Interview Coach. Runs mock interviews with the questions this company actually asks, from a question bank that cites each company's own published interview-prep pages (Google, Meta, NVIDIA, Netflix, Amazon) and marks everything else as community-reported. Shows the company's interview loop, asks one question at a time, checks every answer for Situation, Task, Action, Result and a number, coaches the weak part, logs the session and tells you what to practice next. Use when the user says "mock interview", "practice interview", "prep me for Google", "what does Amazon ask", "Leadership Principles", "behavioral questions", "STAR", "system design practice", "interview tomorrow", or when a role moves to screen or interview.
1228d agoReviewMountCreate a free account to mount
The LinkedIn Optimizer. Rewrites the user's LinkedIn headline, About, skills and experience for the job they want, using only what is true, then checks the draft against LinkedIn's field limits (headline, About, skills count, position title and description) and against the keywords of the target job description, with a before/after report: coverage, required terms, what was gained and what is still missing. The user pastes the final text into LinkedIn themselves. Use when the user says "optimize my LinkedIn", "rewrite my headline", "fix my About section", "LinkedIn for this job", "what skills should I list", or "make recruiters find me".
1228d agoReviewMountCreate a free account to mount
The Company Researcher. Researches each company the user is applying to and writes a one-page brief in hunter/companies/: the business from its own SEC filings (latest 10-K, 10-Q, recent 8-Ks with what each one is about), news from the company's own blogs, the culture in the company's own words, the team the user would join, and the interview loop with a source on every line (official prep pages for Google, Meta, NVIDIA, Netflix and Amazon, everything else marked community-reported). Use when the user says "research Google", "tell me about this company", "company brief", "prep me for Meta", "what's their interview process", "what does this team do", or before a coffee chat or interview.
1228d agoReviewMountCreate a free account to mount
Resume Writer. Rewrites your resume for each role so it reads like the job description, using only what is true: it mirrors the posting's own words for skills you really have, moves buried results into strong bullets (a number, a strong verb, one line), reorders for the role, and asks you about anything the posting wants that the resume does not show. Scores the match from 0 to 100 with a published formula (minimum qualifications, preferred qualifications, bullet strength, sections) and runs a truth check that fails if the rewrite adds a number or a skill that was not in your original. Use when the user says "rewrite my resume", "tailor my resume", "ATS score", "beat the ATS", "match my resume to this job", "resume for Google", "improve my bullets", or after /hunter-scout picks a role.
1228d agoReviewMountCreate a free account to mount
Salary Negotiator. Benchmarks the role and scripts your counter-offer. Turns an offer into total compensation year by year (base, bonus target, equity with its real vesting schedule including back-loaded ones, sign-on), compares offers side by side, pulls wage percentiles from the U.S. Bureau of Labor Statistics (OEWS) for your occupation and area, adds pay ranges printed in job postings with their URL, and writes a counter range and a polite script that cites every number. Never invents a market number. Use when the user says "I got an offer", "negotiate my salary", "is this offer good", "compare offers", "counter offer", "what should I ask for", "total compensation", "RSU vesting", or when a role reaches the offer stage.
1228d agoReviewMountCreate a free account to mount
The Job Scout. Finds the best open roles for the user's profile and ranks them by fit: pulls live listings from public job boards that need no login (Greenhouse, Lever, Ashby, NVIDIA's Workday board, Netflix's careers search), filters by title, place, remote and how recent, scores every listing 0-100 against hunter/profile.json with the reasons (title, skills, location, seniority, pay range, freshness), writes hunter/jobs.json and adds the user's picks to the pipeline. Gives the manual route for Google, Meta and Amazon, whose careers sites cannot be read by a script. Use when the user says "find me jobs", "best listings for me", "scout roles", "what's open at Google", "search Software Engineer jobs", "rank these jobs", or "where should I apply".
