Copy this prompt into the AI assistant you're using.
Follow https://skillsmp.com/skill-install/prompt.md to install Agent Skills from https://github.com/gavin844/claude-code-skills.Loading the repository README…
Showing 37 of 37 collected skills.
A personal-CFO and investing-coach persona that keeps a money scoreboard honest and gets better at weekly stock picks by reading a lessons ledger before every new pick. Use for choosing a weekly watchlist of picks, writing the weekly P&L recap, explaining why…
How to reliably capture a sportsbook's board and prop menus with Playwright without destroying the user's logged-in session or reporting fake success. Use for "capture the board", "scrape my book", "get the soccer lines", "the scraper is broken", or any work…
The daily step-by-step for building a recommend-only betting card across every sport you follow. Use for "start building the card", "build today's card", "make the card", "morning card", or any request to produce the day's plays. Runs the captures, ingests…
A recommend-only sports-betting analysis agent. It finds plays that are genuinely +EV at your sportsbook by de-vigging sharp markets and running per-sport models, gates them through backtest-proven confidence, grades only final games, and gets sharper from…
Analyze a UFC or MMA card the user sends and give an honest read on who to back, priced against their sportsbook. Use for "who do you got", "UFC card", "fight night", "who wins this fight", "MMA picks", "break down this card", or when the user pastes or…
Builds an Opportunity Blueprint, the tailored top-of-funnel document that shows a prospect where AI can move their business and earns the first meeting. Load when the user says "build a blueprint," "opportunity blueprint," "top-of-funnel doc for [company],"…
After a client or prospect meeting, turns the transcript or notes into a crisp follow-up email plus a list of concrete next actions with owners and dates. Load when the user says "write the follow-up," "draft a recap email," "follow up with [company]," or a…
Scripts a tight two-minute product demo for a prospect: the hook, the one wow moment, and the ask, with no filler. Load when the user says "script a demo," "demo script for [company]," "how should I demo this," or has a prototype, MVP, or batch run to show a…
Produces a one-page pre-call brief covering the company, who is in the room, their likely AI pains, and your angle, pulled from the CRM, calendar, past meeting notes, and web research. Load when the user says "prep me for my call with X," "I have a call with…
When the user wants a human-readable changelog or release notes from shipped work. Use when the user says "write release notes," "changelog," "what shipped," "summarize this branch/PR for release," or wants a plain-language summary of what changed for a…
Turns discovery notes into a structured Statement of Work draft with objectives, phases, deliverables, timeline, team, and an investment placeholder. Load when the user says "scope this," "draft a SOW," "statement of work," "turn these notes into a proposal,"…
Write and edit source files with Write/Edit, never through bash heredocs or python -c string surgery. Use when creating or modifying any code file. Prevents escaping corruption that silently breaks the file you just wrote.
Make failures visible instead of silent. Use when writing exception handling, truthiness checks, resource lifecycles, or any lookup that can return nothing. Prevents bugs that present as working code.
Find the line that produced the wrong output before adding a check that would have caught it. A guard is not a diagnosis, and a guard that reads as correct hides the cause it failed to fix. Use whenever tempted to add a cap, assert, retry, or validation in…
Every guard, validator, audit or harness must be proven against a known-bad case AND a known-good case before its output is trusted. Load before writing or believing any checker - a contrast audit, a line-band guard, a UI harness, a lint rule, a fraud filter.
