New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Session Deep Dive

by oliver-kriska in oliver-kriska/claude-elixir-phoenix

Deep qualitative analysis of high-signal sessions. An agent skill from oliver-kriska/claude-elixir-phoenix.

MITAuto-check passedAgent Workflows

Install Session Deep Dive

skills CLI
$ npx skills add oliver-kriska/claude-elixir-phoenix --skill session-deep-dive -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install oliver-kriska/claude-elixir-phoenix session-deep-dive --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/oliver-kriska/claude-elixir-phoenix.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/session-deep-dive .claude/skills/session-deep-dive && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
session-deep-dive
GitHub stars
565
Token cost
~1.6k tokens
SKILL.md length
491 words
Files
3 (incl. references)
Skills in repo
111
Repo updated
First seen
Licence
MIT

At a glance

Deep qualitative analysis of high-signal sessions. An agent skill from oliver-kriska/claude-elixir-phoenix.

  • Works in 8 steps: Resolve Target Sessions → Load Pre-computed Metrics → Fetch Transcripts — One Subagent Per… → …
  • Tasks that involve Subagents
  • SKILL.md covers Requirements, Usage, Pipeline and Output Files, plus 1 more section
  • Calls python3

What it does

Session Deep Dive is an agent skill from oliver-kriska/claude-elixir-phoenix. Deep qualitative analysis of high-signal sessions. Spawns subagents with v2 template, synthesizes patterns, compares against known findings. Use after /session-scan.

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including reference files (for example `references/analysis-template-v2.md` and `references/synthesis-template.md`).

It sits in Agent Workflows, covering Subagents. The repository describes itself as: Claude Code plugin for Elixir/Phoenix/LiveView — 26 specialist agents, Iron Laws enforcement, and Tidewave MCP integration. Plan features with parallel research agents, execute… The licence is MIT.

When your agent uses it

  • Tasks that involve Subagents

Example prompts

  • “/session-deep-dive”

Requirements

  • Python 3

Workflow steps

8 steps, taken from the step headings in SKILL.md.

  1. Resolve Target Sessions
  2. Load Pre-computed Metrics
  3. Fetch Transcripts — One Subagent Per Session
  4. Analyze Sessions
  5. Compress (if 3+ sessions)
  6. Synthesize
  7. Update Ledger
  8. Write Output

What it can do on your machine

Read from SKILL.md and the folder at commit 9767a82. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • python3

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • github.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Session Deep Dive loads about 1.6k tokens when it runs, and up to ~3.2k if it reads all its reference files. Until then it costs about 46 tokens; SKILL.md has 491 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~46
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~3.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from oliver-kriska/claude-elixir-phoenix at commit 9767a82, republished under its MIT licence (© oliver-kriska). 491 words, ~1,622 tokens.

Download SKILL.mdSave it as .claude/skills/session-deep-dive/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
session-deep-dive
description
Deep qualitative analysis of high-signal sessions. Spawns subagents with v2 template, synthesizes patterns, compares against known findings. Use after /session-scan.
argument-hint
<session-id> | --last | --from-scan [--compare REPORT.md]
disable-model-invocation
true

Session Deep Dive (Tier 2)

Qualitative analysis of high-signal sessions identified by /session-scan. Spawns subagents with pre-computed metrics context for focused analysis.

Requirements

Requires ccrider MCP. If not available:

ccrider MCP is required. See: https://github.com/neilberkman/ccrider

Usage

/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

Pipeline

Step 1: Resolve Target Sessions

From $ARGUMENTS:

  • Session ID: Single session to analyze
  • --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-scan first to discover and score sessions.

Step 2: Load Pre-computed Metrics

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.

Step 3: Fetch Transcripts — One Subagent Per Session

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.

Step 4: Analyze Sessions

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.

  • 1-6 sessions: Spawn sonnet subagents (one per session)
  • 7+ sessions: Spawn haiku subagents for speed

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.

Step 5: Compress (if 3+ sessions)

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.

