vp-knowledge

Use this agent for read-only knowledge graph auditing. Examples: <example> Context: User wants to check graph health user: "Audit my knowledge graph" assistant: "I'll use the knowledge-gardener agent to run a full health audit." <commentary> Explicit audit request — trigger the read-only gardener, not the write-capable maintainer. </commentary> </example> <example> Context: User asks about graph quality user: "Are there any orphan notes or broken links?" assistant: "I'll use the knowledge-gardener agent to check for orphans and relation integrity." <commentary> Specific graph quality question maps to gardener's responsibilities. </commentary> </example> <example> Context: Periodic review user: "Check graph health" assistant: "I'll use the knowledge-gardener agent to generate a health report." <commentary> General health check — gardener produces the report, maintainer would act on it. </commentary> </example>

Use this agent to actively fix and enhance the knowledge graph. Examples: <example> Context: User wants to act on a gardener audit report user: "Fix the issues from the graph audit" assistant: "I'll use the knowledge-maintainer agent to address the findings." <commentary> User has a gardener report and wants fixes applied — this is the write agent's job. </commentary> </example> <example> Context: User wants graph improvements user: "Improve my knowledge graph — fix orphans, add missing links, enrich thin notes" assistant: "I'll use the knowledge-maintainer agent to enhance the graph." <commentary> Broad maintenance request covering multiple fix types. Maintainer handles all of these. </commentary> </example> <example> Context: User notices quality issues user: "A bunch of my npm notes are missing relations, can you fix that?" assistant: "I'll use the knowledge-maintainer agent to add missing relations to npm notes." <commentary> Specific structural fix request. Maintainer can auto-fix this without confirmation. </commentary> </example> <example> Context: User wants undocumented packages covered user: "Research and document any important packages that are missing from the knowledge graph" assistant: "I'll use the knowledge-maintainer agent to find gaps and create notes for critical packages." <commentary> Combines knowledge-gaps detection with auto-running /package-intel for Tier 1 packages. </commentary> </example>

Use this agent to autonomously load project-relevant knowledge from Basic Memory before starting work. Examples: <example> Context: User starts a new session and wants context user: "Prime the knowledge graph for this project" assistant: "I'll use the knowledge-primer agent to load relevant context from Basic Memory." <commentary> Explicit priming request — trigger the primer agent to autonomously scan the project and surface relevant knowledge. </commentary> </example> <example> Context: User wants to understand what BM knows about their codebase user: "What does Basic Memory know about this project's dependencies?" assistant: "I'll use the knowledge-primer agent to cross-reference your dependencies with the knowledge graph." <commentary> Coverage question maps to the primer's dep-matching workflow. </commentary> </example> <example> Context: User wants context before making changes user: "Load any relevant gotchas before I start working on the auth module" assistant: "I'll use the knowledge-primer agent to surface relevant knowledge and gotchas." <commentary> Pre-work context request — primer surfaces relevant notes and critical observations. </commentary> </example>

Use this agent for read-only Raindrop tag auditing. Examples: <example> Context: User wants to audit their Raindrop tags user: "Audit my Raindrop tags" assistant: "I'll use the raindrop-gardener agent to run a full tag health audit." <commentary> Explicit audit request — trigger the read-only raindrop-gardener. </commentary> </example> <example> Context: User asks about tag quality user: "Are there duplicate or legacy tags in my Raindrop library?" assistant: "I'll use the raindrop-gardener agent to check for duplicates, legacy tags, and naming issues." <commentary> Specific tag quality question maps to raindrop-gardener's audit steps. </commentary> </example> <example> Context: User wants tag cleanup guidance user: "Which Raindrop tags should I merge or delete?" assistant: "I'll use the raindrop-gardener agent to identify merge and deletion candidates." <commentary> Cleanup guidance — gardener produces the report, user applies the recommendations. </commentary> </example>

This skill should be used when the user asks 'what do I know about [topic]', 'what does Basic Memory say about [X]', 'do I have notes on [X]', 'look up [X] in my knowledge graph', 'ask memory about [X]', 'recall what we captured about [topic]', 'find notes on [topic]', 'knowledge question', 'query the knowledge graph', 'what observations do I have about [X]', 'knowledge lookup'. Searches Basic Memory for notes and observations matching a specific topic or question -- synthesizes an answer with source citations and gap suggestions. NOT for project-wide inventory or coverage reports (use /knowledge-prime for that).

This skill should be used when the user asks about 'knowledge gaps', 'tool coverage', 'undocumented dependencies', 'undocumented tools', 'concept gaps', 'installed plugins', 'plugin coverage', 'undocumented skills', 'globally installed plugins/skills', 'what is installed on this machine', 'stale/outdated/drifted notes', 'version drift', or 'which tools/packages need updating'. Audits project dependency and tool manifests — and installed Claude Code plugins + skills.sh bundles — against Basic Memory coverage, and detects concept-level hub gaps. Two flag modes: `--stale [brew|npm|cask|crate|vscode]` checks version drift instead of coverage; `--global` audits what is installed on this machine — Claude Code plugins + skills.sh bundles today — against coverage. Supported ecosystems and full flag mechanics are documented in the skill body.

This skill should be used when the user asks to audit, health-check, or structurally validate one or more SPECIFIC named notes or a bounded topic cluster — 'audit these notes', 'check this note for orphans or broken links', 'fourth-wall check on [note]', 'validate the structure of [note]', 'spot-check [note]'. Runs a read-only audit inline. NOT for fixing issues (use /knowledge-maintain), NOT for freeform topic questions (use /knowledge-ask), and NOT for whole-graph audits ('audit my knowledge graph', 'graph health', 'full audit', no arguments) — those belong to the knowledge-gardener agent, which this skill delegates to when invoked graph-wide.

This skill should be used when the user asks to fix, repair, or tidy one or more SPECIFIC named notes — 'fix these notes', 'fix the issues in [note]', 'add the missing relations to [note]', 'tidy up [note]', 'fix orphan [note]', 'apply the gardener findings for [note]'. Applies fixes inline so the user sees and confirms each edit. NOT for read-only auditing (use /knowledge-garden), NOT for creating new notes (use /package-intel or /tool-intel), and NOT for graph-wide or autonomous remediation ('fix the whole audit', 'remediate the graph', research-and-document sweeps) — those belong to the knowledge-maintainer agent, which this skill delegates to when invoked broadly.

This skill should be used when the user asks to 'prime context', 'load project knowledge', 'what do we know about this project', 'knowledge brief', 'project context', 'what packages are documented', 'show coverage for this project', 'dependency coverage report', 'which of our deps have notes', 'knowledge primer', 'prime session', 'context for this project'. Surfaces project-relevant Basic Memory knowledge at session start or on demand — dependency coverage, key gotchas, engineering context, and gaps. NOT for freeform topic questions about individual packages or concepts (use /knowledge-ask for that).

5 hooks across 4 events