SQLite best practices for Python -- connection setup, WAL mode, foreign keys PRAGMA (must be set per connection!), context managers for transactions, parameterized queries, row_factory, executemany, connection management, indexes on FKs, and money as INTEGER cents. Use when building or reviewing any Python app with SQLite, when you see sqlite3 imports, or when setting up a new local database in a FastAPI/Flask project.

Tests memory writes, confirms read-back accuracy, and validates retrieval success to ensure saved information can actually be recovered. Use when you need to verify memory was saved correctly, check if stored data can be retrieved, confirm a memory entry is discoverable, or escalate when saved information appears lost or corrupted. Covers write confirmation, read-back comparison, retrieval smoke testing, and failure escalation.

Create terminal-based presentation slides using presenterm's markdown format. presenterm renders markdown files as slides in the terminal with themes, code highlighting, images, column layouts, speaker notes, and more. Use this skill whenever the user wants to create a presenterm presentation, terminal slides, markdown slides for presenterm, or mentions "presenterm" in any context. Also trigger when the user asks for "terminal presentation", "markdown presentation", "slide deck in markdown", or wants to convert content into presenterm format. Even if the user just says "create a presentation" and they have used presenterm before or the context suggests terminal-based slides, use this skill.

Resolve pull request feedback by critically assessing each item, fixing source files (not generated files), regenerating derived artifacts, running lint/format, committing, pushing, and replying on the appropriate GitHub thread. Use when the user asks to address PR feedback, respond to reviewer suggestions, fix issues from code review, or resolve GitHub review comments, PR issue comments, or review summaries.

Create or update a CONSTITUTION.md that defines project governance — establishes coding standards, quality gates, TDD policy, review requirements, and non-negotiable development principles with versioned amendment tracking. Use when defining project rules, setting up coding standards, establishing quality gates, configuring TDD requirements, or creating non-negotiable development principles.

Create a feature specification from a natural language description — generates user stories with Given/When/Then scenarios, functional requirements (FR-XXX), success criteria, and a quality checklist. Use when starting a new feature, writing a PRD, defining user stories, capturing acceptance criteria, or documenting requirements for a product idea.

Generate a technical design document from a feature spec — selects frameworks, defines data models, produces API contracts, and creates a dependency-ordered implementation strategy. Use when planning how to build a feature, writing a technical design doc, choosing libraries, defining database schemas, or setting up Tessl tiles for runtime library knowledge.

Generate, review, and curate eval scenarios for Tessl skills. Handles scenario generation, bleeding/leaking detection, criteria quality checks, coverage gap analysis, and score-driven iteration. Use when creating test cases or test scenarios for a skill, evaluating or assessing skill quality, running evals or evaluations, reviewing existing evals, expanding eval coverage, or skill testing.

Scaffold the `jbaruch/coding-policy` gh-aw PR review workflows into a consumer repository: copies the packaged paired workflow templates (OpenAI + Anthropic reviewers), compiles them with `gh aw`, and opens a PR. After merge, every pull request in the repo is reviewed against the latest published `jbaruch/coding-policy` rules by the reviewer whose family differs from the PR's declared author model — avoiding self-review bias per `rules/author-model-declaration.md`. Use when the user wants to add, install, enable, scaffold, set up, or wire up an automated policy review / PR reviewer / coding-policy CI reviewer in a consumer repo. Also use to upgrade, update, refresh, or pull the latest reviewer templates into a consumer repo that already has the scaffold installed — the skill switches to override mode in that case.

Structured workflow for shipping code via GitHub pull requests: PR creation, dual-lens automated review (gh-aw for `rules/*.md` compliance + Copilot for doc accuracy and cross-step consistency), merge, and branch cleanup. Covers readiness checks, version reasoning, review polling, feedback handling, and post-merge verification. Use when the user wants to open a pull request, ship code, merge a branch, or handle post-merge cleanup on GitHub.

Stress-test the primary review with an additional independent reviewer that generates its own findings, compares reviewer conclusions, and identifies issues the primary reviewer may have missed. Use when performing a second opinion or double-check review on a pull request, for medium or high risk PRs, when authoring was heavily AI-assisted, when primary reviewer confidence is low, when findings conflict, or when you need to verify findings with a cross-model or same-model challenger. Supports same-model and cross-model configurations for fair comparison.

Turn many candidate findings from reviewers and verifiers into a small, decision-useful set. Deduplicates, ranks, and suppresses weak findings to consolidate review results into a prioritized, actionable list with severity ratings and merged confidence scores. Use when you need to merge findings, consolidate feedback, prioritize issues, or summarize review output after review passes are complete and before human handoff. Trigger phrases: "consolidate review results", "merge findings", "deduplicate feedback", "prioritize issues from review", "summarize reviewer output". The evidence threshold is the filter — not an arbitrary cap.

Provide an independent critique of a pull request (PR) using a clean reviewer context, identifying bugs, security issues, code quality problems, API misuse, and missing test coverage. Use when performing a code review or pull request review after an evidence pack has been built, for green or yellow risk lane PRs, or as part of a full pipeline for red risk lane PRs. Produces candidate findings (covering correctness, security, and architectural concerns) for downstream synthesis — not final verdicts. Operates as a critic, not a co-author. Common triggers: "review this PR", "code review feedback", "fresh review", "independent review".

Apache Flink SQL, Table API, and UDF development for both OSS Flink and Confluent Cloud. Use when: (1) Writing Flink SQL queries (windows, joins, aggregations, MATCH_RECOGNIZE), (2) Building Table API pipelines in Java or Python, (3) Creating UDFs (scalar, table functions) for Flink, (4) Deploying Flink jobs to Confluent Cloud, (5) Converting between DataStream and Table API, (6) Troubleshooting Flink SQL errors. Covers windowing, event-time processing, watermarks, state management, and Confluent-specific patterns.