playbooks

home / skills / tangc / tangzhan-skills / tangzhan-skill-opencodeinsights

tangzhan-skill-opencodeInsights skill

/skills/tangzhan-skill-opencodeInsights

This skill analyzes your OpenCode session history to generate actionable insights and visualization reports that reveal patterns and strategic improvements.

npx playbooks add skill tangc/tangzhan-skills --skill tangzhan-skill-opencodeinsights

Review the files below or copy the command above to add this skill to your agents.

Files (3)
SKILL.md
2.5 KB
---
name: tangzhan-skill-opencodeInsights
description: Generate deep insights and visualization reports from your OpenCode session history. Analyzes work patterns, friction points, and provides strategic recommendations.
---

# OpenCode Insights Analyst

## Role
You are an elite Developer Productivity Analyst and Strategic Coach. Your goal is to analyze the user's OpenCode session history to generate a "OpenCode Insights" HTML report.

## Capabilities
You verify and analyze:
1.  **Work Patterns**: identifying what projects/modules the user worked on.
2.  **Tool Usage**: analyzing which tools (Bash, Edit, Read, etc.) were used and how.
3.  **Friction Points**: finding errors, interruptions, user rejections, and "babysitting" moments.
4.  **Strategic Horizons**: suggesting workflows, automations, and skills based on actual usage.

## Workflow

### 1. Data Gathering
-   Use `session_list` to retrieve recent sessions (default: last 20 sessions or last 2 weeks).
-   Use `session_read` to fetch full transcripts for detailed analysis.
-   *Optional*: If the user provides a specific range or session ID, focus on that.

### 2. Analysis Phase
Analyze the raw logs to extract:
-   **Stats**: Total messages, lines changed (estimate from Edit/Write), files touched, active days.
-   **Project Areas**: Cluster sessions into 3-5 main topics (e.g., "Admin API", "Refactoring", "Documentation").
-   **Wins**: Identify successful complex tasks (multi-file edits, long autonomous runs).
-   **Friction**: Categorize failures (API errors, Tool failures, Ambiguous requests requiring restarts).
-   **Horizon**: Propose specific "next steps" (e.g., "Create a skill for X", "Use TodoWrite for Y").

### 3. Report Generation
1.  Read the template file at `tangzhan-opencode-insights/template.html`.
2.  Generate the HTML content by replacing the template placeholders (e.g., `{{STATS_ROW}}`, `{{PROJECT_AREAS}}`, `{{BIG_WINS}}`) with your analyzed data.
    -   **Important**: Follow the exact HTML structure for each section as found in the reference or inferred from the template context.
    -   Ensure all CSS classes (like `chart-card`, `big-win`, `friction-category`) are used correctly to maintain styling.
    -   Inject the JSON data for `{{RAW_HOUR_COUNTS}}` script variable.
3.  Write the final report to `insight-report.html`.

## Output
-   A fully rendered HTML file named `insight-report.html`.
-   A brief summary in the chat confirming the analysis covers N sessions and pointing the user to the generated file.

Overview

This skill generates deep insights and a visual HTML report from your OpenCode session history to help you understand developer productivity and friction. It summarizes work patterns, tool usage, friction points, and strategic recommendations in a single insight-report.html file. The report is styled and includes charts and JSON data for hour-by-hour activity for easy sharing and archiving.

How this skill works

The skill fetches recent OpenCode sessions (default: last 20 or two weeks) and reads full transcripts to extract stats like messages, files touched, and estimated lines changed. It clusters sessions into 3–5 project areas, identifies wins and friction events, and proposes concrete next steps and automations. The analysis is rendered into a preformatted HTML template with preserved CSS classes and embedded JSON for visualizations, then written to insight-report.html.

When to use it

  • After a sprint or focused work period to review productivity and blockers.
  • When you want evidence-based coaching or to prepare a retrospective.
  • Before planning automations or creating new skills based on real usage.
  • To audit tool usage and identify opportunities for better tool chaining.
  • When preparing a one-page report for managers or teammates.

Best practices

  • Run the report on the last 2–4 weeks of sessions for meaningful patterns.
  • Include session IDs or a focused date range if you want targeted analysis.
  • Keep OpenCode transcripts enabled so edits, runs, and tool outputs are captured.
  • Use the generated horizon suggestions to create small, incremental automations.
  • Review friction categories and prioritize fixes by frequency and impact.

Example use cases

  • Generate a post-sprint productivity report highlighting major wins and recurring blockers.
  • Identify which tools (edit, run, bash) are overused or underused for a given project area.
  • Discover repeated errors and convert them into automated checks or skills.
  • Create a manager-facing summary with charts showing active days and files changed.
  • Seed a backlog of automation ideas (scripts, templates, skills) drawn from real friction points.

FAQ

How many sessions does the report analyze by default?

By default it analyzes the last 20 sessions or the last two weeks, whichever fits the settings.

What output files are produced?

It produces a single insight-report.html file containing charts, styled sections, and embedded JSON for hour counts.