feat(setup): add documents/projects/ ingestion for independent projects (Path A) (#468)

This commit is contained in:
Oscar Madera
2026-09-16 06:47:15 +02:00
committed by GitHub
parent c93609cd22
commit e92f7d9065
8 changed files with 67 additions and 6 deletions
+20
View File
@@ -12,6 +12,7 @@ documents/
├── linkedin/ # LinkedIn profile export (PDF)
├── diplomas/ # Degree certificates and transcripts
├── references/ # Reference letters
├── projects/ # Independent project summaries, case studies, or portfolio docs
├── postings/ # Raw job posting text, pasted manually for pages Claude can't fetch
│ └── <Company> - <Job Title>.txt # Filename = company + job title, content = full posting text
├── applications/ # Past job applications
@@ -97,6 +98,25 @@ Reference letters from former managers, supervisors, or collaborators.
---
## projects/
Summaries, case studies, READMEs, writeups, or documentation for independent, open-source, freelance, or personal portfolio projects.
**Supported formats:** `.md`, `.txt`, `.pdf`
**What `/setup` extracts:**
- Project name and description
- Problem domain and target audience
- Tech stack, tools, and libraries used
- Key technical challenges and architectural decisions
- Measurable outcomes, metrics, or performance improvements (added to `01-candidate-profile.md` under `## Independent Projects`)
**Naming:** Use descriptive project names, e.g. `project_realtime_chat.md`, `portfolio_compiler.txt`, `open_source_etl.pdf`.
**Tip:** These feed into the `## Independent Projects` section of `01-candidate-profile.md` and provide concrete technical evidence that `/apply` can weave into tailored CVs and cover letters.
---
## postings/
A drop folder for raw job posting text when Claude can't fetch a page directly (bot-blocked ATS platforms like Lever, Greenhouse behind Cloudflare, JS-heavy SPAs that return empty content, etc.). You open the posting yourself and paste the full text into a `.txt` file here.
View File