analyze-session
Analyze a Figma MCP test session transcript. Reads raw session data (JSON or HTML) and produces a structured analysis document with metrics, efficiency issues, error patterns, and prioritized improvements. Updates the cross-session improvement tracker. Use after completing a Figma session or when reviewing past sessions. Accepts an optional file path argument; if omitted, analyzes the most recent transcript.
npx skills add majiayu000/claude-skill-registry --skill analyze-session --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Analyze Session Transcript Analyze a Figma MCP test session transcript and produce a structured efficiency/error audit. After large Figma sessions (50+ tool calls), run this skill to capture learnings and track improvement over time. --- ## Phase 1: Locate and Ingest Transcript ### Session manifest A manifest at `.claude/analysis/sessions.json` tracks all sessions and their analysis status: ```json { "sessions": { "<session-id>": { "sessionType": "figma" | "dev" | "empty", "skip": true, // present on dev/empty sessions "toolCalls": 56, "figmaToolCalls": 48, "durationMinutes": 20, "sourceModified": 1710000000.00, // mtime of source JSON "analysis": "figma-mcp-session4-analysis.md", // only if analyzed "analyzedAt": 1710000000.00 // mtime of analysis file } } } ``` Sessions with `sessionType: "figma"` (at least 1 `mcp__Figmagent__*` tool call) are candidates for analysis. Sessions with `sessionType: "dev"` or `"empty"` are skipped. ### Picking the session to analyze 1. **First, ensure all sessions are extracted**: Run `bun extract-sessions --compact --no-thinking` to extract any new/updated sessions (mtime-based skipping is built in). For sessions from other projects, use `--file <
- Phase 1: Locate and Ingest Transcript
- Session manifest
- Picking the session to analyze
- Manifest update script
- After completing analysis
- Phase 2: Compute Metrics
- Session Overview
- Tool Call Distribution Table
- Error Extraction
- Efficiency Signals — Detect These Patterns
- Phase 3: Cross-Session Comparison
- Phase 4: Generate Analysis Document
- Phase 5: Update Improvement Tracker
- Phase 6: Generate Fix Plans (if applicable)
python3 -c "
import json, os, glob
sessions_dir = '.claude/sessions-json'
analysis_dir = '.claude/analysis'
manifest_path = f'{analysis_dir}/sessions.json'
Load existing manifest or start fresh
with open(manifest_path) as fh:
manifest = json.load(fh)
except (FileNotFoundError, json.JSONDecodeError):
manifest = {'sessions': {}}What does the analyze-session skill do?
Analyze a Figma MCP test session transcript. Reads raw session data (JSON or HTML) and produces a structured analysis document with metrics, efficiency issues, error patterns, and prioritized improvements. Updates the cross-session improvement tracker. Use after completing a Figma session or when reviewing past sessions. Accepts an optional file path argument; if omitted, analyzes the most recent transcript.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill analyze-session --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.