Use when writing a script, or when about to write one that resembles something written before, or when the user says reuse, do not rewrite, regenerate, you wrote this before, or every time you. Turns a working one-off into a tool a future session runs instead…
When you add a config value, threshold, or flag, prove some code reads it before claiming it does anything. Use whenever writing to a config file or introducing a constant that is meant to gate or size behaviour. Prevents settings that look like controls but…
Grade a job posting for listing integrity (is it a live, current, original posting) and measure whether the employer replies to applicants. Load before building or changing a posting grader, its signals, its wording layer, its corpus of postings, or any…
SOP for running a client's batch of resumes through an AI resume-screening tool. Receive the job description plus a zip of resumes, score resume-only against the role's must-haves, and deliver a ranked A/B/C shortlist with the top slice flagged for interview.…
Write cold outreach to staffing agencies and in-house recruiting teams, the buyers for an AI resume-screening product, leading with their real pain (a pile of applicants nobody has dispositioned). Use when the user says "write outreach to a staffing agency",…
A limit that counts by name misses things that share a cause. Group by what decides the outcome, not by how the source labels it. Use for concentration caps, diversification, retries, test coverage, and any "at most N of these" rule.
List the whole option set before picking from it. Ranking a subset you happened to load is not selection, it is accident. Use before choosing a best candidate, and whenever the pool comes from a file list, glob, or pipeline step that could quietly be short.
Treat the age of every input as part of its validity. Use whenever reading cached files, scraped captures, stored prices, stats, or history that a later step will act on. Prevents confident output computed from stale data.
Any balance, bankroll, profit or spend figure must be read from the system of record, never recomputed from history. Load before touching bankroll, P&L, capitalized profit, casino ledgers, spend meters, or any number the user will compare against a real…
Any file, DB row or KV key that both a scheduled task and an interactive session can write needs exactly one owner, or it gets destroyed. Load before adding a cron job, a watcher, a screenshot script, or any second process that touches state a human is also…
Anything the user explicitly decided is a fact about the world, not data your code owns. Never let a regeneration delete, overwrite, or transplant it. Use whenever a rebuild, re-render, re-sync or re-record replaces rows the user has touched.
When you change what a metric counts, every stored value of it becomes incomparable. Stamp the definition alongside the data and refuse to diff across versions. Use whenever editing an exclusion list, filter, threshold, or formula behind a tracked number.
The 20 checks every web app must pass before it is called done, plus the measurement commands that prove it. Use whenever building, styling, theming or shipping any rendered surface - a page, a dashboard, an artifact, a landing page. Load BEFORE writing UI,…
How to put real motion and real 3D into a web app without it reading as generated. Jitter to Lottie (dotlottie-react, the Lottie Creator and LottieFiles MCPs), Vectary embeds and their free-tier limits, and 3D in React via React Three Fiber (Threlte is the…
The 30 tells that make a site look vibecoded, with a runnable detector, plus the design tools worth reaching for (Magic MCP, Vectary, Threlte / React Three Fiber, Jitter). Use whenever building, restyling, reviewing or shipping any website, landing page,…
Use the moment the user corrects something, pushes back, repeats an instruction, or says that is not what I meant, no I said, I told you, you keep, stop doing, or every time. Turns a correction into a durable change in the smallest place that will hold it,…
Activate when the user asks for creativity, invention, or ambition: "be creative", "creative mode", "think bigger", "innovate", "surprise me", "don't be literal/basic", "come up with something", "what could this be", "make it special", "add cool stuff", or…
Use before telling the user anything is done, fixed, working, shipped, deployed, or passing, and use at the start of any multi-step task to state what finished will look like. Defines what counts as evidence for a web page, a script, a scheduled job, a…
Do the work instead of asking permission for it. Always on. When the next step is obvious and reversible, take it and report what happened. Reserve questions for choices only the user can make.
Load the skill that matches the situation you are IN, not the words the user used. Use when about to add a guard, automate a browser, ship a UI change, add a constant, or explain a zero. The router fires on the user's prompt; these failures happen hours later…
Never quietly change a rule the user set, and run the one cheap check that would settle your assumption before acting. Use before any command that writes, sends, deploys, or spends. Removes the mistake-then-immediate-fix loop.
Always on. Hard word caps on every reply to the user. Lead with the answer, cut process narration, no recaps. Use for every response, not just when asked to be brief.
Repository README source: README.md
Read the source README