Builds and refreshes the project context stack before non-trivial engineering work.
npx skills add https://github.com/reddb-io/red-skills --skill context-reddb-io
Please help me install this Agent Skill. Skill: context Source: https://github.com/reddb-io/red-skills/tree/main/plugins/dev/skills/engineering/context Command: npx skills add https://github.com/reddb-io/red-skills --skill context-reddb-io
High-intent search queries and answers about installing and using this skill.
Run the context workflow to read CLAUDE.md or AGENTS.md, the domain glossary in .red/CONTEXT.md, and recent ADRs first. It then recalls prior memory, maps module boundaries, and reports a grounded context posture before any implementation begins.
Use targeted memory recall with red-skills-memory recall before deep investigation. In graph mode, recall is neighborhood-expanded and supersede-aware; treat hits as historical claims and verify them against the current worktree before relying on them.
No, Memory is an optimization, not a hard dependency. If Memory is absent, uninitialized, or failing, the workflow falls back to ordinary repository reads and continues with committed docs and ADRs.
Run red-skills-memory ingest only for large or unfamiliar codebases, impact analysis, onboarding, or repeated cross-session work, and only when Memory is initialized in graph mode. Re-run after large refactors or when the graph is stale.
Store only durable operational decisions, root causes, and gotchas using red-skills-memory store. Do not store secrets, personal facts, transient progress, issue or PR numbers, commit SHAs, or task-done logs that go stale quickly.
Cain-IshEnforce named-entity wiki lookups before answering with Second-Brain memory.
tonamsonOrchestrates feature implementation workflows with subagents across phases and finalization steps.
pax-kDistill raw documents into an Obsidian wiki with frontmatter metadata and wikilinks.
AO-Cyber-SystemsExecute ad-hoc tasks with atomic commits and STATE.md updates.