Show full SKILL.md (192 more words)Show less
Step 6: Synthesize

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:

  • New findings vs known patterns from MEMORY.md
  • Confirmed patterns (seen before, still present)
  • New patterns (not in previous reports)
  • Resolved patterns (previously noted, no new occurrences)
Step 7: Update Ledger

Use Python to safely update metrics.jsonl — never manually read/modify/rewrite in the LLM context:

bash
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')
"
Step 8: Write Output

Write synthesis to .claude/session-analysis/insights-{date}.md

Present key findings directly in conversation. Tell user:

Full report: .claude/session-analysis/insights-{date}.md Per-session reports: .claude/session-analysis/{id}-report.md

Output Files

FilePurpose
.claude/session-analysis/{id}-transcript.mdRaw transcript
.claude/session-analysis/{id}-report.mdPer-session analysis
.claude/session-analysis/summaries/consolidated.mdCompressed reports
.claude/session-analysis/insights-{date}.mdCross-session synthesis

Iron Laws

  1. ONE ccrider call = ONE subagent — never batch multiple fetches
  2. NEVER fetch or analyze in main context — always subagents
  3. Absolute paths in subagent prompts — subagents don't inherit skill context
  4. Python for jsonl updates — never manually rewrite in LLM context
  5. ALWAYS pass pre-computed metrics to analysis subagents — don't re-derive
  6. NEVER skip synthesis — cross-session patterns are the real value
  7. TAG evidence strength — every finding must be STRONG/MODERATE/WEAK

© oliver-kriska, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (references) in .claude/skills/session-deep-dive of oliver-kriska/claude-elixir-phoenix.

  • SKILL.md
  • references/analysis-template-v2.md
  • references/synthesis-template.md

Open the folder on GitHubat commit 9767a82

Compare with similar skills

Session Deep Dive next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Session Deep Dive compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Session Deep Dive this skilloliver-kriska/claude-elixir-phoenix565—~1.6kAutomated safety check: PassMIT
Claude Code Agent Developmentanthropics/claude-plugins-official38k7 repos~2.8kAutomated safety check: PassApache-2.0
Subagent Driven DevelopmentAsvarox/allkaraoke26137 repos~1.2kAutomated safety check: PassNone
Dispatching Parallel Agentsultralisp/ultralisp25840 repos~1.5kAutomated safety check: PassNone
Paseo Advisor Second Opiniongetpaseo/paseo20k1 repos~756Automated safety check: PassCustom licence
Task Observerrebelytics/one-skill-to-rule-them-all3.2k1 repos~12kAutomated safety check: PassCC-BY-4.0

Similar skills

  • Claude Code Agent Development

    anthropics/claude-plugins-official

    Official

    Explains how to write agents for Claude Code plugins: the markdown file with YAML frontmatter, trigger descriptions, model and color settings, and system prompt design.

    38k GitHub starsUsed in 7 repos~2.8k tokens
    Agent WorkflowsAuto-check passed

  • Subagent Driven Development

    Asvarox/allkaraoke

    A skill your agent uses when executing implementation plans with independent tasks in the current session

    261 GitHub starsUsed in 37 repos~1.2k tokens
    Agent WorkflowsAuto-check passed

  • Dispatching Parallel Agents

    ultralisp/ultralisp

    A skill your agent uses when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

    258 GitHub starsUsed in 40 repos~1.5k tokens
    Agent WorkflowsAuto-check passed

  • Paseo Advisor Second Opinion

    getpaseo/paseo

    Launches one separate agent through Paseo to give a second opinion on the current task, with a self-contained briefing and no permission to edit files.

    20k GitHub starsUsed in 1 repo~756 tokens
    Agent WorkflowsAuto-check passed

  • Task Observer

    rebelytics/one-skill-to-rule-them-all

    Monitors task execution for skill improvement opportunities.

    3.2k GitHub starsUsed in 1 repo~12k tokens
    Agent WorkflowsAuto-check passed

  • O2 Review Loop

    openobserve/openobserve

    Splits a change into planner, coder and independent reviewer roles: you confirm a spec, a subagent implements it, and a separate reviewer checks each round's local WIP commit.

    22k GitHub stars~3.7k tokensUpdated today
    Agent WorkflowsAuto-check passed

More from oliver-kriska/claude-elixir-phoenix

All 111 skills in this repo

  • Codex Ab

    oliver-kriska/claude-elixir-phoenix

    Run an A/B codex review experiment — holistic codex review vs 3 focused dimension passes (security, ecto, liveview) on the branch diff, classify findings, report a panel-value verdict.

