resume-bank-editor
Skill0 starsChanged 4 months agoMITView on GitHub
Autonomous job-tailoring and bank CRUD optimization loop for agentic resume editing.
In this repository3 other files it gives its agents.
- AGENTS.mdAGENTS.md
- project-auditorSkill
- resume-optimizerSkill
The file
We split this skill into the rules it gives an agent
7 rules. About 0 are common, 3 are distinctive, and 4 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 13
Run --summary to inspect active roles (configurations), experience entries, project entries, and bullet IDs with character counts and …
- Distinctive: line 19
Create a dedicated role target for a specific job posting or update an existing role:
- Distinctive: line 29
Run schema linting to check character count warnings (target ~220–245 characters per bullet for 2 full lines):
- Distinctive: line 35
Use CLI CRUD flags to add, edit, or delete entries and bullets without raw JSON formatting risks:
- Very specific: line 52
Verify stdout output reports PASSED (1 Page) and vertical page fill between 82.0% and 95.0%.
- Very specific: line 53
If OVERFLOW occurs: trim 3–5 words from longer bullets using --edit-bullet.
- Very specific: line 54
If UNDERFLOW occurs: expand bullets or select an extra project in --edit-role.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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.
Files
Resume Bank Editor Skill
This skill provides step-by-step instructions for AI agents operating on data/resume_bank.json to tailor resumes for specific job descriptions, modify entries/bullets via CLI CRUD flags, lint schema rules, build PDFs, and optimize visual page budget metrics.
Autonomous Optimization Loop
- Inspect Bank Summary:
Run
--summaryto inspect active roles (configurations), experience entries, project entries, and bullet IDs with character counts and verification statuses:python3 build_resume.py --summary - Tailor or Add a Role Configuration:
Create a dedicated role target for a specific job posting or update an existing role:
# Add a new role selecting target experiences and projects python3 build_resume.py --add-role --key backend_eng --title "Backend Engineer" --out backend_resume --experiences env_science_lab,caas_care_lab --projects smart_cache,distributed_kv # Or edit selected items for an existing role python3 build_resume.py --edit-role swe --projects smart_cache,env_science_lab - Audit Bullet Character Density:
Run schema linting to check character count warnings (target ~220–245 characters per bullet for 2 full lines):
python3 build_resume.py --lint - Execute Precise Deterministic Edits:
Use CLI CRUD flags to add, edit, or delete entries and bullets without raw JSON formatting risks:
# Add a new bullet to an experience or project entry python3 build_resume.py --add-bullet smart_cache --id cache_perf --text "Engineered an in-memory caching engine reducing latency by 93% across zonal grid datasets." # Edit an existing bullet text by ID python3 build_resume.py --edit-bullet env_geo_pipeline --text "Engineered a Python geospatial processing package using GeoPandas, Shapely, and Rasterio with UTM 60S projections to render interactive H3 maps." # Delete a bullet by ID python3 build_resume.py --delete-bullet cache_perf - Build Target PDF & Verify Page Budget:
Compile PDF for the specific role profile:
python3 build_resume.py --role backend_eng- Verify stdout output reports
PASSED (1 Page)and vertical page fill between 82.0% and 95.0%. - If
OVERFLOWoccurs: trim 3–5 words from longer bullets using--edit-bullet. - If
UNDERFLOWoccurs: expand bullets or select an extra project in--edit-role.
- Verify stdout output reports
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
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.

