resume-tailor
Skill0 starsChanged 7 months agoMITView on GitHub
Tailor a resume for a specific job posting by scoring achievements against requirements, selecting the best template variant (Innovation/Delivery/Generic), generating a tailored .docx and PDF, and drafting a cover letter. Uses master YAML data from the active user's resume data. NEVER fabricates achievements.
32 other projects use a version of this.
Adopted by
Most recently taken up by
- studiocon/resume-templatetheir own version, first seen Nov 15, 2026
- wangssc/resume-tailor-skilltheir own version, first seen Nov 15, 2026
- chezou/skillstheir own version, first seen Nov 15, 2026
- skills-agents-co/skills-and-agents-librarytheir own version, first seen Nov 11, 2026
- gkmr/career-agent-kittheir own version, first seen Nov 8, 2026
- sunil-kumarr/JobIttheir own version, first seen Nov 8, 2026
Used with
Projects with it also use interview-prep.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
AnthropicSkillinterview-prep
Create structured interview plans with competency-based questions and scorecards. Trigger with "interview plan for", "interview questions for", "how should we interview", "scorecard for", or when the user is preparing to interview candidates.
Also in 3 projects that use this
Other versions32 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 32
- claude-office-skills/skills★ 433same name
- olegvg/resume-tailor-plugin★ 44same name
- vignzpie/resume-agent-skills★ 17same name
- Mahashwetha/Job-search-email-system-claude★ 12same name
- FlavioZanoni/mercury★ 8same name
- opencue/cuecards★ 8same name
- tstapler/dotfiles★ 8same name
- KinomotoMio/resumaker★ 5same name
- chezou/skills★ 4same name
- wexxwuther/job-hunter★ 4same name
22 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository14 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- application-trackerSkill
- applySkill
- cold-outreachSkill
- company-deep-diveSkill
- contact-populationSkill
- job-searchSkill
- meeting-prepSkill
- onboard-userSkill
- session-checkpointSkill
- session-endSkill
- session-startSkill
- warm-followupSkill
The file
We split this skill into the rules it gives an agent
10 rules. 0 are common, 4 are distinctive, and 6 are very specific to this project.
0
Common
Most of the 27 edited versions we read keep these.
4
Distinctive
This author's own choices. Worth a look.
6
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 48
Read the job posting (from applications/jobs/{company}-{job}.md / .yaml or URL).
- Very specific: line 54
Read default mapping from applications/resumes/data/{user-slug}/user-config.yaml (template_mapping):
- Very specific: line 63
Read the full JD and create applications/jobs/{company}-{job-slug}.yaml:
- Very specific: line 106
Update the job YAML with text_overrides, summary_override, skills_override, optionally title_override.
- Distinctive: line 114
NEVER include soft capability statements like "Strategic Partnership", "Cross-Functional Leadership".
- Distinctive: line 134
Read scorecard to identify failures.
- Distinctive: line 140
If WARN: flag to user, proceed.
- Distinctive: line 142
NEVER proceed to PDF or submission with FAIL.
- Very specific: line 162
Create Interaction record with type Resume Tailored.
- Very specific: line 212
Do not hardcode user-specific reframing rules in this skill.
“Common” is measured: kept by at least 6 in 10 of the 27 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Resume Tailor
Generates role-specific resume versions and cover letters tailored to individual job postings.
What This Skill Does
- Template selection — Innovation / Delivery / Generic variant based on role type
- Achievement scoring — score each achievement against job requirements (0-10)
- Content selection — pick top-scoring achievements per experience entry
- Resume generation — create tailored
.docxviapython-docx - PDF conversion — via
docx2pdf - Cover-letter drafting — 250-400 words, Hook-Alignment-Value-CTA structure
- Database integration — update Job Posting record with the resume version used
Prerequisites
Required:
- Python 3.10+ with
python-docx,pyyaml,docx2pdf - Active user's master data:
applications/resumes/data/{user-slug}/master-experience.yaml - Active user's skills inventory:
applications/resumes/data/{user-slug}/skills-inventory.yaml - Active user's user-config:
applications/resumes/data/{user-slug}/user-config.yaml - Shared role schemas:
applications/resumes/data/role-type-schemas.yaml(optional — falls back to defaults)
Multi-user: the active user's slug (from JOB_HUNT_USER) determines which data directory to use.
Python tools:
tools/resume-tailor/tailor-resume.py— supports--user {slug}flagtools/resume-tailor/generate-pdf.pytools/resume-tailor/generate-cover-letter-pdf.py— supports--user {slug}flagtools/resume-tailor/quality-gate.py
Quick Start
"Tailor my resume for the Senior Program Manager role at Acme Renewables"
"Create a resume version using the Innovation template for the AI Product Lead role at Globex Power"Workflow
Step 1: Analyze job posting
- Read the job posting (from
applications/jobs/{company}-{job}.md/.yamlor URL). - Extract must-have requirements, nice-to-haves, and industry keywords.
- Determine role category from
config/user-profile.yamltarget_roles[].
Step 2: Select template
Read default mapping from applications/resumes/data/{user-slug}/user-config.yaml (template_mapping):
- PM / Operations → Delivery
- AI-DT / Product → Innovation
- Mixed / unclear → Generic
User can override.
