winui-session-report

Name: winui-session-report
Author: microsoft

82installs20forks

How to install winui-session-report?

microsoft/win-dev-skills/winui-session-report

$npx -y skills add microsoft/win-dev-skills --skill winui-session-report

Installs into the current project.

Summary

Analyze the current or a recent agent session (GitHub Copilot CLI or Claude Code) and generate a diagnostic report. Use when asking for session feedback, debugging agent behavior, or reviewing what happened during a build session.

Files · 1

View on GitHub

SKILL.md

1	### Session Analysis Report
2
3	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.
4
5	### Privacy and sensitivity — surface this guidance to the user
6
7	`Analyze-Session.ps1` always:
8
9	1. Embeds a "Privacy and sensitivity" section at the top of the generated `session-report.md` (right above the Overview table), and
10	2. Prints a yellow PRIVACY NOTICE banner to the console when it finishes writing the file.
11
12	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:
13
14	> ⚠️ 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.
15
16	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.
17
18	### Steps
19
20	1. Run the analysis script to generate the report:
21
22	```powershell
23	# Analyze the most recent session (auto-detects harness) and save report
24	.\Analyze-Session.ps1 -OutputFile session-report.md
25
26	# Or analyze a specific session by ID (searched in both harness locations)
27	.\Analyze-Session.ps1 -SessionId "<session-id>" -OutputFile session-report.md
28
29	# Or analyze a transcript file directly (format sniffed from content)
30	.\Analyze-Session.ps1 -EventsFile <path-to-transcript.jsonl> -OutputFile session-report.md
31
32	# Force a specific format if auto-detection picks the wrong harness
33	.\Analyze-Session.ps1 -Format ClaudeCode -OutputFile session-report.md
34
35	# Skip subagent transcripts (Claude Code only) for a parent-only view
36	.\Analyze-Session.ps1 -SkipSubagents -OutputFile session-report.md
37	```
38
39	Detection rules:
40	- 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.
41	- Environment first: `CLAUDECODE=1` or `CLAUDE_CODE_ENTRYPOINT` -> Claude Code; `COPILOT_*` env vars -> Copilot.
42	- For Claude Code, the most-recent JSONL whose `cwd` matches the current working directory is preferred.
43	- For an explicit `-EventsFile`, the format is sniffed from the first events.
44	- If neither harness is detected, the script exits with a non-zero status and a message naming both supported locations.
45
46	2. Review the generated report — read `session-report.md` and summarize key findings for the user:
47	- How many turns, how long, token usage
48	- What skills were loaded and when
49	- Build success/failure pattern
50	- Any stuck patterns or tooling issues detected
51
52	3. Add your own observations — append a section to the report with any additional context:
53	- Was the final app working? What's missing?
54	- Quality assessment of the generated code
55	- Suggestions specific to what went wrong
56
57	4. Include any tooling improvements or recommendations based on the analysis.
58	- Are there rules that need to be added to the Roslyn analyzer to prevent common mistakes detected during the session?
59	- Were there bugs or issues with winapp run or the BuildAndRun.ps1 script?
60	- Are there features that could be added to lower the number of turns required to complete a task?
61
62	### What the Report Covers
63
64	\| Section \| Details \|
65	\|---------\|---------\|
66	\| Overview \| Harness, session ID, model, duration, turns, tokens (incl. cache tokens for Claude Code) \|
67	\| Prompt \| The original user request \|
68	\| Turn Breakdown \| Turns and tokens by cat

People who liked this also viewed

6 picks

Type

winui-session-report

82installs20forks

View on GitHub

How to install winui-session-report?

microsoft/win-dev-skills/winui-session-report

$npx -y skills add microsoft/win-dev-skills --skill winui-session-report

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	### Session Analysis Report
2
3	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.
4
5	### Privacy and sensitivity — surface this guidance to the user
6
7	`Analyze-Session.ps1` always:
8
9	1. Embeds a "Privacy and sensitivity" section at the top of the generated `session-report.md` (right above the Overview table), and
10	2. Prints a yellow PRIVACY NOTICE banner to the console when it finishes writing the file.
11
12	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:
13
14	> ⚠️ 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.
15
16	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.
17
18	### Steps
19
20	1. Run the analysis script to generate the report:
21
22	```powershell
23	# Analyze the most recent session (auto-detects harness) and save report
24	.\Analyze-Session.ps1 -OutputFile session-report.md
25
26	# Or analyze a specific session by ID (searched in both harness locations)
27	.\Analyze-Session.ps1 -SessionId "<session-id>" -OutputFile session-report.md
28
29	# Or analyze a transcript file directly (format sniffed from content)
30	.\Analyze-Session.ps1 -EventsFile <path-to-transcript.jsonl> -OutputFile session-report.md
31
32	# Force a specific format if auto-detection picks the wrong harness
33	.\Analyze-Session.ps1 -Format ClaudeCode -OutputFile session-report.md
34
35	# Skip subagent transcripts (Claude Code only) for a parent-only view
36	.\Analyze-Session.ps1 -SkipSubagents -OutputFile session-report.md
37	```
38
39	Detection rules:
40	- 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.
41	- Environment first: `CLAUDECODE=1` or `CLAUDE_CODE_ENTRYPOINT` -> Claude Code; `COPILOT_*` env vars -> Copilot.
42	- For Claude Code, the most-recent JSONL whose `cwd` matches the current working directory is preferred.
43	- For an explicit `-EventsFile`, the format is sniffed from the first events.
44	- If neither harness is detected, the script exits with a non-zero status and a message naming both supported locations.
45
46	2. Review the generated report — read `session-report.md` and summarize key findings for the user:
47	- How many turns, how long, token usage
48	- What skills were loaded and when
49	- Build success/failure pattern
50	- Any stuck patterns or tooling issues detected
51
52	3. Add your own observations — append a section to the report with any additional context:
53	- Was the final app working? What's missing?
54	- Quality assessment of the generated code
55	- Suggestions specific to what went wrong
56
57	4. Include any tooling improvements or recommendations based on the analysis.
58	- Are there rules that need to be added to the Roslyn analyzer to prevent common mistakes detected during the session?
59	- Were there bugs or issues with winapp run or the BuildAndRun.ps1 script?
60	- Are there features that could be added to lower the number of turns required to complete a task?
61
62	### What the Report Covers
63
64	\| Section \| Details \|
65	\|---------\|---------\|
66	\| Overview \| Harness, session ID, model, duration, turns, tokens (incl. cache tokens for Claude Code) \|
67	\| Prompt \| The original user request \|
68	\| Turn Breakdown \| Turns and tokens by cat

People who liked this also viewed

6 picks

Type