cal/claude-plugins
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
c9ad101b85
claude-plugins/plugins/resume-tailoring/skills/tailor/EDGE_CASES.md
Cal Corum e02eb28e98 refactor: rename skill dirs to verb-based names to reduce autocomplete redundancy 
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>
2026-03-19 13:57:19 -05:00

2.0 KiB
Raw Blame History

Resume Tailoring - Error Handling & Edge Cases

Insufficient Resume Library

Scenario: User has only 1-2 resumes, limited content. Handling: Warn about limited matching options, recommend Experience Discovery, proceed with available content.

No Good Matches (confidence <60% for critical requirement)

Scenario: Template slot requires experience user doesn't have. Options:

  1. Run Experience Discovery to surface undocumented work
  2. Reframe best available (show reframing with truthfulness justification)
  3. Omit bullet slot (reduce template allocation)
  4. Note for cover letter (emphasize learning ability)

Don't force matches - be transparent about gaps.

Research Phase Failures

Scenario: WebSearch fails, LinkedIn unavailable, company info sparse. Handling: Fall back to JD-only analysis. Ask user for additional context about company culture, team structure, technologies. Proceed with best-effort approach.

Job Description Quality Issues

Scenario: Vague JD, missing requirements, poorly written. Handling: Identify missing areas, ask user for clarification, extract what's possible and proceed.

Ambiguous Role Consolidation

Scenario: Unclear whether to merge roles or keep separate. Handling: Present both options with rationales. Remember user preference for future.

Resume Length Constraints

Scenario: Too much good content, exceeds target page count. Handling: Show pruning suggestions ranked by relevance score. User decides priority.

Error Recovery

  • All checkpoints allow going back to previous phase
  • User can request adjustments at any checkpoint
  • Generation failures (DOCX/PDF) fall back to markdown-only
  • Progress saved between phases (can resume if interrupted)

Graceful Degradation

  • Research limited → Fall back to JD-only analysis
  • Library small → Work with available + emphasize discovery
  • Matches weak → Transparent gap identification
  • Generation fails → Provide markdown + error details