portfolio-readiness
Skill1 starsChanged 3 months agoMITView on GitHub
Comprehensive project readiness audit across 6 engineering pillars and 10 presentation dimensions for portfolio, resume, LinkedIn, and technical interviews.
- Reads credentials
In this repository30 other files it gives its agents.
- AGENTS.mdAGENTS.md
- adr-managementSkill
- agentic-developmentSkill
- ci-cdSkill
- code-architectureSkill
- database-postgresqlSkill
- data-engineeringSkill
- debuggingSkill
- deep-learningSkill
- dependency-managementSkill
- deploymentSkill
- dockerSkill
- documentation-orchestratorSkill
- documentationSkill
- environment-guardrailsSkill
- frontend-react-typescriptSkill
- git-githubSkill
- machine-learningSkill
- observabilitySkill
- performance-optimizationSkill
- project-bootstrapSkill
- project-knowledgeSkill
- python-apiSkill
- python-environmentSkill
- rag-ocr-llmSkill
- release-engineeringSkill
- reusable-componentsSkill
- security-secretsSkill
- supply-chain-securitySkill
- testing-qualitySkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 10
Use this skill when:
- Distinctive: line 16
Never fabricate metrics, benchmarks, or user statistics.
- Distinctive: line 24
Repository Cleanliness: Ensure zero untracked scratch files, no leaked API keys, and clean main branch Git history.
- Distinctive: line 115
NEVER invent fake benchmark numbers: If you did not benchmark latency, run a benchmark before quoting a number.
- Distinctive: line 117
NEVER leave broken live demo links: Ensure cloud free tiers have not expired or spun down into permanent error states.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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
Portfolio Readiness Skill
1. When Should I Use This?
Use this skill when:
- Polishing and auditing a completed project for inclusion in your professional engineering portfolio.
- Generating resume bullet points, LinkedIn project summaries, or technical interview talking points.
- Validating that an open-source repository meets enterprise visual and engineering showcase standards.
- Auditing an existing project against the 6 Engineering Pillars and 10 Presentation Dimensions.
Never fabricate metrics, benchmarks, or user statistics.
2. What Should I Inspect First?
- Working State & Live Demos: Is there a live working URL (Vercel, Render, Streamlit Cloud)?
- Visual Assets: Are there high-resolution screenshots, architecture diagrams, or demo recordings in
docs/assets/orimages/? - Repository Cleanliness: Ensure zero untracked scratch files, no leaked API keys, and clean
mainbranch Git history.
3. What Workflow Should I Follow?
Audit 6 Engineering Pillars (Tests, Architecture, Security, Deploy, Observe, Docs)
↓
Audit 10 Presentation Dimensions (Hero, Diagram, Screenshots, Demos, Metrics)
↓
Generate Concise Resume Bullet Points (Action Verb + Tech + Quantified Result)
↓
Generate LinkedIn Project Narrative & Technical Highlights
↓
Prepare 2-Minute Interview Elevator Pitch & Deep-Dive Talking Points
↓
Verify Zero Fabricated Claims & Verify All External LinksThe 6 Engineering Pillars Audit
┌───────────────────────────┬───────────────────────────────────────────────────────────┐
│ Engineering Pillar │ Minimum Readiness Criteria │
├───────────────────────────┼───────────────────────────────────────────────────────────┤
│ 1. Tests & Quality │ • Automated test suite (Pytest/Vitest) with >= 80% pass │
│ │ • Static typing (mypy/tsc) and linting (Ruff/ESLint) clean │
├───────────────────────────┼───────────────────────────────────────────────────────────┤
│ 2. Code Architecture │ • Layered separation (API, Service, Repository, Models) │
│ │ • Clean dependency injection without god-files │
├───────────────────────────┼───────────────────────────────────────────────────────────┤
│ 3. Security & Hygiene │ • Clean secret scan (zero leaked credentials) │
│ │ • Pydantic SecretStr & sanitized .env.example │
├───────────────────────────┼───────────────────────────────────────────────────────────┤
│ 4. Deployment & DevOps │ • Multi-stage Dockerfile or Live Cloud URL (Render/Vercel)│
│ │ • Passing CI pipeline (.github/workflows/ci.yml) │
├───────────────────────────┼───────────────────────────────────────────────────────────┤
│ 5. Observability │ • Structured JSON logging with Request IDs │
│ │ • Health check probe (/health) returning 200 OK │
├───────────────────────────┼───────────────────────────────────────────────────────────┤
│ 6. Documentation │ • Synchronized README, ARCHITECTURE.md, and ADRs │
└───────────────────────────┴───────────────────────────────────────────────────────────┘The 10 Presentation Dimensions Checklist
- README Hero Section: Clear title, 1-sentence value proposition, status badges, tech stack badges.
- Architecture Diagram: High-resolution ASCII or Mermaid diagram showing data flow.
- Visual Screenshots: Clean, captioned UI screenshots demonstrating core user workflows.
- Live Demo Link: Working public URL (Streamlit / Vercel / Render).
- Demo Video / GIF: 30-90 second walkthrough video or animated GIF.
- Quantified Performance Metrics: Real measured metrics (e.g. "sub-50ms OCR retrieval", "0.0% patient leakage").
- Key Technical Highlights: Bulleted list of the 3 most complex engineering problems solved.
- Resume Bullets: 2-3 impact-driven bullets in Google XYZ format (
Accomplished [X] as measured by [Y] by doing [Z]). - LinkedIn Project Post: Engaging announcement with architecture image and key takeaways.
- Technical Interview Explanation: 2-minute elevator pitch + trade-off defense.
Resume Bullet & Interview Artifact Generator
### 📄 Resume Bullets (Google XYZ Format)
* Architected a distributed RAG & OCR document analysis system using **FastAPI**, **PaddleOCR**, and **FAISS**, enabling sub-50ms semantic search over complex PDFs with zero external cloud API costs.
* Designed an end-to-end time-series energy demand forecasting platform with **XGBoost** and **Streamlit**, resolving Daylight Saving Time timestamp anomalies and beating 24h persistence baselines by 38% MAE.
* Implemented a patient-stratified deep learning pipeline in **TensorFlow 2.16** fine-tuning **DenseNet121** with protected BatchNorm layers, achieving 94.2% ROC-AUC on RSNA chest X-rays with 0% patient leakage.
---
### 🎙️ 2-Minute Technical Interview Pitch
"In this project, I set out to solve [Problem X]. Rather than relying on fragile single-script workflows, I designed a production-grade layered architecture separating [API layer, business services, and storage].
One of the most interesting technical challenges was [Challenge Y, e.g. handling Daylight Saving Time duplicate timestamps / multi-modal OCR bounding boxes]. I evaluated alternatives [Option A vs Option B] in an ADR, ultimately choosing [Option B] because [Rationale Z].
I verified the solution with [N tests], deployed it via [Docker/Render/Vercel], and added structured observability with correlation IDs."4. What Decisions Should I Make?
| Showcase Audience | Priority Focus |
| Recruiters / Hiring Managers | Live URL, clean UI screenshots, quantified resume bullets, concise 1-sentence summary. |
| Senior Engineers / Staff Architects | Layered code architecture, ADR trade-offs, testing pyramid, Docker builds, OpenTelemetry. |
5. What Should I Avoid?
- NEVER invent fake benchmark numbers: If you did not benchmark latency, run a benchmark before quoting a number.
- NEVER use low-resolution blurry screenshots: Capture crisp, high-DPI screenshots with clean mock data.
- NEVER leave broken live demo links: Ensure cloud free tiers have not expired or spun down into permanent error states.
6. How Should I Verify Success?
# 1. Audit all links in README.md
python -c "
import urllib.request, re
readme = open('README.md', encoding='utf-8').read()
urls = re.findall(r'https?://[^\s\)\"]+', readme)
print(f'Auditing {len(urls)} external links...')
for u in set(urls):
try:
req = urllib.request.Request(u, headers={'User-Agent': 'Mozilla/5.0'})
code = urllib.request.urlopen(req, timeout=5).getcode()
print(f'[OK {code}] {u}')
except Exception as e:
print(f'[FAILED] {u}: {e}')
"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.

