From coquill
Transcript generator for CoQuill. Reads an interview_log.json and manifest.yaml, then writes a human-readable transcript.md to the job folder. Called by the coquill orchestrator — not triggered directly by the user.
npx claudepluginhub houfu/coquill --plugin coquillThis skill uses the workspace's default tool permissions.
You generate a transcript from a completed interview session. The heavy lifting
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Searches prompts.chat for AI prompt templates by keyword or category, retrieves by ID with variable handling, and improves prompts via AI. Use for discovering or enhancing prompts.
Checks Next.js compilation errors using a running Turbopack dev server after code edits. Fixes actionable issues before reporting complete. Replaces `next build`.
You generate a transcript from a completed interview session. The heavy lifting
is handled by scripts/transcribe.py; your job is to invoke it and relay the result.
interview_log_path — path to interview_log.json in the job foldermanifest_path — path to manifest.yaml in the template directoryjob_folder — path to the job output folderoutput_files — comma-separated output file basenames (e.g., agreement.docx, agreement.pdf)ended_at — ISO 8601 timestamp for when the document was renderedThe interview log records the substance of each exchange, not a literal word-for-word
transcript of every micro-turn. When a user answered multiple questions at once, the log
records the net result. The clarification entry handles the exceptional case where
the user asked a substantive question about the document before answering.
Resolve the script path relative to the project root and invoke it:
python scripts/transcribe.py \
--interview-log <interview_log_path> \
--manifest <manifest_path> \
--job-folder <job_folder> \
--output-files "<output_files>" \
--ended-at "<ended_at>"
The script reads both files, builds the four transcript sections (header, interview,
confirmed values, footer), writes transcript.md to the job folder, and prints a
JSON result to stdout.
The script prints JSON: {"transcript_path": "...", "success": true} on success,
or {"transcript_path": null, "success": false, "error": "..."} on failure.