- name
SKILL.md
स्किल फ़ाइल पब्लिशर की रिपॉज़िटरी में ही रहती है।
कॉपी की गई कमांड टर्मिनल में पेस्ट करें। यह इस SKILL.md को उस एजेंट में इंस्टॉल करती है।
npx skills add oliver-kriska/claude-elixir-phoenix --skill session-deep-dive -a cursor -yकॉपी की गई कमांड टर्मिनल में पेस्ट करें। यह इस SKILL.md को उस एजेंट में इंस्टॉल करती है।
npx skills add oliver-kriska/claude-elixir-phoenix --skill session-deep-dive -a claude-code -yकॉपी की गई कमांड टर्मिनल में पेस्ट करें। यह इस SKILL.md को उस एजेंट में इंस्टॉल करती है।
npx skills add oliver-kriska/claude-elixir-phoenix --skill session-deep-dive -a codex -yकॉपी की गई कमांड टर्मिनल में पेस्ट करें। यह इस SKILL.md को उस एजेंट में इंस्टॉल करती है।
npx skills add oliver-kriska/claude-elixir-phoenix --skill session-deep-dive -a grok -yकॉपी किया गया संदेश Grok Bot चैट में भेजें। Bot यह SKILL.md GitHub से लाता है और उसे उन स्किल में जोड़ देता है जो आपके सभी Bot साझा करते हैं।
Install this skill: https://github.com/oliver-kriska/claude-elixir-phoenix/tree/HEAD/.claude/skills/session-deep-diveपब्लिशर से
Qualitative analysis of high-signal sessions identified by /session-scan.
Spawns subagents with pre-computed metrics context for focused analysis.
Requires ccrider MCP. If not available:
ccrider MCP is required. See: https://github.com/neilberkman/ccrider
/session-deep-dive ffa155ee-ed8a-492c-8797-878fcbec4d9e
/session-deep-dive --last # Most recent Tier 2 eligible
/session-deep-dive --from-scan # All Tier 2 eligible from last scan
/session-deep-dive --from-scan --compare .claude/UPDATED_PLUGIN_REPORT_160_SESSIONS.md
From $ARGUMENTS:
--last: Most recent Tier 2 eligible session from metrics.jsonl--from-scan: All sessions where tier2_eligible: true AND
tier2_completed: false in .claude/session-metrics/metrics.jsonl--compare REPORT.md: Previous report to compare against
(default: most recent .claude/session-analysis/insights-*.md)If no metrics.jsonl exists, tell the user:
No metrics found. Run
/session-scanfirst to discover and score sessions.
For each target session, read its entry from metrics.jsonl.
Format the metrics as a context block for subagent prompts:
## Pre-computed Metrics (from /session-scan)
- Friction: 0.42 (retry_loops: 1, user_corrections: 3, approach_changes: 2)
- Fingerprint: bug-fix (confidence: 0.85)
- Plugin opportunity: 0.65 (could use: investigate, quick)
- Tool profile: Read 28.7%, Edit 15.2%, Bash 19.3%, Tidewave 22.8%
- Duration: 78 minutes, 19 user messages, 171 tool calls
Determine PROJECT_ROOT from current working directory.
CRITICAL: One ccrider call = one subagent. Full transcripts are 5-30KB each. Even 3 per worker floods the worker's context.
For EACH session, spawn a haiku subagent:
Task(subagent_type="general-purpose", model="haiku", mode="bypassPermissions", prompt="""
Fetch one session transcript and save it.
1. mcp__ccrider__get_session_messages(session_id: "{SESSION_ID}")
If > 200 messages: use last_n: 200
2. Write transcript to {PROJECT_ROOT}/.claude/session-analysis/{SHORT_ID}-transcript.md
Format:
# Session: {SHORT_ID}
Project: {PROJECT}
Date: {DATE}
Messages: {COUNT}
## Messages
### User (seq N)
{content}
### Assistant (seq N)
{content}
3. Report: "Wrote {SHORT_ID}-transcript.md ({N} messages)"
""")
Spawn ALL fetch subagents in parallel. Wait for all to complete.
Read the analysis template — inline it into subagent prompts:
Glob: **/session-deep-dive/references/analysis-template-v2.md
ALWAYS use subagents — never analyze in main context.
Each analysis subagent prompt:
Read the session transcript at {transcript_path}. Apply the analysis template below to analyze this session. The pre-computed metrics below give you quantitative context — validate them and add qualitative depth.
{metrics_context_block}
{analysis_template_content}
Write your report (under 200 lines) to {report_path}.
Reports go to .claude/session-analysis/{short_id}-report.md.
If 3+ sessions analyzed, spawn context-supervisor (haiku) to compress:
Read all report files in
.claude/session-analysis/*-report.md. Write a consolidated summary to.claude/session-analysis/summaries/consolidated.md. Preserve: friction patterns, plugin opportunities, evidence strength tags. Remove: per-file details, generic observations, repeated context.
Read the synthesis template:
Glob: **/session-deep-dive/references/synthesis-template.md
Read the --compare report (or latest insights file).
Read MEMORY.md for known findings.
If 3+ sessions: read summaries/consolidated.md (NOT individual reports).
If 1-2 sessions: read individual reports directly.
Produce synthesis comparing:
Use Python to safely update metrics.jsonl — never manually
read/modify/rewrite in the LLM context:
python3 -c "
import json
ids = {SESSION_IDS_SET} # e.g., {'ffa155ee-...', '90a74843-...'}
lines = open('{PROJECT_ROOT}/.claude/session-metrics/metrics.jsonl').readlines()
with open('{PROJECT_ROOT}/.claude/session-metrics/metrics.jsonl', 'w') as f:
for line in lines:
entry = json.loads(line)
if entry.get('session_id') in ids:
entry['tier2_completed'] = True
f.write(json.dumps(entry) + '\n')
"
Write synthesis to .claude/session-analysis/insights-{date}.md
Present key findings directly in conversation. Tell user:
Full report:
.claude/session-analysis/insights-{date}.mdPer-session reports:.claude/session-analysis/{id}-report.md
Deep qualitative analysis of high-signal sessions. Spawns subagents with v2 template, synthesizes patterns, compares against known findings. Use after /session-scan.
---name: session-deep-divedescription: Deep qualitative analysis of high-signal sessions. Spawns subagents with v2 template, synthesizes patterns…---# .claude/skills/session-deep-dive/SKILL.mdFAQ
पब्लिशर से .claude/skills/session-deep-dive/SKILL.md डाउनलोड करें, या पाथ कॉपी करके रिपॉज़िटरी खोलें। PlugMCP स्किल को सूचीबद्ध करता है, फ़ाइल होस्ट नहीं करता।
पब्लिशर इसे https://github.com/oliver-kriska/claude-elixir-phoenix पर रखता है।
Claude, Cursor, Codex और Grok Build वह SKILL.md पढ़ सकते हैं जिसे आप पब्लिशर की रिपॉज़िटरी से जोड़ते हैं। जब आप चैट में स्किल के GitHub फ़ोल्डर का लिंक भेजते हैं, तो Grok Bot उसे इंस्टॉल कर देता है।