mfittko

Single public dev-loop entrypoint. Resolve canonical current state first, then load only route-specific internal skills.

Internal routed strategy behind `dev-loop` for local phase-bounded implementation. Use it when authoritative startup/resume routing selects the `local_implementation` strategy so the child agent can own phase planning, artifact discipline, test-first implementation, and local validation in fresh context.

Standalone pre-loop Socratic Q&A grill for issues (tracker-first), PR bodies, or local plan files (local-planning). Detects spec gaps, asks clarifying questions (interactive) or self-answers them from codebase context (--auto), then synthesizes Acceptance criteria / Definition of done / Non-goals into the body while keeping the raw Q&A only in an ephemeral tmp artifact.

Single public dev-loop entrypoint. Resolve canonical current state first, then load only route-specific internal skills.

Internal routed strategy behind `dev-loop` for local phase-bounded implementation. Use it when authoritative startup/resume routing selects the `local_implementation` strategy so the child agent can own phase planning, artifact discipline, test-first implementation, and local validation in fresh context.

Standalone pre-loop Socratic Q&A grill for issues (tracker-first), PR bodies, or local plan files (local-planning). Detects spec gaps, asks clarifying questions (interactive) or self-answers them from codebase context (--auto), then synthesizes Acceptance criteria / Definition of done / Non-goals into the body while keeping the raw Q&A only in an ephemeral tmp artifact.

Internal routed strategy behind `dev-loop` for GitHub-first Copilot-owned PR follow-up: inspect the canonical PR state, request or re-request Copilot when appropriate, wait deterministically for new review activity, run narrow Pi fix/reply/resolve passes, verify gate evidence, and stop for explicit human approval before merge.

Internal routed strategy behind `dev-loop` for GitHub-first Copilot-owned PR follow-up: inspect the canonical PR state, request or re-request Copilot when appropriate, wait deterministically for new review activity, run narrow Pi fix/reply/resolve passes, verify gate evidence, and stop for explicit human approval before merge.

Use when exploring, modifying, reviewing, or planning work in this repository. Read the generated local wiki first as an orientation aid, then verify implementation details against source code. Keywords: navigation, orientation, local wiki, repo wiki, codebase map, architecture, modules.

Use when running repo-wiki CLI workflows in this repository or as a distributed plugin for external repositories: scanning, planning, compiling, linting, local wiki regeneration, and GitHub Wiki publishing. Keywords: repo-wiki CLI, npx repo-wiki, self:wiki, kb:bootstrap, lint:local, lint-docs, publish wiki, GitHub Wiki, .llmwiki.

Use when creating or maintaining CHANGELOG.md, deriving Keep a Changelog 1.1.0 entries from merged pull request metadata, or cutting a release section from Unreleased. Keywords: changelog, CHANGELOG.md, Keep a Changelog, release notes, unreleased, changelog maintenance.

Use when planning or reviewing work against docs/iOS/spec.md, docs/iOS/PLAN.md, or docs/iOS/plan/*. Keep scope aligned to the current Apple phase and prevent cross-phase drift.

Use when working on route sharing, hydration, route persistence, stale-anchor handling, GPX export boundaries, or watch payload semantics.

Use when working on WatchConnectivity, send-to-watch availability, acknowledgement states, watch persistence, or stale and partial route behavior on Apple Watch.

Store and retrieve knowledge using raged semantic search with enrichment and knowledge graph. Ingest any content — code, docs, PDFs, images, articles, emails, transcripts, notes — and query by natural language. Supports async metadata extraction, entity/relationship tracking, and hybrid vector+graph retrieval. Use when the user needs grounded context from their knowledge base.

Store and retrieve knowledge using raged semantic search with enrichment and knowledge graph. Ingest any content — code, docs, PDFs, images, articles, emails, transcripts, notes — and query by natural language. Supports async metadata extraction, entity/relationship tracking, and hybrid vector+graph retrieval. Use when the user needs grounded context from their knowledge base.