write-application
Skill2 starsChanged 8 months agoMITView on GitHub
This skill should be used when the user asks to "write a cover letter", "draft outreach", "LinkedIn message", "referral ask", "write my essay", "answer this application question", or "help me apply to [company]". Produces all written application materials in one flow.
In this repository13 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- coffee-chatSkill
- company-researchSkill
- discoverSkill
- fit-analysisSkill
- follow-upSkill
- interview-debriefSkill
- interview-prepSkill
- mock-interviewSkill
- negotiateSkill
- offer-analysisSkill
- personalizeSkill
- pipeline-statusSkill
The file
We split this skill into the rules it gives an agent
7 rules. About 0 are common, 4 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 27
If available: output/[company]/fit-analysis.md — what to emphasize
- Distinctive: line 96
No JD provided: Ask for it — "Paste the JD or tell me the company and role."
- Very specific: line 97
No writing framework set up: Use defaults (direct, confident, evidence-based) and note: "Run /personalize framework to set up your voice …
- Very specific: line 98
No knowledge base at all: Stop and say: "Run /personalize first — I need your profile and stories to write compelling materials."
- Distinctive: line 110
Never use: "I am writing to express my interest"
- Distinctive: line 111
Never use: "I am passionate about"
- Very specific: line 113
Never fabricate stories or metrics — reference specific stories from knowledge/stories/
≈ “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
/write-application
Usage
/write-application <paste JD or company name>
/write-application <essay prompt with word limit>Inputs
- Job description (provided by user)
- knowledge/profile.md — candidate context
- knowledge/frameworks/writing-framework.md — apply to every paragraph
- knowledge/voice/samples.md — match this tone
- If available: output/[company]/fit-analysis.md — what to emphasize
- For essays: the question(s) and word limits
Produce
1. Cover Letter (~250-300 words, 3 paragraphs max)
- Para 1: Hook — specific to THIS company. Reference something real. No generic openers.
- Para 2: Evidence — specific achievements that map to the role's biggest needs. Use numbers.
- Para 3: Forward — what you'll bring, confident close.
2. LinkedIn DM
- Connection note (max 300 characters)
- Follow-up message (concise, ~150 words)
- Hook with something specific about their work. Clear ask, easy to respond to.
3. Referral Ask Message (if mutual connection exists)
Warm, specific, not transactional. Give them everything they need to refer in 2 sentences.
4. Email Subject Lines
3 options, ranked by open-rate likelihood.
5. Application Essays (if essay questions provided)
For each essay question:
- Draft — within word limit, ready to submit
- Word count — confirm it's within limits (aim for 90-100% of limit)
- Key choices — why you emphasized what you did
- Alternative angle — a different approach if user wants options
Output Format
## Cover Letter
[Full cover letter text — ready to copy/paste]
---
## LinkedIn
**Connection note (≤300 chars):**
[text]
**Follow-up message:**
[text]
---
## Referral Ask
[text — or "No mutual connection identified"]
---
## Email Subject Lines
1. [option — why it works]
2. [option]
3. [option]
---
## Essay: "[Question]" (word limit: X)
**Word count:** X/Y
[Full essay text]
**Why this angle:** [brief explanation]
**Alternative angle:** [one-sentence alternative if they want a different approach]If Something Goes Wrong
- No JD provided: Ask for it — "Paste the JD or tell me the company and role."
- No writing framework set up: Use defaults (direct, confident, evidence-based) and note: "Run
/personalize frameworkto set up your voice for better results." - No knowledge base at all: Stop and say: "Run
/personalizefirst — I need your profile and stories to write compelling materials." - Essay exceeds word limit: Cut ruthlessly. Every sentence must earn its place.
After Output
- "Want to adjust the tone? Tell me what to change"
- "Have essay prompts? Paste them and I'll draft responses"
- "Ready to track this?
/pipeline-status add [company] [role]" - "Need interview prep?
/interview-prep"
Rules
- Apply writing framework to every paragraph — no exceptions
- Match candidate's voice from samples
- Never use: "I am writing to express my interest"
- Never use: "I am passionate about"
- Tone: confident, specific, human — not corporate, not desperate
- Never fabricate stories or metrics — reference specific stories from knowledge/stories/
- "Why company" must reference something only TRUE of that company
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.

