technical-job-search
Use this skill when a software engineer asks for help with job search tasks: parsing or analyzing a job description, tailoring a CV/resume, writing a cover letter, evaluating a job offer, or drafting a post-interview follow-up email. Do not activate for general career advice unrelated to an active job search action.
- License 许可
- MIT
- 最近更新
- 2026-08-25
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- technical-job-search
- license
- MIT
- description
- Use this skill when a software engineer asks for help with job search tasks: parsing or analyzing a job description, tailoring a CV/resume, writing a cover letter, evaluating a job offer, or drafting a post-interview follow-up email. Do not activate for general career advice unrelated to an active job search action.
- argument-hint
- Optional: the specific task — e.g. "analyze this JD", "tailor my CV", "write cover letter", "evaluate this offer"
03 SKILL.md 正文
Technical Job Search
Helps software engineers with discrete job search tasks: job description analysis, CV tailoring, cover letter writing, offer evaluation, and follow-up emails.
Job Description Analysis
When given a job description, extract and structure:
Must-haves (explicitly required or repeated multiple times):
- Technical skills, years of experience, specific domain knowledge
Nice-to-haves (preferred, a bonus, or mentioned once):
- List these separately. Candidates often disqualify themselves over requirements that are actually optional.
What the role actually solves (inferred from the description):
- Summarize in 2-3 sentences what business problem this hire addresses
Red flags to surface:
- "Wear many hats" with no clarity on scope — risk of undefined ownership
- 10+ must-have technologies for a single role — unrealistic bar or poor team planning
- No mention of team size, tech stack, or what the role ships — may indicate disorganization
CV / Resume Tailoring
When tailoring a CV to a specific job description:
- Match language exactly — use the same terminology as the JD, not synonyms. If the JD says "distributed systems", do not write "large-scale systems".
- Lead with impact — every bullet should have a result: "Reduced P99 latency by 40%" not "Worked on performance improvements".
- Quantify everything possible — users, QPS, team size, cost saved, revenue impact.
- Cut what does not match — a two-page CV tailored to the role beats a four-page generic one.
- Mirror the seniority signals — entry roles want "built", senior roles want "designed", staff and principal roles want "drove" or "defined".
Do not keyword-stuff. Write for the hiring manager reading it, not for an ATS parser.
Cover Letter Writing
A cover letter should answer three questions in under 300 words:
- Why this company? Something specific — a product, a technical challenge they have written about, a problem space you care about. Not "I admire your mission."
- Why you? One or two concrete things from your background that directly match what they need. Link to the specific role, not your full career history.
- Why now? What is your motivation at this point in your career? One sentence.
Format: three short paragraphs. No preamble ("I am writing to apply for..."). No summary of your CV.
Avoid:
- Restating your CV in prose form
- "I am passionate about..."
- Generic company praise ("a leader in the industry", "innovative company")
- Going longer than one page
Offer Evaluation
When evaluating a job offer, compare across these dimensions:
Compensation
- Base salary: check against market rate for role, level, and location (levels.fyi, Glassdoor, Blind, Comprehensive.io)
- Equity: current valuation, vesting schedule (4-year with 1-year cliff is standard), dilution risk for early-stage companies
- Bonus: target percentage vs actual historical payout
- Total comp = base + expected bonus + annualized equity value
Role clarity
- Scope: what does "owning" this role actually mean vs what is already decided?
- Team: size, structure, who you report to, tenure of the team
- Growth: what does the next level look like and how long do people typically take to get there?
Company health
- Stage: runway, revenue, growth rate — ask directly if not public
- Engineering culture signals: PR review process, incident postmortem culture, on-call burden
- Remote or hybrid reality: written policy vs actual practice
Red flags in an offer
- Pressure to decide in under 48 hours — a reasonable window is one to two weeks
- Equity with no clear liquidity path for a company that has been private for 10+ years
- A role described as greenfield that turns out to have 6 months of existing unmaintained code
Get everything in writing before accepting.
Follow-up Emails
After an interview, send a follow-up within 24 hours:
- One sentence thanking them for the time
- One sentence referencing something specific from the conversation (a problem discussed, a question they asked)
- One sentence reaffirming interest, if genuine
Do not write multiple paragraphs. Do not restate your qualifications. Do not follow up more than once if there is no reply.
04 同仓库更多 Skills
webmcpify
Make a web app agent-ready — propose a WebMCP tool manifest, integrate, verify in a real browser, heal; unrelated code stays untouched. Use for "webmcpify", "add WebMCP", or "expose app actions to AI agents".
vardoger-analyze
Use when the user asks to personalize the GitHub Copilot CLI assistant, adapt Copilot to their style, use vardoger, or analyze their Copilot CLI conversation history. Reads the local session directory at `~/.copilot/session-state/`, extracts recurring preferences and conventions, and writes a fenced personalization block into `~/.copilot/copilot-instructions.md`. Runs entirely on the user's machine via the local `vardoger` CLI (`pipx install vardoger`); no network calls and no uploads. Triggers: 'personalize my copilot', 'analyze my copilot history', 'tailor copilot to me', 'run vardoger', 'update my copilot instructions from history', 'make copilot learn my style'.
transloadit-media-processing
Process media files (video, audio, images, documents) using Transloadit. Use when asked to encode video to HLS/MP4, generate thumbnails, resize or watermark images, extract audio, concatenate clips, add subtitles, OCR documents, or run any media processing pipeline. Covers 86+ processing robots for file transformation at scale.
terraform-azurerm-set-diff-analyzer
Analyze Terraform plan JSON output for AzureRM Provider to distinguish between false-positive diffs (order-only changes in Set-type attributes) and actual resource changes. Use when reviewing terraform plan output for Azure resources like Application Gateway, Load Balancer, Firewall, Front Door, NSG, and other resources with Set-type attributes that cause spurious diffs due to internal ordering changes.
steno-mode
Shorthand-first response compression that cuts ~40% of response tokens while preserving technical precision and exact literals. Use when the user says "steno mode", "shorthand mode", "compressed responses", "token reduction", "brief structured output", or invokes /steno. Supports four compression levels: lite, brief, court, machine. Do not trigger for requests needing polished prose such as onboarding/tutorial content, stakeholder or customer-facing copy, or teaching-focused explanations.
shopify-review-triage
Use this skill when someone wants public Shopify App Store reviews, low-star reviews, or merchant feedback triaged, prioritized, clustered, or turned into a product or support brief. Trigger for prompts like "triage these app store reviews", "what should we fix first from this feedback", "cluster our 1-star reviews", or "write a weekly low-star review brief", for a single Shopify app or a portfolio plus watched competitors. Produces a P0-P3 brief covering incident risk, repeated friction, pricing confusion, feature requests, and an explicit needs-human-read bucket, where every item keeps its public source link and stays labeled first pass or human-checked. Do not trigger for support tickets, order data, or any other private merchant data, and never use it to reply to or contact a reviewer.