agentleFS
Sign inStart free
xialangji-debugxialangji-debug/codex-skills-agentmd-obsidian/skills/catstudio-log-extractor/SKILL.md

catstudio-log-extractor

Skill3 starsChanged 2 months agoMITView on GitHub

Extract ASR/CATStudio offline logs, capture the current session, receive an explicitly requested YModem dump, or apply selected-Bug evidence presets. Use for CATStudio ZIP/ICL/ILD files, LogViewer exports, 当前设备抓日志, 抓 dump, and YModem. Start with the narrow mode and expand when its evidence is insufficient.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Do not load device, Dump, or business-acceptance procedures for a local file extraction.

    line 18
  2. Very specific:

    Add only known issue terms with repeated --keyword.

    line 26
  3. Distinctive:

    Only an explicit Dump request may enter YModem receive.

    line 42

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

CATStudio Log Extractor

Route Once

RequestDirect path
Local .zip, .icl/.ild, or extracted folderRun extract_catstudio_logs.py --fast-evidence
Current device logUse the catstudio-capture MCP log-only workflow
Explicit 抓 dump / YModemUse the MCP YModem workflow
Build or flash, then captureHand off once to asr3602-local-build-flash
C10 Bug 3996/4003/4045/4046 attachmentsRun extract_bug_evidence.py --bugs <ids>

Do not load device, Dump, or business-acceptance procedures for a local file extraction. Do not flash firmware from this Skill.

Fast Offline Path

python "$env:USERPROFILE\.codex\skills\catstudio-log-extractor\scripts\extract_catstudio_logs.py" "<log.zip>" --fast-evidence --output-dir "<output>"

Add only known issue terms with repeated --keyword. Expand to --evidence-pack only when the compact MMI evidence is insufficient. Read offline-profiles.md only for a non-default profile or custom category selection.

C10 Presets

python "$env:USERPROFILE\.codex\skills\catstudio-log-extractor\scripts\extract_bug_evidence.py" --bugs 4003,4045,4046

Presets live in profiles/c10-bugs.json. 3996 is marked video-only; never invent CATStudio evidence when no log archive exists. Use --attachments <dir> for a specific selected-Bug snapshot and --list-presets to inspect available presets.

Live And Dump Paths

For current-device log capture or explicit YModem Dump, read live-capture.md. Keep these boundaries:

  • Plain 抓日志 means Stop, wait for a stable current-session .icl/.ild pair, copy it, then optionally extract.
  • Pause is not a save boundary.
  • Only an explicit Dump request may enter YModem receive.
  • Capture success proves transport and session identity, not firmware behavior.
  • Keywords are extraction hints. Business behavior passes only when the requested patterns are present in the current-session record TSV.

Report

Report the input/session identity, outputs, directly supported evidence, missing evidence, and the narrow next step. Keep platform, device, and QA conclusions separate from parser hits. Update fix-pattern memory only when the evidence leads to a completed behavior-changing fix.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free