Agent-Skills.md

Agent Skills: MCP Response Analyzer

MCP Response Analyzer pattern - Write large responses to temp files, load summaries into context

UncategorizedID: nguyenthienthanh/aura-frog/response-analyzer

Repository

nguyenthienthanh/aura-frog
nguyenthienthanh
142

Install this agent skill to your local

pnpm dlx add-skill https://github.com/nguyenthienthanh/aura-frog/tree/HEAD/aura-frog/skills/response-analyzer

Skill Files

Browse the full folder contents for response-analyzer.

Download Skill

Loading file tree…

aura-frog/skills/response-analyzer/SKILL.md

Skill Metadata

Name
response-analyzer
Description
"MCP Response Analyzer pattern - Write large responses to temp files, load summaries into context"

AI-consumed reference. Optimized for Claude to read during execution. Human-readable explanation: see docs/architecture/HIERARCHICAL_PLANNING.md or docs/getting-started/ depending on topic.

MCP Response Analyzer

Reduce context bloat: write large outputs to /tmp/aura-frog/, load only summaries.

Triggers

triggers[5]{scenario,threshold,action}:
  Command output,>100 lines,Save to temp + summarize
  API response,>5KB,Save JSON + extract key fields
  File search results,>50 files,Save list + show top 10
  Test output,>50 lines,Save full + summarize pass/fail
  Build output,>100 lines,Save full + show errors only

Directory

/tmp/aura-frog/
├── responses/   # cmd-*.txt, api-*.json, search-*.txt
├── summaries/   # summary-*.md
└── session/     # per-session data

Patterns

Large Command Output

npm test > /tmp/aura-frog/responses/test-$(date +%s).txt 2>&1
grep -E "(PASS|FAIL|Tests:|Suites:)" /tmp/aura-frog/responses/test-*.txt | tail -10

API Response

curl url > /tmp/aura-frog/responses/api-$(date +%s).json
jq '{total: .data | length, first_3: .data[:3] | map(.name)}' /tmp/aura-frog/responses/api-*.json

File Search

find . -name "*.ts" > /tmp/aura-frog/responses/search-$(date +%s).txt
echo "Found $(wc -l < file) TypeScript files"; head -10 file

Token Savings

savings[4]{scenario,without,with,saved}:
  500-line test output,~2000,~100,95%
  Large JSON response,~5000,~200,96%
  200 file search,~800,~100,87%
  Build log,~3000,~150,95%

Integration

workflow_integration[4]{phase,use_case,pattern}:
  Phase 2 (Test RED),Test output,Command
  Phase 4 (Review),Linter output,Command
  Phase 4 (Review),Coverage report,Command
  Any,Large API responses,API

Cleanup: find /tmp/aura-frog -mtime +1 -delete