Skill

advanced-workflows

Orchestrates multi-tool patterns for BK knowledge retrieval and management, including progressive library exploration, indexing waits, detail strategies, and cross-library comparisons.

developer-tools

documentation

npx claudepluginhub chris-xperimntl/agent-knowledge

Tool Access

This skill uses the workspace's default tool permissions.

Preview

Multi-tool patterns for efficient knowledge retrieval and management.

Supporting Assets

references/combining-workflows.mdreferences/error-recovery.mdreferences/examples.mdreferences/handling-large-results.mdreferences/multi-store-search.md

SKILL.md

Similar Skills

Search Knowledge Stores

Searches indexed library sources using vector, FTS, or hybrid modes with options for stores, limits, thresholds, and detail levels to find code implementations.

2 files1 tool

agent-knowledge

mcp-research

143

Guides doc lookup and web search workflow for investigating libraries, APIs, or unfamiliar patterns before implementation.

airis-mcp-gateway

evm-token-decimals

173.8k

Prevents silent decimal mismatch bugs in EVM ERC-20 tokens via runtime decimals lookup, chain-aware caching, bridged-token handling, and normalization. For DeFi bots, dashboards using Python/Web3, TypeScript/ethers, Solidity.

everything-claude-code

Stats

Stars11

Forks3

Last CommitMar 19, 2026

Actions

View Source View Plugin View on GitHub View README

Help us improve

Share bugs, ideas, or general feedback.

Advanced BK Workflows

Multi-tool patterns for efficient knowledge retrieval and management.

Core Patterns

Progressive Library Exploration

1. list_stores() → identify target store 2. search(query, detail='minimal', stores=[target]) → scan summaries 3. get_full_context(top_result_ids) → deep dive on best matches

Add Library + Wait for Index

1. create_store(url, name) → job_id 2. check_job_status(job_id) → poll every 15-30s 3. When completed: search(query, stores=[name]) → verify

Progressive Detail Strategy

1. search(query, detail='minimal', limit=20) → ~100 tokens/result 2. Filter by score (>0.7 = strong match) 3. get_full_context(top_3_ids) → saves ~80% context 4. If nothing relevant: refine query and retry

Cross-Library Comparison

1. search(query, limit=10) → searches ALL stores 2. Review store distribution 3. Narrow: search(query, stores=['lib1', 'lib2'], limit=15)

Best Practices

Start with detail='minimal' — summaries first, full context selectively

Monitor background jobs — don't search until indexing completes

Use intent parameter — 'find-implementation' vs 'find-usage' vs 'find-documentation'

Filter by stores — faster, more focused results

Check scores — >0.7 strong match, <0.5 likely noise

Detailed examples and error recovery: references/examples.md

Advanced BK Workflows

Multi-tool patterns for efficient knowledge retrieval and management.

Core Patterns

Progressive Library Exploration

1. list_stores() → identify target store
2. search(query, detail='minimal', stores=[target]) → scan summaries
3. get_full_context(top_result_ids) → deep dive on best matches

Add Library + Wait for Index

1. create_store(url, name) → job_id
2. check_job_status(job_id) → poll every 15-30s
3. When completed: search(query, stores=[name]) → verify

Progressive Detail Strategy

1. search(query, detail='minimal', limit=20) → ~100 tokens/result
2. Filter by score (>0.7 = strong match)
3. get_full_context(top_3_ids) → saves ~80% context
4. If nothing relevant: refine query and retry

Cross-Library Comparison

1. search(query, limit=10) → searches ALL stores
2. Review store distribution
3. Narrow: search(query, stores=['lib1', 'lib2'], limit=15)

Best Practices

Start with detail='minimal' — summaries first, full context selectively
Monitor background jobs — don't search until indexing completes
Use intent parameter — 'find-implementation' vs 'find-usage' vs 'find-documentation'
Filter by stores — faster, more focused results
Check scores — >0.7 strong match, <0.5 likely noise

Detailed examples and error recovery: references/examples.md