feat: add cold-email-writer and application-form-filler skills

Two new skills for the outreach and application side of job searching —
areas not covered by the existing resume-focused skills.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
vswaroop04
2026-05-26 23:38:33 +05:30
parent 24c6edc894
commit 7ff14a3e23
2 changed files with 460 additions and 0 deletions
+247
View File
@@ -0,0 +1,247 @@
---
name: application-form-filler
description: Fill out job application form fields with context-aware, tailored answers drawn from the candidate's CV and the job description
---
# Application Form Filler
## When to Use This Skill
Use this skill when the user wants to:
- Answer specific questions on a job application form
- Fill out text fields on Greenhouse, Lever, Ashby, Workday, or any ATS
- Write responses to "tell us about yourself" or "why do you want to work here" prompts
- Get clean, copy-pasteable answers to application questions
- Mentions: "fill this out", "what do I write here", "answer this question", "application form", "form field"
## Core Principle
Application form answers should be direct and specific — not a cover letter crammed into a text box. Each field has a purpose. Answer that purpose clearly, then stop.
**The answer should feel like:** A real person typed it, not a template was filled in.
## Before Answering
Always read:
1. **The job description** — mirror its language and priorities
2. **The candidate's CV/profile** — pull real projects, roles, and metrics
3. **The specific question** — answer exactly what was asked, not what you wish was asked
If the user hasn't provided a CV or JD, ask for them before writing.
## Question Types and How to Handle Each
---
### Type 1: Experience/Background Questions
**Examples:**
- "How many years of experience do you have with [technology]?"
- "Describe your experience with [domain]"
- "What backend frameworks have you used?"
**Format:**
```
[Technology/skill] — [X years]. [One sentence on what you used it for, with a
specific project or context]. [Optional: secondary tools in the same category].
```
**Rules:**
- Lead with the most used/relevant technology
- Give years honestly — don't inflate
- Anchor every claim to a real project or role
- For "describe experience" questions: 2-4 sentences max, one project per sentence
- If experience is indirect (adjacent domain), say so and pivot to what is relevant
---
### Type 2: Why This Company / What Interests You
**Examples:**
- "Why do you want to work at [Company]?"
- "What interests you about this role?"
- "Why are you a good fit?"
**Format:**
```
[Specific thing about the company/role that's genuinely interesting — not generic].
[How that connects to something the candidate has actually worked on].
[Optional: one line on why this domain, not just this company].
```
**Rules:**
- Must be specific to this company — no boilerplate
- Research the company before answering if needed
- Connect to real work, not aspirations
- Keep it under 150 words for a form field
- Don't repeat the JD back to them
---
### Type 3: Portfolio / Work Samples
**Examples:**
- "Include any other samples of work you're proud of"
- "Link to relevant projects or repositories"
- "Describe a project you've built end-to-end"
**Format:**
List projects with one-line descriptions and links. Lead with the most relevant.
```
[Project Name] ([live URL] | [github URL]) — [one line: what it is and one
proof point]. [Stack if relevant].
```
**Rules:**
- Only include projects relevant to the role
- Always include links (live demo > GitHub > nothing)
- If the project has paying users or measurable usage, say so — once
- Don't pad with irrelevant projects to look prolific
---
### Type 4: Technical Skill Questions
**Examples:**
- "Which frontend frameworks have you used most extensively?"
- "Rate your proficiency in Python"
- "Describe your experience with cloud infrastructure"
**Format:**
For open-text fields:
```
[Primary skill] — [X years]. [Specific use: what you built with it, in what context].
[Secondary skill] — [X years]. [Same].
[Note any relevant gaps honestly].
```
For rating/dropdown fields: pick the honest level — don't optimize for the highest rating if it's not accurate.
**Rules:**
- Years + context beats years alone
- Acknowledge gaps rather than hiding them
- If asked to rate, rate honestly — inflated ratings create problems in technical interviews
- For stacks you've used but not recently, note it
---
### Type 5: Open-Ended / "Tell Us About Yourself"
**Examples:**
- "Tell us about yourself"
- "Describe your professional background"
- "What are you looking for in your next role?"
**Format:**
```
Current role + what you do there (1 sentence).
Relevant prior experience, briefly (1 sentence).
What you're looking for / why this role (1-2 sentences — specific to the company).
Optional: one project or side work that's relevant (1 sentence).
```
**Rules:**
- Start with current role, not education
- Keep to 100-200 words for most form fields
- End on the forward-looking note (what you want, not where you've been)
- No trait statements ("I'm passionate about...") — just facts and projects
---
### Type 6: Situational / Behavioral Questions
**Examples:**
- "Describe a time you solved a complex technical problem"
- "Tell us about a project you led end-to-end"
- "How do you handle working across multiple teams?"
