudeloop/domain/ or tests/domain/, whenever the user asks about rate-limit classification,...
Covers how to run and FIX every quality gate in this repo — ruff (lint + format), mypy --strict, pytest with per-layer coverage, import-linter (lint-imports), bandit, and pip-audit. Use this whenever a quality gate fails locally or in CI, whenever the user asks how to lint, format, type-check, or run security scans on this codebase, or before opening a PR to run the full gate set proactively. Make sure to consult this whenever a ruff, mypy, lint-imports, or bandit error appears in tool output...
Explains the gitflow branch model (feature/* -> develop -> main), Conventional Commits requirements and types, how release-please automates version bumps and changelog generation from commit history, and how PyPI Trusted Publishing (OIDC) works via publish-to-pypi.yml. Use this whenever creating a branch, writing a commit message, opening a PR, asking about versioning, releases, or publishing to PyPI, or when a commit-msg hook rejects a commit. Make sure to consult this before writing any com...
Explains the design of the generated `claudeloop api ...` command tree — introspecting the anthropic SDK's resource class tree, binding methods to Typer commands, the --raw/--stream/--provider modifiers, and the CI drift gate that enforces 1:1 parity with the SDK. Use this whenever building or modifying src/claudeloop/infrastructure/api/ (introspect.py, binder, gateway, providers) or the generated CLI sub-app, whenever the user asks about the REST API surface, the anthropic SDK's endpoints, o...
Explains claudeloop's testing philosophy and pytest layout — fakes over mocks for every port, FakeClock/FakeSleeper for simulating multi-day waits without real sleeping, mandatory Hypothesis property tests for numeric/time-based invariants, per-layer coverage gates (100% for domain and application), and the documented # pragma no cover policy. Use this whenever writing or modifying any test under tests/, whenever the user asks how to test something in this codebase, mentions coverage, Hypothe...
Onion layers for codexloop (domain, application, infrastructure, cli), import-linter, and where new code belongs. Use before adding a module under src/codexloop/.
Three-layer completion evaluation (structured output → marker → continue), capacity rejection outranks completion claim. Use when working with completion.py.
mkdocs-material, ADR structure, and doc build/serve commands. Use when adding documentation.
QuotaExhausted has no reset field, body-first classification ladder, and waitability rules. Use when working with capacity.py or classify.py.
release-please, gitflow (develop → main), TestPyPI + PyPI publishing, and the known publish-testpypi gap. Use before cutting a release.
Generated `codexloop api` command tree, api_baseline.json drift gate, and how to refresh the baseline. Use when SDK upgrades change the surface.
Run and debug codexloop autonomous sessions.
Fakes over mocks, FakeClock/FakeSleeper, Hypothesis, pytest markers, per-layer 100% coverage. Consult before adding tests or mocks.
cursorloop guidance
cursorloop guidance
cursorloop guidance
cursorloop guidance
cursorloop guidance
cursorloop guidance
cursorloop guidance
cursorloop guidance
Use for configuration, policy, adapters, CLI, or workflow changes. Follow `AGENTS.md`, keep decisions deterministic, isolate remote mutation, preserve the dependency-free runtime, and update template, renderer, dogfood copy, tests, and docs together.
Use after materializing the exact unresolved path set. Preserve both intents, edit only conflicted paths, run normal CI afterward, and never delete or force-push permanent branches.
Inventory public behavior from source, tests, workflows, packaging, and configuration. Update human docs, agent rules, examples, cross-links, changelog, crawler surfaces, structured metadata, LLM discovery, and provenance together. Never invent a capability. Run the deterministic documentation contract and the complete project gates.
Use to create or refresh the complete human, governance, operational, security, agent, crawler, SEO, and LLM documentation suite. Derive every claim from repository evidence; never invent behavior. Keep all cross-links, examples, configuration, and provenance fresh.