Step 3: Create job YAML with keyword extraction
Read the full JD and create applications/jobs/{company}-{job-slug}.yaml:
company: "Acme Renewables"
job_title: "Senior Program Manager"
role_category: "PM"
template: "Delivery"
requirements:
- "..."
nice_to_haves:
- "..."
industry_keywords:
- "..."Step 4: Run scoring (--scoring-only mode)
python tools/resume-tailor/tailor-resume.py \
--user {user-slug} \
--job-file applications/jobs/{company}-{job-slug}.yaml \
--output-dir applications/{user-slug}/{company}-{job-slug}/ \
--scoring-onlyOutputs JSON: selected achievements, scores, matched requirements/keywords per bullet.
Step 5: Rewrite bullets to mirror JD (Claude LLM step)
Review the JSON and rewrite each selected bullet:
Rules:
- Mirror JD terminology — exact phrasing.
- Front-load JD keywords.
- Preserve all facts — every metric, number, company name, timeline.
- Emphasise matching aspects — restructure to lead with what JD emphasises.
- Keep similar length — max +10 words.
- NEVER fabricate — no new achievements or claims.
Also write:
summary_override— summary echoing JD themesskills_override— skills line reordered to prioritise JD-mentioned tools (see format below)title_override— optional, when template title doesn't fit
Update the job YAML with text_overrides, summary_override, skills_override, optionally title_override.
skills_override format (MANDATORY):
"Technical Skills: Power BI | JIRA | SAP | SQL | AWS | Python | Docker | Agile/Scrum | <user certifications from config/user-profile.yaml credentials[]>"- First 60% MUST be hard tools.
- Last 40% can include methodologies (Agile/Scrum, PMP, CSPO, PRINCE2, Lean/Six Sigma).
- NEVER include soft capability statements like "Strategic Partnership", "Cross-Functional Leadership".
Step 6: Generate resume (full mode with overrides)
python tools/resume-tailor/tailor-resume.py \
--user {user-slug} \
--job-file applications/jobs/{company}-{job-slug}.yaml \
--output-dir applications/{user-slug}/{company}-{job-slug}/Step 6.5: Quality gate (MANDATORY — BLOCKING)
python tools/resume-tailor/quality-gate.py \
--resume applications/{user-slug}/{company}-{job-slug}/resume.docx \
--job-file applications/jobs/{company}-{job-slug}.yamlIf FAIL:
- Read scorecard to identify failures.
- Fix the job YAML (more overrides, fix
skills_override, addtitle_override). - Regenerate (re-run Step 6).
- Re-run quality gate.
- Repeat until PASS.
If WARN: flag to user, proceed.
NEVER proceed to PDF or submission with FAIL.
Step 7: Generate PDF
python tools/resume-tailor/generate-pdf.py \
--input applications/{user-slug}/{company}-{job-slug}/resume.docxStep 8: Draft cover letter
Create at applications/{user-slug}/{company}-{job-slug}/cover-letter.md:
- Hook (1-2 sentences) — reference specific company news/initiative.
- Alignment (2-3 sentences) — connect user's experience to their needs.
- Value (2-3 sentences) — unique value proposition (regional + AI + enterprise — pull from
config/user-profile.yamlvalue_props[]). - CTA (1-2 sentences) — specific next step.
Step 9: Update database
- Set
resume_version_usedfield on Job Posting record. - Create Interaction record with type
Resume Tailored.
Output Structure
applications/{user-slug}/{company}-{job-slug}/
├── resume.docx
├── resume.pdf
└── cover-letter.mdRules
- NEVER fabricate achievements — only use data from
master-experience.yaml. - NEVER modify source
.docxtemplates — read-only. - ALWAYS score before selecting — document which achievements were chosen and why.
- Keep to 2 pages maximum.
- Cover letters: 250-400 words with Hook-Alignment-Value-CTA structure.
- Every tailored version must reference a Job Posting record.
- Resume bullet rewriting (Step 5) MUST use a high-quality model — Claude Sonnet 4.6 / Opus 4.6+ or equivalent. Never use a small/fast model for resume content generation.
- Quality gate (Step 6.5) MUST pass before PDF generation.
skills_overrideMUST contain hard tools — see format above.title_override— use when the template-derived title doesn't match the target role. Set in job YAML alongsidesummary_override.role_category— accepts both forms with hyphens or underscores (AI-DT/AI_DT). Both work.
Reframed-Experience Guidance (driven by gap-analysis.yaml)
The user's applications/resumes/data/{user-slug}/gap-analysis.yaml defines reframing rules per role type. The agent reads it and applies the rules during tailoring. The shape of the file:
reframes:
- role_type: "consulting"
description: "Consulting / advisory / transformation roles"
rules:
- "Use 'consulting' title variants for any independent-engagement roles"
- "Frame summary_override with total years of independent consulting"
- "Include engagement_type=consulting achievements prominently"
- role_type: "regional"
description: "Roles based in or focused on the user's target region"
rules:
- "ALWAYS include region-specific achievement bullets"
- "Frame regional tenure prominently in summary_override"
- role_type: "technical_pm"
description: "Technical PM / data / digital transformation roles"
rules:
- "ALWAYS include cloud / data-pipeline achievement bullets"
- "Frame technical depth: SQL, Power Query/DAX, AWS, Docker"
# ... add moreDo not hardcode user-specific reframing rules in this skill. Read them from the user's gap-analysis.yaml.
Template Selection Guide
| Role Type | Template | Emphasis |
| Program Manager | Delivery | PMO, execution, risk management, $-M scale |
| Product Manager | Delivery | Product lifecycle, user journey, backlog |
| AI/ML Lead | Innovation | Startup founder, LLMs, computer vision |
| Innovation Director | Innovation | Design thinking, corporate innovation |
| DT Consultant | Generic | Balanced transformation + technology |
| Operations Director | Delivery | Stakeholder management, team leadership |
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.