1228d agoReviewMountCreate a free account to mount
Pipeline Tracker. Tracks every role, contact and next step in one pipeline: hunter/pipeline.json, the single file every hunter skill reads and writes. Adds and updates roles and contacts, moves roles through the stages (saved, applied, screen, interview, onsite, offer, rejected, withdrawn), shows a summary by stage, what is coming up this week, what has gone stale, and exports CSV for a spreadsheet. Owns the pipeline schema and validates it after every change. Use when the user says "show my pipeline", "where am I with each application", "add this job", "I applied", "I got an interview", "I got rejected", "what's next", "what's stale", "export my applications", or "track this".
1228d agoReviewMountCreate a free account to mount
Runs the task through six agents in parallel, each locked to a different strategy, then a seventh judge ranks the six attempts and synthesizes a final answer that steals the strongest part of each; invoke via /67 for high-stakes or open-ended work where a single attempt would leave quality on the table.
113mo agoReviewMountCreate a free account to mount
Maximum-aesthetic mode for any visual deliverable (Meta ads, slide decks, landing pages, social graphics, posters, UI) that bans every AI-slop tell, forces a real design direction, and audits the result before shipping; invoke via /aura-farming whenever a visual is being created and it needs to look like a designer made it.
113mo agoReviewMountCreate a free account to mount
Session mode that translates every sub-agent prompt into Mandarin before dispatch (more meaning per character, fewer tokens) while keeping code, identifiers, and all user-facing output in English; invoke via /china-maxing at the start of any session that will fan out sub-agents and the token bill matters.
113mo agoReviewMountCreate a free account to mount
Anti-hallucination mode where Claude drafts an answer and then becomes obsessed with proving itself wrong, attacking every claim with tools and counter-evidence and shipping only what survives; invoke via /crash-out on factual questions, debugging, research, or any answer where confident-and-wrong is expensive.
113mo agoReviewMountCreate a free account to mount
Startup idea analyzer that channels a 24-year-old founder with Euro Summer photos and a $100M raise for a ChatGPT wrapper, runs the idea through a rigorous teardown underneath the bit, and assembles the strongest possible business model and pitch; invoke via /larp when the user shares a business, app, or product idea worth pressure-testing.
113mo agoReviewMountCreate a free account to mount
Works a critical failure under hard constraints — limited options, no clean fix — to get the broken thing home with whatever you have; invoke via /apollo-13 when something important is down, the usual tools are unavailable, and you must improvise a survival fix.
105mo agoReviewMountCreate a free account to mount
Takes the whole task and runs it end to end without stopping to ask, leaving the user to review at the finish line; invoke via /autopilot-chaos when you want a fully autonomous run and will inspect the result once it's done.
105mo agoReviewMountCreate a free account to mount
Goes underground to reverse-engineer internals, read the source nobody reads, and explain how something actually works; invoke via /basement-hacker when documentation is missing or lying and you need ground truth from the implementation itself.
105mo agoReviewMountCreate a free account to mount
Goes wide and exhaustive — every option, every edge, every step spelled out, the opposite of a compressor; invoke via /caffeine-overdose when you want maximum thoroughness and nothing left implicit.
105mo agoReviewMountCreate a free account to mount
Compresses long, repeated sub-agent instructions by translating them into Mandarin (more meaning per character) to slash the token bill, then dispatches the compressed brief to a fleet of sub-agents while preserving original intent; invoke via /chinese-grandpa when you are about to fan out the same heavy instructions to many sub-agents and the cost is climbing.
105mo agoReviewMountCreate a free account to mount
Makes the judgment calls itself and keeps moving instead of pausing at every fork — fast and opinionated, best on low-stakes work; invoke via /cowboy-coder when you'd rather get a decisive result than answer twenty clarifying questions.
105mo agoReviewMountCreate a free account to mount
Fires out ideas at full speed — twenty rough directions in a minute for the user to cherry-pick; invoke via /crackhead-energy when you're brainstorming and want raw quantity and range over polish.
105mo agoReviewMountCreate a free account to mount
Anti-gold-plating mode that builds the simplest functional version first, skips overengineering, and ships something usable today because working beats perfect; invoke via /divorced-dad when you need it live tonight, not pretty.
105mo agoReviewMountCreate a free account to mount
Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.
CLAUDE.md or AGENTS.md?
CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.
What is a skill?
A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.
Can I search my own team's files too?
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.
JakeschincariolSkill