- name
SKILL.md
技能檔案保留在發布者的儲存庫中。
在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add oliver-kriska/claude-elixir-phoenix --skill session-trends -a cursor -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add oliver-kriska/claude-elixir-phoenix --skill session-trends -a claude-code -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add oliver-kriska/claude-elixir-phoenix --skill session-trends -a codex -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add oliver-kriska/claude-elixir-phoenix --skill session-trends -a grok -y在 Grok Bot 聊天中傳送複製的訊息。Bot 會從 GitHub 取得這個 SKILL.md,並加入你所有 Bot 共用的技能中。
Install this skill: https://github.com/oliver-kriska/claude-elixir-phoenix/tree/HEAD/.claude/skills/session-trends來自發布者
Analyze trends from the metrics ledger. Computes windowed aggregates, fingerprint distributions, and compares against MEMORY.md baselines.
Requires .claude/session-metrics/metrics.jsonl from /session-scan.
/session-trends # All windows (7d, 30d, all)
/session-trends --window 30d # Specific window only
/session-trends --project enaia # Filter by project
/session-trends --compare MEMORY.md # Compare against memory baseline
/session-trends --html out.html # Write HTML report with ASCII bars
For pure context-window stats (max prompt tokens, ctx %, compaction rate)
across raw Claude Code JSONL files, see the --scan-jsonl mode of
compute-metrics.py (inspired by badlogic / earendil-works/pi).
Extract from $ARGUMENTS:
--window WINDOW: Time window — 7d, 30d, or all (default: show all three)--project NAME: Filter metrics by project name--compare PATH: Path to MEMORY.md for baseline comparison
(default: auto-detect from .claude/ project memory)Read .claude/session-metrics/metrics.jsonl.
If empty or missing:
No metrics found. Run
/session-scanfirst.
If --project specified, filter entries by project field.
python3 .claude/skills/session-scan/references/compute-metrics.py \
--trends .claude/session-metrics/metrics.jsonl \
--memory {MEMORY_PATH}
Capture the JSON output.
Format the JSON output as a readable report:
Total sessions: {N} ({backfilled} backfilled from v1)
Date range: {earliest} to {latest}
| Metric | 7 days | 30 days | All time |
|-------------------------|--------|---------|----------|
| Sessions | 12 | 45 | 165 |
| Avg friction | 0.28 | 0.24 | 0.22 |
| Max friction | 0.72 | 0.72 | 0.89 |
| Avg opportunity | 0.35 | 0.30 | 0.28 |
| Tier 2 eligible | 40% | 33% | 30% |
| Plugin adoption | 12% | 10% | 8% |
| Type | 7d | 30d | All |
|---------------|-----|-----|------|
| bug-fix | 4 | 15 | 52 |
| feature | 3 | 12 | 48 |
| exploration | 2 | 8 | 30 |
| maintenance | 1 | 5 | 18 |
| review | 1 | 3 | 10 |
| refactoring | 1 | 2 | 7 |
Compare measured values against MEMORY.md claims:
| MEMORY.md Claim | Measured | Match? |
|------------------------------|-------------|--------|
| Plugin adoption: 8-12% | 10.2% | Yes |
| Minimal friction in 40+ of 74| 68% smooth | Yes |
Write computed trends to .claude/session-metrics/trends.json.
Based on trends:
/session-deep-dive --from-scan to investigate"See references/trend-queries.md for interpreting specific trend patterns.
The HTML report layout (preformatted text + ASCII bar charts via █/░)
and per-model + threshold-bucket breakdown (>=80%, >=90%, >=100%,
compaction_rate) were borrowed from
badlogic / earendil-works/pi session-context-stats.mjs.
Our pipeline's qualitative metrics (friction, fingerprint, plugin
opportunity, skill effectiveness) are additive on top.
Analyze trends across session metrics. Computes windowed aggregates, deltas, and compares against MEMORY.md findings. Use periodically for progress tracking.
---name: session-trendsdescription: Analyze trends across session metrics. Computes windowed aggregates, deltas, and compares against MEMORY.md…---# .claude/skills/session-trends/SKILL.md常見問題
從發布者下載 .claude/skills/session-trends/SKILL.md,或複製路徑後開啟儲存庫。PlugMCP 只收錄這項技能,不代管檔案。
發布者將它存放在 https://github.com/oliver-kriska/claude-elixir-phoenix。
Claude、Cursor、Codex 和 Grok Build 可以讀取你從發布者儲存庫加入的 SKILL.md。在聊天中傳送技能的 GitHub 資料夾連結,Grok Bot 就會安裝它。