メニュー
Use when the user uploads files or a .zip archive (like user research or logs). Describes how to locate attached files in the sandbox, extract archives if necessary, synthesize findings, and save results back to Mighty.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
| name | files |
| description | Use when the user uploads files or a .zip archive (like user research or logs). Describes how to locate attached files in the sandbox, extract archives if necessary, synthesize findings, and save results back to Mighty. |
Use this workflow when a user uploads files (like .zip archives, logs, or documents) and asks you to analyze their contents.
The system securely stages attached files directly into your sandbox. It does not automatically unzip archives; you must extract them yourself if needed.
Any files attached to the message are staged in the sandbox. You can locate them by exploring the $MIGHTY_ATTACHMENTS_DIR directory.
Tip: Use ls $MIGHTY_ATTACHMENTS_DIR/files/ to see the exact filenames.
If the file is a regular file (e.g., .log, .csv, .md), you can read it directly:
cat $MIGHTY_ATTACHMENTS_DIR/files/<filename>
If the file is a .zip archive, extract it into a local temporary directory within your sandbox:
mkdir -p /tmp/extracted_files
unzip $MIGHTY_ATTACHMENTS_DIR/files/<filename>.zip -d /tmp/extracted_files
Iterate over the files or extracted contents. You can use standard tools like ls, cat, jq, and rg to examine the structure and data.
If the dataset is large, consider:
Once you have completed the analysis and synthesized your findings, you MUST persist the results back into the Mighty graph so they are searchable in the future.
Option A: Create a record (Preferred for structured text/learnings) Create a new spec, doc, or decision with your findings:
mt new doc "Research Findings: Q3 User Interviews" --description-file /path/to/your/synthesis.md
Option B: Upload an artifact file (Preferred for large output files like CSVs or combined logs) If your output is a raw file, upload it as a new artifact:
mt file upload /path/to/your/compiled_results.csv
This command returns a reference (e.g., ![[file <file_id>]]) which you can then link to a task or include in a comment.
Guide for creating, configuring, and leveraging Mighty actions (action_def), specifically focusing on sandbox_command bindings and the use of setup/teardown commands to execute safe repo-local operations. Use when users ask to define actions, leverage setup_commands/teardown_commands, or understand the action execution model.
Upload local screenshot/video artifacts from agent runs and return renderable file embeds (`![[file ...]]`) plus `mighty-file:` refs for thread UI previews.
Upload files and reference them correctly in Mighty specs/tasks/decisions. Use when asked to attach screenshots, logs, PDFs, or other file artifacts and ensure they are represented in both rich text and graph evidence links.
Use the `mt` tool to work with this repo’s Mighty graph: run `mt prime` at session start; prefer `mt search`/`mt tree`/`mt show` before reading code; create specs/decisions/tasks and link evidence; triage `mt inbox`; and close out with `mt closeout` then `mt commit`. For full workflow + templates, run `mt prime`.
Plan work using Mighty (mt) by creating/updating specs and recording decisions, then spawning/structuring implementation tasks. Use when asked to plan/outline/break down a change, draft a spec (feature/rule/invariant/bug), record an ADR-style decision, or turn a fuzzy request into a structured Mighty spec tree with linked tasks.
Track and execute implementation work using Mighty (mt) tasks, with progress comments, linked evidence, recorded decisions, and clean closeout. Use when asked to fix a bug, implement a feature/refactor, or “work through” changes in code while keeping Mighty tasks/specs/decisions updated.