**Format:** Condensed STAR (no labels, just flow)
```
[Context in one sentence]. [What you specifically did — 2 sentences]. [Outcome
with a metric if possible — 1 sentence].
```
**Rules:**
- Be specific — name the project, the tech, the team size
- Don't generalize ("I always approach problems by...")
- Keep to 150-250 words
- First-person, active voice throughout
- End with the result, not the lesson learned (save that for interviews)
---
### Type 7: Opinion / Vision Questions
**Examples:**
- "Which technologies do you think are most important for the future?"
- "What would you learn if you had unlimited time?"
- "Where do you see AI/[domain] in 5 years?"
**Format:**
Answer with a genuine opinion. Pick one or two things and explain the reasoning briefly.
**Rules:**
- Have an actual point of view — vague answers are forgettable
- Ground opinions in domain knowledge or real experience
- Keep to 100-150 words
- Don't hedge everything — commit to a view, acknowledge it's one perspective
---
## Output Format
Always wrap the answer in a plain code block so it's clean to copy-paste:
```
[Answer text here]
```
If providing multiple answers (one per field), use separate code blocks with a label above each:
**Years of React experience:**
```
4 years. Used it across Screenr (agentic hiring SaaS), a Tauri-based POS
system, and several client projects. Also used Next.js where SSR was needed.
```
**Describe your backend experience:**
```
...
```
## Length Calibration
| Field type | Target length |
|------------|---------------|
| Single-line text | 1 sentence |
| Short answer | 2-4 sentences |
| Long answer / textarea | 100-250 words |
| "Describe your experience" | 150-300 words |
| "Tell us about yourself" | 100-200 words |
| Portfolio / links section | List format, no prose |
When in doubt, shorter is better. Recruiters skim form answers. The goal is to be clear and memorable, not comprehensive.
## Common Mistakes to Avoid
**Repeating the JD:**
❌ "I am interested in this role because you are looking for someone to build scalable backend systems..."
✅ "What caught my attention was the real-time constraint — healthcare data at milliseconds latency is a different class of problem than most backend work."
**Generic trait claims:**
❌ "I am a fast learner who thrives in collaborative environments"
✅ [Just describe the actual work — the traits come through]
**Over-qualifying:**
❌ "While I may not have exactly 5 years, I believe my experience..."
✅ "The role mentions 5 years — I'm at 3, but the systems I've shipped are production-facing."
**Listing without context:**
❌ "React, Vue, Angular, Next.js, TypeScript, Node.js..."
✅ "React is my primary frontend framework — 4 years across Screenr and several client projects. Vue and Angular for about 3 years each, mostly dashboards and admin tooling."
**Padding to fill space:**
❌ Adding projects or experience that aren't relevant just to look prolific
✅ Include only what's relevant to this specific role
+213
View File
@@ -0,0 +1,213 @@
---
name: cold-email-writer
description: Write personalized cold outreach emails to hiring managers and founders — specific, human, not a pitch deck
---
# Cold Email Writer
## When to Use This Skill
Use this skill when the user wants to:
- Write a cold outreach email to a hiring manager, founder, or recruiter
- Reach out about a job opening they weren't referred to
- Introduce themselves to a company they want to work at
- Mentions: "cold email", "reach out", "intro email", "outreach", "contact hiring manager"
## Core Principle
Cold emails fail because they sound like cover letters. The goal is to sound like a smart person who genuinely noticed something specific about the company — not a candidate broadcasting their credentials.
**The email should feel like:** A colleague mentioning something interesting they read, not a sales pitch.
## The Template Structure
### Subject
```
Quick intro — [First Name Last Name]
```
Simple. No clickbait. No role title. Just a name.
### Opening — The Hook (2-3 sentences)
Start with what genuinely pulled the candidate in. Must be specific to this company — not a generic compliment.
```
I just came across [Company] and ended up spending more time on it than I expected.
[One specific thing that caught their attention — a stat, a product decision, a market insight from the JD or website]
```
**What makes a good hook:**
- A specific number or stat from the company's materials ("only 5% of the market is online")
- A product decision that shows you understand the domain ("you're building from scratch alongside underwriters, not just distribution")
- A technical insight from the JD ("improving the data infrastructure for LLM usage, not just the model layer")
**What makes a bad hook:**
- Generic: "I love what you're building"
- Vague: "Your mission resonates with me"
- Flattering: "You're one of the most exciting companies in the space"
### Location Disclosure (if international)
If the candidate is in a different country from the company, disclose it early and casually:
```
Before you read further, I should mention I'm based in [country]. But if we both
feel there's a strong fit, I'd be open to figuring things out.
