Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
microsoft avatar

Winui Session Report

  • 91 installs
  • 373 repo stars
  • Updated August 3, 2026
  • microsoft/win-dev-skills

winui-session-report is an agent skill that runs Analyze-Session.ps1 to produce diagnostic reports for Copilot CLI or Claude Code sessions.

About

The winui-session-report skill generates a diagnostic report for agent coding sessions by running the bundled Analyze-Session.ps1 script. It auto-detects whether the session came from GitHub Copilot CLI or Claude Code using environment variables and on-disk transcript formats, then parses turns, token usage, skill invocations, build attempts, stuck patterns, and tooling issues into session-report.md. Detection prefers explicit COPILOT_AGENT_SESSION_ID or CLAUDE_SESSION_ID over most-recently-modified files so parallel terminals do not shadow the active session. The agent must surface privacy guidance because reports embed unredacted transcripts including file paths, prompts, secrets, and local environment values. Users may request high-level metric summaries instead of sharing the full file. Report sections cover overview, prompt, turn breakdown, skills, subagents for Claude Code, build analysis, stuck patterns, tooling issues, and per-turn detail. After script output the agent adds observations on app quality, missing work, and WinUI tooling improvements. Triggers include session feedback, debugging agent behavior, or reviewing what happened during a build session.

  • Auto-detects Copilot CLI or Claude Code session transcripts.
  • Analyze-Session.ps1 produces structured session-report.md output.
  • Covers turns, tokens, skills, builds, stuck patterns, and tooling issues.
  • Mandatory privacy warning for unredacted transcript content.
  • Supports explicit session ID, events file, and subagent skip options.

Winui Session Report by the numbers

  • 91 all-time installs (skills.sh)
  • +9 installs in the week ending Aug 4, 2026 (Skillselion tracking)
  • Ranked #250 of 596 Debugging skills by installs in the Skillselion catalog
  • Data as of Aug 5, 2026 (Skillselion catalog sync)
At a glance

winui-session-report capabilities & compatibility

Capabilities
harness auto detection for copilot cli and claud · analyze session.ps1 report generation · turn, token, and skill usage breakdown · build failure and stuck pattern detection · privacy guidance for unredacted transcript shari
Use cases
debugging · planning
npx skills add https://github.com/microsoft/win-dev-skills --skill winui-session-report

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Installs91
repo stars373
Last updatedAugust 3, 2026
Repositorymicrosoft/win-dev-skills

What happened during my agent session and where did builds or tooling get stuck?

Analyze a GitHub Copilot CLI or Claude Code agent session and generate a diagnostic session-report.md with turns, skills, builds, and stuck patterns.

Who is it for?

WinUI developers reviewing Copilot CLI or Claude Code session quality and tooling gaps.

Skip if: Skip for non-agent sessions, live debugging without transcripts, or non-Windows harnesses.

When should I use this skill?

User asks for session feedback, a session report, or review of recent agent build behavior.

What you get

A session-report.md with turn metrics, skill usage, build analysis, stuck patterns, and agent observations.

Files

SKILL.mdMarkdownGitHub ↗

Session Analysis Report

Generate a diagnostic report for an agent session by running the Analyze-Session.ps1 script included with this skill. The script auto-detects whether the current session was produced by GitHub Copilot CLI or Claude Code from environment variables and on-disk file format, and dispatches to the appropriate parser. If neither harness can be detected, the script exits with a clear error.

Privacy and sensitivity — surface this guidance to the user

Analyze-Session.ps1 always:

1. Embeds a "Privacy and sensitivity" section at the top of the generated `session-report.md` (right above the Overview table), and 2. Prints a yellow PRIVACY NOTICE banner to the console when it finishes writing the file.

