context-map/SKILL.md
Produce a DDD Context Map showing relationships between Bounded Contexts from existing UBIQUITOUS_LANGUAGE.md glossaries or conversation context. Saves to CONTEXT_MAP.md. Triggers on "context map", "context mapping", "bounded context relationships", "how do these contexts relate", "upstream downstream".
npx skillsauth add sanurb/skills context-mapInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Identify all Bounded Contexts in scope and classify the relationship between each pair using Evans/Vernon's canonical patterns. One map per system. Every relationship typed, every direction explicit.
Discover contexts. Scan the working directory for UBIQUITOUS_LANGUAGE.md files — each one names a Bounded Context in its header. If none exist, extract context boundaries from the current conversation. Ask the user if the boundary between two contexts is unclear. Minimum 2 contexts required — a map of one context is meaningless; tell the user to run ubiquitous-language first.
Classify relationships. For every pair of contexts that communicate, assign exactly one relationship pattern from relationship-patterns.md. Determine direction: which is upstream (supplier) and which is downstream (consumer). If a pair has no communication, omit it — do not invent relationships. Use 🔀 CROSS-CONTEXT flags from glossaries as evidence when available.
Write. Produce CONTEXT_MAP.md in the working directory following the exact structure in output-format.md. Then print an inline summary: N contexts | M relationships | K unresolved.
N contexts | M relationships | K unresolved.File: CONTEXT_MAP.md in the current working directory.
Format: output-format.md.
Inline: summary line after file is written.
development
Sets up an `## Agent skills` block in AGENTS.md/CLAUDE.md and `docs/agents/` so the engineering skills know this repo's issue tracker (GitHub, GitLab, fp, or local markdown), triage label vocabulary, and domain doc layout. Run before first use of `fp-plan`, `fp-implement`, `fp-review`, `to-issues`, `to-prd`, `triage`, `diagnose`, `tdd`, `improve-codebase-architecture`, or `zoom-out` — or if those skills appear to be missing context about the issue tracker, triage labels, or domain docs.
development
Build a throwaway prototype to flush out a design before committing to it. Routes between two branches — a runnable terminal app for state/business-logic questions, or several radically different UI variations toggleable from one route. Use when the user wants to prototype, sanity-check a data model or state machine, mock up a UI, explore design options, or says "prototype this", "let me play with it", "try a few designs".
tools
Control herdr (a terminal-native agent multiplexer) from inside it. Manage workspaces and tabs, split panes, spawn sibling agents, read pane output, and wait for state changes — all via CLI commands that talk to the running herdr instance over a local unix socket. Use when running inside herdr (HERDR_ENV=1). Do not use outside herdr.
documentation
Compact the current conversation into a handoff document for another agent to pick up.