e02eb28e98
Plugin:skill pairs now read as noun:verb commands instead of repeating the plugin name. Also added concise descriptions to all SKILL.md frontmatter. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
83 lines
3.2 KiB
Markdown
83 lines
3.2 KiB
Markdown
---
|
|
name: tailor
|
|
description: Research company/role and generate tailored multi-format resumes
|
|
---
|
|
|
|
# Resume Tailoring Skill
|
|
|
|
## Overview
|
|
|
|
Generates high-quality, tailored resumes optimized for specific job descriptions while maintaining factual integrity. Builds resumes around the holistic person by surfacing undocumented experiences through conversational discovery.
|
|
|
|
**Core Principle:** Truth-preserving optimization - maximize fit while maintaining factual integrity. Never fabricate experience, but intelligently reframe and emphasize relevant aspects.
|
|
|
|
**Mission:** A person's ability to get a job should be based on their experiences and capabilities, not on their resume writing skills.
|
|
|
|
## When to Use
|
|
|
|
- User provides a job description and wants a tailored resume
|
|
- User has multiple existing resumes in markdown format
|
|
- User wants to optimize their application for a specific role/company
|
|
- User needs help surfacing and articulating undocumented experiences
|
|
|
|
**DO NOT use for:** Generic resume writing from scratch, cover letters, LinkedIn profiles.
|
|
|
|
## Quick Start
|
|
|
|
**Required from user:**
|
|
1. Job description (text or URL)
|
|
2. Resume library location (defaults to `resumes/` in current directory)
|
|
|
|
**Workflow:**
|
|
1. Build library from existing resumes
|
|
2. Research company/role
|
|
3. Create template (with user checkpoint)
|
|
4. Optional: Branching experience discovery
|
|
5. Match content with confidence scoring
|
|
6. Generate MD + DOCX + PDF + Report
|
|
7. User review → Optional library update
|
|
|
|
## Multi-Job Detection
|
|
|
|
When user provides multiple JDs, URLs, or mentions "multiple jobs" / "batch" / "several positions", offer multi-job mode for shared experience discovery and batch processing.
|
|
|
|
See `multi-job-workflow.md` for complete multi-job implementation.
|
|
|
|
## Workflow Phases
|
|
|
|
| Phase | Description | Details |
|
|
|-------|-------------|---------|
|
|
| Phase 0 | Library Initialization | `PHASES.md#phase-0` |
|
|
| Phase 1 | Research (company + role benchmarking) | `PHASES.md#phase-1` |
|
|
| Phase 2 | Template Generation | `PHASES.md#phase-2` |
|
|
| Phase 2.5 | Experience Discovery (optional) | `PHASES.md#phase-25` |
|
|
| Phase 3 | Assembly (matching + scoring) | `PHASES.md#phase-3` |
|
|
| Phase 4 | Generation (MD + DOCX + PDF + Report) | `PHASES.md#phase-4` |
|
|
| Phase 5 | Library Update (conditional) | `PHASES.md#phase-5` |
|
|
|
|
## Supporting Files
|
|
|
|
| File | Purpose |
|
|
|------|---------|
|
|
| `PHASES.md` | Detailed workflow for all phases |
|
|
| `EDGE_CASES.md` | Error handling and graceful degradation |
|
|
| `EXAMPLES.md` | Usage examples (internal role, career transition, gaps, batch) |
|
|
| `TESTING.md` | Manual testing checklist |
|
|
| `research-prompts.md` | Structured prompts for company/role research |
|
|
| `matching-strategies.md` | Content matching algorithms and scoring |
|
|
| `branching-questions.md` | Experience discovery conversation patterns |
|
|
| `multi-job-workflow.md` | Complete multi-job batch workflow |
|
|
|
|
## Key Constraints
|
|
|
|
- NEVER fabricate experience — reframe truthfully
|
|
- NEVER inflate seniority beyond defensible
|
|
- Company names and dates MUST be exact
|
|
- All checkpoints require user approval before proceeding
|
|
- Generation failures fall back to markdown-only
|
|
|
|
---
|
|
|
|
**Updated**: 2026-03-05
|
|
**Version**: 3.0.0 (modularized)
|