project-rules-generator

When the user wants to add a new feature or capability. When the user says "I want to build" or "I'm thinking about". When requirements are unclear and need to be refined.

When the user says they are ready for review or wants to create a PR. When the user asks to check if code is ready for review. When the task or feature is complete and needs quality validation.

When the user approves a plan and wants to execute it. When the user says "execute the plan" or "let's go" or "start implementation". When a PLAN.md exists and is ready to be executed task-by-task.

When the user is implementing a new feature or fixing a bug. When the user wants to write tests first before writing code. When the user is refactoring and needs to verify behaviour is preserved.

When the user wants to create an implementation plan. When the user says "let's implement this" or "create a plan". When a design has been approved and is ready to be broken into tasks.

Systematic code review workflow — evaluate changes for correctness, style, security, and test coverage before merging. When the user asks to review code or a pull request. When the user says "check code quality" or "look over this diff". When the user requests feedback on changes before merging.

Restart containers, prune images, tail logs.

Inspect Telegram chat IDs, message history, and webhook delivery.

Query the bot's PostgreSQL DB for active users in a time window.

<!-- ONE sentence: what the skill does AND when to trigger. See guide below. [REQUIRED] -->

When the user needs to clear temporary files and build artifacts to ensure a fresh project state. When the user encounters inconsistent test results or unexpected build behavior due to stale cache files. When the user wants to reduce repository noise or prepare the project for a clean build or release. When the user mentions "cleanup", "clean project", "clear cache", "remove artifacts", "fresh start". Do NOT activate for: "clean code", "clean architecture", "refactor", "database cleanup".

Helps developers understand, extend, and debug the PRG agent system. When the user asks how the agent system works, how to add a new command, or how Ralph operates. When the user asks why auto-trigger matching is not working or returning wrong results. When the user wants to add a new skill trigger, extend the fallback trigger table, or tune synonym expansion. When the user wants to understand or modify the Ralph loop — thresholds, iteration steps, or exit conditions. When the user asks about skill routing, the two-pass trigger strategy, or AgentExecutor internals. Do NOT activate for general debugging ("bug", "error") — use systematic-debugging instead. Do NOT activate for "create a skill" or "add a skill" — those are for skill management commands.

Systematically audits the project for bugs, regressions, and quality gaps — runs tests, inspects coverage, and reports findings with reproducers. When the user mentions "qa and bugs finder", "find bugs", "audit quality", "regression scan". Do NOT activate for general "fix this bug" requests that already have a known defect.

Refactors the project's test suite to remove duplication, extract fixtures, and tighten assertions — keeps behaviour unchanged while improving readability. When the user mentions "test refactor", "test cleanup", "testing refactor", "refactor tests". Do NOT activate for writing new tests from scratch (use tdd-guide instead).

When the user mentions "docker deployment", "docker", "deployment". When the user needs help with docker deployment.

When the user needs to automate Git repository interactions within their Python project. When the user is writing scripts to programmatically manage repository state, commits, or branches using gitpython. When the user encounters issues with git operations failing silently or unexpectedly in their Python code.

Developers struggle with inconsistent type checking, leading to runtime errors and hard-to-debug issues. When the user reports mypy errors or type checking failures, use this skill. When the user asks to fix type hints or resolve type annotation issues, use this skill. When the user encounters `Incompatible types`, `union-attr`, or `arg-type` errors, use this skill.

When the user reports a bug, error, or something not working. When there is a failing test or CI/CD failure. When the user sees an exception in logs or unexpected behaviour.

Use when user mentions "broad exception", "except Exception", "narrow catch", "exception handling", "failure masking", "swallowing errors", "catch-all". Do NOT activate for "try-except tutorial" or general Python questions.

Use when user mentions "break up analyze", "god function", "oversized command", "split analyze_cmd", "extract services", "too many responsibilities". Do NOT activate for "analyze project" or "run analysis".

Use when user mentions "skill schema", "contract mismatch", "stub validation gap", "unify skill sections", "skill contract", "generator validator inconsistency". Do NOT activate for "analyze skill" or "list skills".

When the user needs to evaluate changes made to the codebase for quality, correctness, and adherence to project standards. When the user wants to ensure new code integrates seamlessly with existing features and dependencies like Gemini, Groq, Anthropic, and OpenAI. When the user is preparing code for merging and needs a structured approach to feedback.

When the user wants to create a new skill for a repeated pattern. When the user says "create a skill for" or "we should formalize this". When the user identifies a repetitive workflow that should be automated.