Stats
Actions
Tags
From dstoic
Generates aggregate reports with trends and Mermaid visualizations across Claude Code sessions. Use for reviewing activity patterns, retrospective summaries, and collaboration insights.
How this skill is triggered — by the user, by Claude, or both
Slash command
/dstoic:retrospect-reportopusThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Generate aggregate views across captured sessions: compute trends, identify patterns, create Mermaid visualizations.
Generate aggregate views across captured sessions: compute trends, identify patterns, create Mermaid visualizations.
Filter sessions by timeframe:
bash ${CLAUDE_PLUGIN_ROOT}/scripts/retrospect-load-sessions.sh $@
First line: PERIOD: YYYY-MM-DD_to_YYYY-MM-DD (use for output filename). Remaining: session file paths.
Read session files — extract: user_prompts, tool_calls, duration_seconds, subagent_spawns, started_at
Compute metrics: total sessions, avg prompts/session, avg tool calls, total duration, date range
Check collaboration insights: list .retro/insights/collab/ for scores (Context quality, Guidance clarity, Critical thinking, Bias awareness)
Identify activity patterns: sessions per day/week, high prompt counts (>15), subagent usage, tool patterns
Generate Mermaid visualizations (xychart-beta for collaboration scores if available)
Write report to .retro/reports/{PERIOD}.md
Report completion: file path, summary stats, suggest reviewing domain/collab insights
See reference.md for report template, Mermaid chart syntax, and metric computation details.
npx claudepluginhub digital-stoic-org/agent-skills --plugin dstoicAnalyzes human-AI collaboration patterns and computes metrics from Claude Code sessions for reviewing interaction quality, technical effectiveness, and cognitive posture.
Generates usage analytics dashboard from Claude Code sessions with epistemic protocol coverage metrics, friction analysis, growth timelines, and improvement recommendations.
Generates an in-chat session report from the active or named transcript — every tool call, sub-agent delegation, and file edit, with diagnostics for missed parallelism, redundant work, and over-serialization.