diff --git a/input/AGENTS.md b/input/AGENTS.md index c6f160b..40771a1 100644 --- a/input/AGENTS.md +++ b/input/AGENTS.md @@ -9,7 +9,7 @@ Automate the upstream resume customization workflow. Monitor the job-description - `ForCustomizing/outbox/YYYY/MM/DD/HHMM/` – timestamped folders containing Codex output Markdown (`-.md`) along with the exact prompt and the cleaned job description that fed Codex. - `ForCustomizing/processed/YYYY/MM/DD/HHMM/` – archives of job descriptions that Codex processed successfully. - `ForCustomizing/failed/` – captures job descriptions when Codex errors or a recoverable issue occurs. Fatal configuration errors still exit the container. -- `templates/JobDescriptionNormalizerPrompt.md.example` – default instructions that scrub recruiter chatter and extract metadata; copy to `JobDescriptionNormalizerPrompt.md` to override. +- `templates/JobDescriptionNormalizerPrompt.md.example` – default instructions that scrub recruiter chatter while preserving all job description content and extract metadata; copy to `JobDescriptionNormalizerPrompt.md` to override. - `templates/ResumeCustomizerPrompt.md.example` – default resume-customization instructions; copy to `ResumeCustomizerPrompt.md` to override. ## Running the Input Processor diff --git a/input/README.md b/input/README.md index 0f190d2..929ce6a 100644 --- a/input/README.md +++ b/input/README.md @@ -6,7 +6,7 @@ The input side of ResumeCustomizer prepares job-specific Markdown resumes by sti 1. Ensure `input/resume/` contains exactly one Markdown resume. 2. Drop a single job-description file (plain text or Markdown) into `input/ForCustomizing/inbox/`. 3. Start the watcher stack (`input/Docker/run-input-processor.sh up -d`). -4. The watcher normalizes the messy job description via Codex (using `templates/JobDescriptionNormalizerPrompt.md.example` by default), then combines the cleaned Markdown, the base resume, and the resolved customization prompt into a second Codex run that writes the generated resume to `ForCustomizing/outbox/YYYY/MM/DD/HHMM/-.md`. +4. The watcher normalizes the messy job description via Codex (using `templates/JobDescriptionNormalizerPrompt.md.example` by default), stripping recruiter chatter while preserving every job-related detail, then combines the cleaned Markdown, the base resume, and the resolved customization prompt into a second Codex run that writes the generated resume to `ForCustomizing/outbox/YYYY/MM/DD/HHMM/-.md`. 5. Successful runs archive the job description under `ForCustomizing/processed/`, copy both the prompt and the cleaned job description into the same outbox folder, and leave the Codex output for human review. Failures move the job description into `ForCustomizing/failed/`. The human operator reviews the Codex output Markdown, makes any edits, and then manually hands it off to the output pipeline for document rendering. diff --git a/input/templates/JobDescriptionNormalizerPrompt.md.example b/input/templates/JobDescriptionNormalizerPrompt.md.example index 160ebd7..5066636 100644 --- a/input/templates/JobDescriptionNormalizerPrompt.md.example +++ b/input/templates/JobDescriptionNormalizerPrompt.md.example @@ -16,7 +16,8 @@ Job Title: ``` Guidelines: -- Strip all chatter that is not part of the actual role description. +- Preserve every piece of content that belongs to the job description (responsibilities, requirements, benefits, etc.). Do **not** summarize, condense, or delete substantive details. +- Only remove extraneous recruiter chatter such as greetings, signatures, contact blocks, forwarding notes, or metadata unrelated to the role itself. - If multiple companies or roles appear, pick the primary one the candidate should target. - Normalize whitespace, headings, and bullet lists in the Markdown output. - Omit personal identifiers for recruiters or candidates unless they are essential job facts. @@ -24,4 +25,4 @@ Guidelines: note that it is inferred (e.g., “ (inferred)”). - Never add commentary outside the format shown above. -The raw content follows. +The raw content follows verbatim. Retain all job-related text.