← All skills
analyze-chat-export
82 / 100 · Low risk
Fine to try. Some of what it can do is expected: a coding skill usually runs build and test commands.
By diegosouzapw/awesome-omni-skill (GitHub) · coding · 66 stars · scanned at commit a6b3c30
Export and analyze VS Code Copilot chat logs for retrospective metrics. Extracts model usage, tool invocations, approval patterns, and timing data.
Works with any agent that supports SKILL.md skills.
What this skill can do
Runs commands on your computer
This is disclosed by the author in the skill's SKILL.md or README. Expected for a coding skill.
Found in 15 places.
Show 12 more
- skills/ai-agents/analyze-chat-export/SKILL.md, line 174
jq '[.requests[].modelId] | group_by(.) | map({model: .[0], count: length}) | sort_by(-.count)' "$CHAT_FILE" - skills/ai-agents/analyze-chat-export/SKILL.md, line 180
jq '[.requests[].response[] | select(.kind == "toolInvocationSerialized")] | length' "$CHAT_FILE" - skills/ai-agents/analyze-chat-export/SKILL.md, line 189
jq '[.requests[].response[] | select(.kind == "toolInvocationSerialized") | .isConfirmed.type // "unknown"] | group_by(.) | map({type: .[0], count: length})' "$ - skills/ai-agents/analyze-chat-export/SKILL.md, line 198
jq ' - skills/ai-agents/analyze-chat-export/SKILL.md, line 217
jq ' - skills/ai-agents/analyze-chat-export/SKILL.md, line 230
jq '[.requests[].result.timings.totalElapsed // 0] | add / length / 1000' "$CHAT_FILE" - skills/ai-agents/analyze-chat-export/SKILL.md, line 242
jq '[.requests[] | select(.vote != null) | .vote] | group_by(.) | map({vote: (if .[0] == 1 then "up" else "down" end), count: length})' "$CHAT_FILE" - skills/ai-agents/analyze-chat-export/SKILL.md, line 251
jq '[.requests[].editedFileEvents[]? | {uri: .uri.path, status: (if .eventKind == 1 then "kept" elif .eventKind == 2 then "undone" else "modified" end)}]' "$CHA - skills/ai-agents/analyze-chat-export/SKILL.md, line 260
jq '[.requests[] | select(.modelState.value == 3) | {id: .requestId, error: .result.errorDetails.message}]' "$CHAT_FILE" - skills/ai-agents/analyze-chat-export/SKILL.md, line 275
jq ' - skills/ai-agents/analyze-chat-export/SKILL.md, line 319
jq ' - skills/ai-agents/analyze-chat-export/SKILL.md, line 335
jq '
Changes files outside its own folder
The author does not mention this.
Found in 1 place.
Sends data to these websites: raw.githubusercontent.com
The author does not mention this.
Found in 1 place.
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'analyze-chat-export' ] || [ -L ~/.agents/skills/'analyze-chat-export' ]; then echo 'A skill folder named analyze-chat-export already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/diegosouzapw/awesome-omni-skill' "$d" && git -C "$d" checkout --quiet 'a6b3c3005cedf056a48b084671c6282426d6e9fc' -- 'skills/ai-agents/analyze-chat-export' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/ai-agents/analyze-chat-export' ~/.agents/skills/'analyze-chat-export' && rm -rf "$d"; fi
Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'analyze-chat-export' ~/.claude/skills/'analyze-chat-export' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.
Badge for your README
The badge for diegosouzapw/awesome-omni-skill shows the score of its lowest-scoring skill.
[](https://zalavijaysinh.github.io/skilltrust/repos/diegosouzapw/awesome-omni-skill/)
Score history
| Date | Version | Score |
|---|
| 2026-11-07 | a6b3c30 | 82 |