mick-gsk

Drift-specific ADR workflow for signal, scoring, output, and architecture decisions. Use when creating, updating, or validating ADRs before implementation. Keywords: ADR, decision record, proposed, signal design, scoring change, architecture boundary, output format, Decision trailer.

Drift-specific workflow for creating, extending, and validating ground-truth fixtures for signal precision and recall. Use when adding TP/TN fixtures, confounders, boundary cases, or file_history_overrides in tests/fixtures/ground_truth.py. Keywords: ground truth, fixture, precision recall, TP, TN, confounder, boundary, file_history_overrides, ALL_FIXTURES.

End-to-end Drift workflow for adding or materially changing a signal. Use when designing a signal, implementing BaseSignal logic, adding weights, creating fixtures, updating audits, and validating precision/recall before commit. Keywords: signal development, BaseSignal, register_signal, incremental_scope, signal design, precision recall, mutation benchmark, audit_results, ADR.

Operationaler Workflow für den internen MCP-Server aus scripts/mcp_product_health_server.py. Immer verwenden, wenn Agenten Produktstatus, Release-Gates, Working-Tree-Gates oder Audit-Freshness direkt per MCP abrufen sollen statt manuelle Git-/Script-Aufrufe zu bauen. Keywords: drift_product_health, drift_release_readiness, drift_working_tree_context, drift_audit_freshness, mcp server, pre-push gates, blast report, audit freshness.

Log learnings, errors, and corrections to .learnings/ for continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects the agent, (3) A knowledge gap is identified, (4) A better approach is found. Captures corrections, insights, errors, and feature requests; promotes broadly applicable learnings to project memory files.

Post-completion self-review for coding agents that runs simplify, harden, and micro-documentation passes on non-trivial code changes. Use when: a coding task just completed, the diff touches executable source files with 10+ changed lines or high-impact logic (auth, validation, queries, file paths, network, concurrency). Feeds recurring findings into self-improving-agent via .learnings/LEARNINGS.md.

Erkennt wiederkehrende manuelle Entwicklungsprozesse im Workspace, priorisiert sie nach ROI und fuehrt sichere lokale Automationen automatisch aus. IMMER verwenden, wenn der User repetitive manuelle Schritte, Produktivitaetsverluste, wiederholte QA/Gate-Ablaufe oder den Wunsch nach weniger manuellem Agent-Anstossen beschreibt. Keywords: automate workspace, repetitive tasks, auto run, quality gates, drift workflow automation, productivity.

Drift-spezifischer Workflow zum Erstellen und Verbessern von Agent-Prompts unter .github/prompts/. Verwenden bei neuen .prompt.md-Dateien, bei der Schärfung von Evaluierungs-Prompts, bei der Trennung zwischen internem Prompt und Field-Test-Prompt sowie bei der Ausrichtung auf Drift-Policy und Shared Partials. Keywords: agent prompt, prompt authoring, .prompt.md, evaluation prompt, field-test prompt, work_artifacts, issue filing, bewertungs-taxonomie.

Capture continuity metadata on key execution triggers during work.

Close a session with a compact handoff before switching agents.

Recovery path when continuity packet readiness or tooling is limited.

Mandatory first move for local DevCD continuity before asking for recap.

Use when a change affects architecture, slice boundaries, API contracts, policy rules, or memory schemas. Creates or updates Architecture Decision Records (ADRs) before implementation. Keywords: ADR, decision record, proposed, architecture boundary, policy change, API contract, slice design.

Use when an agent ignores instructions, loses context, misuses tools, produces weak handoffs, behaves unreliably across multiple steps, or needs observability and operational guardrails. Covers instruction loading checks, handoff discipline, context compaction, multi-agent coordination, failure-mode analysis, and verification gates for agent-driven work.

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

Repository-safe commit and push workflow for DevCD. Use when preparing commits, choosing conventional commit messages, running validation, or deciding whether a push is allowed. Keywords: commit, push, git push, conventional commit, changelog, validation.

Big-Tech Engineering Standards (Google/Apple/OpenAI) for portfolio-quality code. Use when: performing code reviews or reviewing PRs; writing design documents or ADRs; planning new features (> 50 LOC); designing APIs or defining contracts; adding observability (logs, metrics, traces, SLOs, alerting); structuring test suites (testing pyramid, 70/20/10 ratio, mutation testing, benchmarks); writing runbooks or post-mortems; evaluating LLM features with evals; checking privacy or GDPR data handling; demonstrating Big Tech engineering practices.