You (the agent) must surface this guidance to the user in your response — do not let it stay buried in script output the user might not have read. When you finish running the script and reporting the findings, include a short privacy reminder in your reply to the user, in plain second-person language. Use this template, adapting wording as needed:

⚠️ Heads-up before you share `session-report.md` — this file contains your unredacted session transcript: file contents and paths the agent read or edited, your prompts verbatim (including any secrets you may have pasted), tool output, environment values, and local paths under C:\Users\<you>\…. You're responsible for what you share — please open the file in your editor and read it end-to-end before attaching it to a public issue, posting it in chat, or sending it outside your organization. Redact anything sensitive. If you only need to share the high-level metrics, ask me to summarize the file instead of attaching it.

If the user only wants the high-level metrics (turn counts, skill usage, build success rate) without the per-turn detail, summarize the report and share the summary instead of the file — and tell the user that's what you're doing so they don't have to read it themselves to confirm.

Steps

1. Run the analysis script to generate the report:

# Analyze the most recent session (auto-detects harness) and save report
.\Analyze-Session.ps1 -OutputFile session-report.md

# Or analyze a specific session by ID (searched in both harness locations)
.\Analyze-Session.ps1 -SessionId "<session-id>" -OutputFile session-report.md

# Or analyze a transcript file directly (format sniffed from content)
.\Analyze-Session.ps1 -EventsFile <path-to-transcript.jsonl> -OutputFile session-report.md

# Force a specific format if auto-detection picks the wrong harness
.\Analyze-Session.ps1 -Format ClaudeCode -OutputFile session-report.md

# Skip subagent transcripts (Claude Code only) for a parent-only view
.\Analyze-Session.ps1 -SkipSubagents -OutputFile session-report.md

Detection rules:

  • The current session is preferred when an explicit ID is available: COPILOT_AGENT_SESSION_ID (Copilot CLI) or CLAUDE_SESSION_ID (Claude Code) take priority over "most recently modified" so a parallel session in another terminal can't shadow the one the skill was invoked from.
  • Environment first: CLAUDECODE=1 or CLAUDE_CODE_ENTRYPOINT -> Claude Code; COPILOT_* env vars -> Copilot.
  • For Claude Code, the most-recent JSONL whose cwd matches the current working directory is preferred.
  • For an explicit -EventsFile, the format is sniffed from the first events.
  • If neither harness is detected, the script exits with a non-zero status and a message naming both supported locations.

2. Review the generated report — read session-report.md and summarize key findings for the user:

  • How many turns, how long, token usage
  • What skills were loaded and when
  • Build success/failure pattern
  • Any stuck patterns or tooling issues detected

3. Add your own observations — append a section to the report with any additional context:

  • Was the final app working? What's missing?
  • Quality assessment of the generated code
  • Suggestions specific to what went wrong

4. Include any tooling improvements or recommendations based on the analysis.

  • Are there rules that need to be added to the Roslyn analyzer to prevent common mistakes detected during the session?
  • Were there bugs or issues with winapp run or the BuildAndRun.ps1 script?
  • Are there features that could be added to lower the number of turns required to complete a task?

What the Report Covers

SectionDetails
OverviewHarness, session ID, model, duration, turns, tokens (incl. cache tokens for Claude Code)
PromptThe original user request
Turn BreakdownTurns and tokens by category (building, coding, exploring, subagent dispatch, etc.)
SkillsWhich were invoked and when, including from inside subagent transcripts
Subagents(Claude Code only) Per-agent breakdown of dispatched subagents and their work
Build AnalysisBuild attempts, failures, errors, whether BuildAndRun.ps1 was used
Stuck PatternsBuild loops, repeated file reads, obj/ clean cycles
Tooling IssuesAuto-detected improvement opportunities
Turn DetailEvery turn with tools used and errors flagged, parent and subagent transcripts shown separately

When to Use

  • When the user asks for a session report to understand what happened during an agent session.

Related skills

FAQ

What does winui-session-report produce?

A session-report.md with turns, tokens, skills, build results, stuck patterns, and tooling issues.

When should I use winui-session-report?

When reviewing a Copilot CLI or Claude Code session to understand agent behavior and failures.

Is winui-session-report safe to install?

Review the Security Audits panel on this page before installing in production.

Debuggingworkflow

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.