    565 GitHub stars~977 tokensUpdated 4 days ago
    Auto-check passed

  • Audit

    oliver-kriska/claude-elixir-phoenix

    Project health audit and health check — architecture, performance, tests, dependencies, code quality.

    565 GitHub stars~2k tokensUpdated 4 days ago
    Auto-check passed

  • Compound Docs

    oliver-kriska/claude-elixir-phoenix

    Searchable Elixir/Phoenix/Ecto solution documentation system with; Use when consulting past solutions…

    565 GitHub stars~528 tokensUpdated 4 days ago
    Auto-check passed

  • Compound Docs

    oliver-kriska/claude-elixir-phoenix

    Searchable Elixir/Phoenix/Ecto solution documentation system with YAML frontmatter.

    565 GitHub stars~547 tokensUpdated 4 days ago
    Auto-check passed

  • Deploy

    oliver-kriska/claude-elixir-phoenix

    Elixir/Phoenix deployment patterns — Dockerfile, fly.toml, runtime.exs, mix release, rel/ overlays.

    565 GitHub stars~1.1k tokensUpdated 4 days ago
    Auto-check passed

  • Deps Update

    oliver-kriska/claude-elixir-phoenix

    Bump outdated Hex deps — inventory, snapshot changelogs, update, fix breaks, split reviewable PRs (patches bundled, majors solo).

    565 GitHub stars~1.4k tokensUpdated 4 days ago
    Auto-check passed

Categories

Questions about Session Deep Dive

What does Session Deep Dive do?

Deep qualitative analysis of high-signal sessions. An agent skill from oliver-kriska/claude-elixir-phoenix. Session Deep Dive is an agent skill from oliver-kriska/claude-elixir-phoenix. Deep qualitative analysis of high-signal sessions.

When should I use Session Deep Dive?

Session Deep Dive fits situations like: tasks that involve Subagents.

How do I install Session Deep Dive in Claude Code?

Run `npx skills add oliver-kriska/claude-elixir-phoenix --skill session-deep-dive -a claude-code`. Or copy the skill folder (.claude/skills/session-deep-dive in oliver-kriska/claude-elixir-phoenix) into .claude/skills/session-deep-dive in your project. Claude Code loads it when a task matches its description.

How do I install Session Deep Dive in Codex?

Run `npx skills add oliver-kriska/claude-elixir-phoenix --skill session-deep-dive -a codex`. Or copy the skill folder (.claude/skills/session-deep-dive in oliver-kriska/claude-elixir-phoenix) into .agents/skills/session-deep-dive in your project. Codex loads it when a task matches its description.

Can I use Session Deep Dive in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add oliver-kriska/claude-elixir-phoenix --skill session-deep-dive -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/session-deep-dive, .gemini/skills/session-deep-dive, .github/skills/session-deep-dive and .opencode/skills/session-deep-dive in your project.

What does Session Deep Dive need to run?

Going by SKILL.md and its folder, Session Deep Dive needs the command-line tools its instructions call (python3). Our summary lists: Python 3.

Does Session Deep Dive access the network?

SKILL.md names 1 domain. As links in the text: github.com. This is read from the text; nothing was executed.

Is Session Deep Dive safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Session Deep Dive use?

Session Deep Dive is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Session Deep Dive use?

About 1.6k tokens (SKILL.md is roughly 6.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.6k tokens, read only when the agent opens those files.

What are the alternatives to Session Deep Dive?

Skills that share tags, products or a category with Session Deep Dive: Claude Code Agent Development (anthropics/claude-plugins-official, 38k stars), Subagent Driven Development (Asvarox/allkaraoke, 261 stars), Dispatching Parallel Agents (ultralisp/ultralisp, 258 stars) and Paseo Advisor Second Opinion (getpaseo/paseo, 20k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Session Deep Dive?

oliver-kriska (a GitHub user) maintains it in oliver-kriska/claude-elixir-phoenix, which has 565 GitHub stars. The repository holds 111 skills in this directory. The repository was last updated on October 5, 2026.

Source: oliver-kriska/claude-elixir-phoenix on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.