knowledge-graph
Manage persistent Knowledge Graph for specifications. Provides read, query, update, and validation capabilities for codebase analysis caching. Use when: spec-to-tasks needs to cache/reuse codebase analysis, task-implementation needs to validate task dependencies or contracts, spec-quality needs to synchronize provides, or any command needs to query existing patterns/components/APIs. Reduces redundant codebase exploration by caching agent discoveries.
What this skill does
# Knowledge Graph Skill
## Overview
The Knowledge Graph (KG) is a persistent JSON file that stores discoveries from codebase analysis, eliminating redundant exploration and enabling task validation.
**Location**: `docs/specs/[ID-feature]/knowledge-graph.json`
**Key Benefits:**
- ✅ Avoid re-exploring already-analyzed codebases
- ✅ Validate task dependencies against actual codebase state
- ✅ Share discoveries across team members
- ✅ Accelerate task generation with cached context
## When to Use
Use this skill when:
1. **spec-to-tasks needs to cache/reuse codebase analysis** - Store agent discoveries for future reuse
2. **task-implementation needs to validate task dependencies and contracts** - Check if required components exist before implementing
3. **Any command needs to query existing patterns/components/APIs** - Retrieve cached codebase context
4. **Reducing redundant codebase exploration** - Avoid re-analyzing already-explored code
**Trigger phrases:**
- "Load knowledge graph"
- "Query knowledge graph"
- "Update knowledge graph"
- "Validate against knowledge graph"
- "Check if component exists"
- "Find existing patterns"
## Instructions
### Available Operations
**1. read-knowledge-graph** - Load and parse KG for a specification
- **Input**: Path to spec folder (e.g., `docs/specs/001-feature/`)
- **Output**: KG object with metadata, patterns, components, APIs
**2. query-knowledge-graph** - Query specific sections (components, patterns, APIs)
- **Input**: Spec folder, query type, optional filters
- **Output**: Filtered results matching criteria
**3. update-knowledge-graph** - Update KG with new discoveries
- **Input**: Spec folder, updates (partial KG), source description
- **Output**: Merged KG with new findings
**4. validate-against-knowledge-graph** - Validate task dependencies against KG
- **Input**: Spec folder, requirements (components, APIs, patterns)
- **Output**: Validation report with errors/warnings
**5. validate-contract** - Validate provides/expects between tasks
- **Input**: Spec folder, expects (files + symbols), completed dependencies
- **Output**: Satisfied/unsatisfied expectations report
**6. extract-provides** - Extract symbols from implemented files
- **Input**: Array of file paths
- **Output**: Array of provides with file, symbols, type
**7. aggregate-knowledge-graphs** - Merge patterns from all specs
- **Input**: Project root path
- **Output**: Global KG with deduplicated patterns
See [references/query-examples.md](references/query-examples.md) for detailed usage examples.
## Examples
### Input/Output Examples
**Read Knowledge Graph:**
```
Input: /knowledge-graph read docs/specs/001-hotel-search/
Output: {
metadata: { spec_id: "001-hotel-search", version: "1.0" },
patterns: { architectural: [...], conventions: [...] },
components: { controllers: [...], services: [...]}
}
```
**Query Components:**
```
Input: /knowledge-graph query docs/specs/001-hotel-search/ components {"category": "services"}
Output: [{ id: "comp-svc-001", name: "HotelSearchService", type: "service"}]
```
**Update Knowledge Graph:**
```
Input: /knowledge-graph update docs/specs/001-hotel-search/ {
patterns: { architectural: [{ name: "Repository Pattern"}] }
}
Output: "Added 1 pattern to knowledge graph"
```
**Validate Dependencies:**
```
Input: /knowledge-graph validate docs/specs/001-hotel-search/ {
components: ["comp-repo-001"]
}
Output: { valid: true, errors: [], warnings: [] }
```
See [references/examples.md](references/examples.md) for comprehensive workflow examples.
## KG Schema Reference
See [references/schema.md](references/schema.md) for complete JSON schema with examples.
## Integration Patterns
See [references/integration-patterns.md](references/integration-patterns.md) for detailed integration with Developer Kit commands.
## Error Handling
See [references/error-handling.md](references/error-handling.md) for comprehensive error handling strategies and recovery procedures.
## Performance Considerations
See [references/performance.md](references/performance.md) for optimization strategies and performance characteristics.
## Security
See [references/security.md](references/security.md) for security considerations, threat mitigation, and best practices.
## Best Practices
**When to Query KG**: Before codebase analysis, task generation, dependency validation
**When to Update KG**: After agent discoveries, component implementation, pattern discovery
**KG Freshness**:
- < 7 days: Fresh
- 7-30 days: Stale, warn user
- > 30 days: Very stale, offer regeneration
See [references/performance.md](references/performance.md) and [references/security.md](references/security.md) for detailed best practices.
## Constraints and Warnings
### Critical Constraints
- **Source-Code Safe Operations**: Does NOT modify source code files. Only creates/updates `knowledge-graph.json` files.
- **Path Validation**: Only reads/writes KG files from `docs/specs/[ID]/` paths.
- **No Automatic Code Generation**: Caches analysis results, does NOT generate implementation code.
### Limitations
- **Validation Scope**: Checks components exist in KG, but cannot verify if they exist in actual codebase if KG is outdated
- **Freshness Dependency**: KG accuracy depends on how recently it was updated
- **Single-Spec First**: Each KG is primarily specific to a single specification
- **File Size**: KG files can grow large (>1MB) for complex specifications
See [references/error-handling.md](references/error-handling.md) and [references/security.md](references/security.md) for complete constraints and warnings.
## Reference Files
- [schema.md](references/schema.md) - Complete JSON schema
- [query-examples.md](references/query-examples.md) - Query patterns
- [integration-patterns.md](references/integration-patterns.md) - Command integration
- [error-handling.md](references/error-handling.md) - Error handling guide
- [performance.md](references/performance.md) - Performance optimization
- [security.md](references/security.md) - Security considerations
- [examples.md](references/examples.md) - Practical examples
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.