splash0047/resume-generator / skills/engineering-evidence-database
Engineering Evidence Database
VerifiedStructured evidence schema for capturing project and experience context before generating resume bullets. Separates implementation, execution, ownership, and impact evidence.
Engineering Evidence Database
Purpose
Build the factual source of truth used by resume generation and interview preparation.
The evidence database must preserve what is known, what is measured, and what is still unverified. Do not collapse evidence into a single numeric confidence score.
Evidence Record
For each project or experience capture:
Identity
- name
- dates
- role
- repository/demo/document links
- candidate ownership/contribution
Problem
- user/system problem
- constraints
- why the work mattered
Implementation
- languages/frameworks
- architecture
- algorithms
- databases
- APIs
- security/reliability features
- deployment/containerization
Execution Evidence
Classify each material feature:
- Source-verified
- Test/CI-verified
- Demo-visible
- README-only
- Candidate-confirmed
- Unverified
Ownership Evidence
- documented contribution;
- candidate-confirmed personal contribution;
- team contribution with scope;
- unknown.
Do not assume repository ownership means the candidate personally implemented every component.
Impact Evidence
Classify:
- Production/operational measurement
- Research/evaluation result
- Development benchmark
- Repository-visible scale/count
- Descriptive only
- Unverified
For every number store:
- value;
- metric definition;
- source;
- environment;
- sample/evaluation scope;
- date/version;
- whether reproducible.
Decisions and Trade-offs
Capture only decisions the candidate can explain:
- alternatives considered;
- chosen approach;
- reason;
- consequences.
Failures and Debugging
Record:
- issue;
- diagnosis;
- fix;
- validation.
Interview Defense
For each resume-worthy claim, prepare:
- What did you personally implement?
- How does it work?
- Why this approach?
- How did you test it?
- What limitation remains?
Resume Claim Matrix
| Proposed claim | Implementation | Execution | Ownership | Impact | Source | Use? |
|---|---|---|---|---|---|---|
| Containerized backend with Docker | Direct | Build/test evidence if present | Confirmed | Descriptive | Dockerfile | Yes |
| Reduced latency 40% | Direct | Benchmark required | Confirmed | Unverified | none | No until measured |
Rules
- An import proves the dependency is referenced; it does not prove successful end-to-end use.
- A README claim is documentation evidence, not execution evidence.
- A deployment link proves public accessibility only if it works; it does not prove production readiness.
- Metrics without provenance must not appear in final resume bullets.
- Development/research measurements must keep their environment/evaluation qualifier.
- If ownership is unclear, confirm it before using first-person resume wording.
- Repository changes can invalidate old resume descriptions; re-audit when architecture changes.
Output
Produce:
- verified technology list;
- claim matrix;
- metric provenance table;
- unresolved evidence questions;
- interview-defense questions;
- bullets safe to generate;
- claims that must be removed or confirmed.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| deprecation-and-migrationaddyosmani/agent-skillsManages deprecation and migration. Use when removing old systems, APIs, or features. Use when migrating users from one implementation to another. Use when migrating a database schema in production, such as renaming or dropping a column without downtime (expand/contract). Use when deciding whether to maintain or sunset existing code. | Stars: 119k | Updated | Claude CodeCodex | Verified | Install |
| performance-optimizationaddyosmani/agent-skillsOptimizes application performance across frontend, backend, queries, and databases. Use when performance requirements exist, when you suspect performance regressions, when Core Web Vitals or load times need improvement, when N+1 query patterns need fixing, or when profiling reveals bottlenecks. | Stars: 119k | Updated | Claude CodeCodex | Verified | Install |
| Agent Cost Reportthedotmack/claude-memBelievable agent cost report for any period, default the last 7 full days PT, not counting today. Measured tokens from Claude Code transcripts priced at OpenRouter list prices (ESTIMATED), measured provider spend when a sanctioned source exists, note-taker cost separate, Timing-style HTML/PDF plus report.json, line-items.csv, evidence.json. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |
| Agent Cost Reportthedotmack/claude-memBelievable agent cost report for any period, default the last 7 full days PT, not counting today. Measured tokens from Claude Code transcripts priced at OpenRouter list prices (ESTIMATED), measured provider spend when a sanctioned source exists, note-taker cost separate, Timing-style HTML/PDF plus report.json, line-items.csv, evidence.json. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |