agent-instructions
Use when writing project instructions for a coding agent (CLAUDE.md, AGENTS.md, or equivalent). Covers what belongs in them, what does not, structure, and…
Use when writing or tailoring a CV or resume. Covers evidence over adjectives, tailoring to a specific role without lying, structure, and the specific patterns that get a resume discarded.
$ npx -y skills add nimadorostkar/Claude-Skills-collection --skill resume --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/resumeContext preview
The summary Claude sees to decide when to auto-load this skill.
Use when writing or tailoring a CV or resume. Covers evidence over adjectives, tailoring to a specific role without lying, structure, and the specific patterns that get a resume discarded.
name: resume description: Use when writing or tailoring a CV or resume. Covers evidence over adjectives, tailoring to a specific role without lying, structure, and the specific patterns that get a resume discarded. metadata: category: business version: 1.0.0 tags: [resume, cv, career, tailoring, writing]
Write a resume that survives a six-second scan and a hiring manager's skepticism. Most resumes fail on the same thing: they list responsibilities rather than demonstrating outcomes.
1. **Extract the outcomes** — For each role: what changed because you were there? Not what you were responsible for. What was different afterwards. 2. **Quantify** — Numbers survive a six-second scan; adjectives do not. If a number is not available, use a comparison, a scale, or a before-and-after. 3. **Lead with the strongest evidence** — The top third of the first page is nearly all that is read on the first pass. Put the best thing there. 4. **Tailor to the posting, honestly** — Reorder, re-emphasize, and use the posting's vocabulary where it genuinely describes what you did. Never invent. 5. **Cut everything irrelevant** — A resume is an argument for one role, not a complete autobiography. 6. **Check it survives a keyword scan** — Most applications pass through automated filtering. If the posting says "Kubernetes" and your resume says "container orchestration", you may be filtered out for a skill you have.
**The single most important transformation:**
BEFORE — a job description. Anyone in the role could have written this.
Senior Software Engineer, Acme Corp (2022-2026)
- Responsible for backend services and API development
- Worked with cross-functional teams to deliver features
- Participated in code reviews and mentored junior developers
- Utilized Python, PostgreSQL, and AWS in a microservices architecture
AFTER — evidence. Only this person could have written this.
Senior Software Engineer, Acme Corp (2022-2026)
- Cut checkout p99 latency from 3.2s to 340ms by replacing an N+1 query
pattern in the pricing service. Checkout abandonment fell 4 points.
- Led the migration of 12 services off a shared database, eliminating the
incident class that caused 3 of the year's 6 SEV-1s.
- Built the deploy gate that made integration tests mandatory. Production
incidents caused by deploys fell from ~2/month to 0 over 8 months.
- Mentored 3 engineers; 2 promoted to senior within 18 months.
Python, PostgreSQL, AWS (ECS, RDS, SQS), TerraformSame job. The first version could describe ten thousand people. The second describes one, and every line is checkable.
**Tailoring honestly:**
The posting emphasizes: reliability, incident response, Kubernetes.
The candidate has all three, but their resume leads with feature work, because
that is what they spent the most time on.
Tailor by reordering — not by inventing:
- Move the incident-reduction bullet to the top of the most recent role.
- Move the database migration bullet (which eliminated an incident class)
to second.
- The feature work moves down. It is still true, still there, and no longer
the first thing read.
- The posting says "Kubernetes"; the resume said "container orchestration".
The candidate used Kubernetes. Say "Kubernetes" — an automated filter does
not do synonyms.
Nothing was invented. The same experience is presented in the order that
answers the question the reader is actually asking.A curated library of 137 production-grade skills for Claude and other AI coding agents. Every skill follows one structure, speaks with one voice, and earns its place by changing what the agent does.
Repo: nimadorostkar/Claude-Skills-collection
Use when writing project instructions for a coding agent (CLAUDE.md, AGENTS.md, or equivalent). Covers what belongs in them, what does not, structure, and…
Use when an agent needs state that survives a session or a context compaction. Covers what to persist, file-based memory, structuring notes for retrieval, and…
Use when automating agent behavior with lifecycle hooks. Covers hook events, deterministic enforcement of rules the model should not be trusted to remember,…
Use when packaging skills, commands, hooks, and MCP servers into a distributable plugin. Covers manifest structure, bundling, versioning, testing, and…
Use when writing a new skill for an AI agent. Covers scoping, description writing for reliable triggering, progressive disclosure, and the difference between a…
Use when reviewing or improving an existing agent skill. Covers triggering accuracy, content quality, redundancy with the base model, and measuring whether the…