```
### Experience Gap (if applicable)
If the role lists more years than the candidate has, acknowledge it briefly and redirect:
```
The role mentions [X] years of experience — I'm at [Y], but the work I've
shipped is production-facing and I'd rather you judge that directly.
```
### The Body — Who They Are (3-5 sentences)
Current role → relevant past → one or two projects. Keep it contextual, not a list.
```
A bit about me: I currently work at [Company], [one line on what the company does],
where I [what they actually do there — not a job title]. Before that I worked
with teams in [region], mostly around [relevant domain].
On the side I've been building [Project] ([link if applicable]) — [one line: what
it is and one proof point like "got to paying clients" or "20K downloads"].
```
**Rules:**
- Mention work as context, not as proof of greatness
- No achievement listings ("I increased X by Y%") — let the project speak
- If current company is remote with a European/international team, say so explicitly
- Keep project mentions to one or two max — the most relevant ones only
### The Connection (1-2 sentences)
Bridge between their background and the specific role. Should feel like an observation, not a claim.
```
I think you're looking for [what the role actually wants] — that's the kind of
work I've been doing, and honestly I feel like I'd be a strong fit.
```
Or more specific:
```
My stack maps naturally to yours — [specific tech overlap]. But more than the
stack, it's the [domain/problem] that I'm genuinely interested in.
```
### Portfolio Link
```
More about me: [portfolio URL]
```
One line. No elaboration.
### Closing
End with low-pressure, confident energy. Not desperate, not corporate.
```
I'm currently at [Company] and open to what's next. I think my experience lends
nicely to what you're building — so I think we'd both get something out of a
conversation.
[First Name]
[email]
```
**Avoid:**
- "I look forward to hearing from you"
- "Please find attached my resume"
- "I would love the opportunity to..."
- "I am excited to potentially join..."
## Research Before Writing
Before writing the email, gather:
1. **Company angle** — read their website, JD, or About page. Find one specific thing worth mentioning.
2. **Recipient name** — LinkedIn, team page, or AngelList. "Hi [Name]" beats "Hi Hiring Manager" every time.
3. **Relevant projects** — match the candidate's most relevant work to the role domain.
4. **Stack overlap** — mention it only if there's a genuine match.
If the user provides a JD but no company website, ask for it or fetch it before writing.
## Length Guidelines
- **Ideal:** 200300 words
- **Maximum:** 400 words
- **Minimum:** 150 words (don't strip out substance for brevity)
Longer is fine if every sentence earns its place. Cut anything that could apply to any company.
## Output Format
Always wrap the final email in a plain code block for clean copy-paste:
```
Subject: Quick intro — [Name]
Hi [Name],
[Email body]
[First Name]
[email]
```
## Common Mistakes to Avoid
**Too confident:**
❌ "I would be an exceptional addition to your team"
❌ "My background uniquely positions me for this role"
✅ "I feel like I'd be a strong fit" — states a belief, doesn't claim certainty
**Too humble:**
❌ "I know I may not have all the experience you're looking for, but..."
❌ "I'm just reaching out on the off chance..."
✅ Acknowledge gaps directly and move on — don't apologize
**Too long:**
❌ Three paragraphs listing every achievement
✅ One paragraph on background, one on the connection
**Too generic:**
❌ Opening with "I am writing to express my interest in..."
✅ Opening with what specifically pulled them to this company
**No research:**
❌ "I love your product and mission"
✅ "The 5% stat — only 5% of a $25B market online — doesn't feel like a feature gap, it feels like an entire industry that hasn't digitised"
## Example Email
```
Subject: Quick intro — Sarah Chen
Hi Marcus,
I just came across Meridian and spent more time on your site than I planned.
What pulled me in was the framing around your data infrastructure — you're not
just building an LLM layer on top of existing records, you're rethinking how
clinical data flows through the system in the first place. That's a harder
problem and a more interesting one.
I'm based in India, flagging that upfront. Happy to figure out the rest if
there's a real fit.
I currently work at Lune, a London-based climate intelligence company, where I
build event-driven data pipelines and agentic AI workflows for emissions
compliance — regulated, data-intensive systems where reliability isn't optional.
I also built Memos, a RAG system from scratch: hybrid retrieval, reranking,
ChromaDB, FastAPI. And InframetAI, an SDK for LLM cost and latency
observability that came out of seeing what breaks when the data layer isn't
designed around how models actually work.
I think you're looking for engineers who've actually built AI systems end to
end, not just wrapped APIs. That's the work I've been doing.
More about me: yourportfolio.com/about
I'm currently at Lune and open to what's next. I think my experience maps
closely to what you're building — so I think we'd both get something out of
a conversation.
Sarah
sarah@email.com
```