Claude Skills by SkillMedev

Turn a job description into a weighted, anchored rubric for the pre-interview resume/CV screen so applicants are filtered against the same job-relevant criteria, in writing, before opinions form. Use when you have a JD and an applicant pile and need to decide who advances to interviews, set up a fair resume screen, or replace gut-feel resume sorting with a defensible filter. Do NOT use when building the interview-loop scorecard interviewers fill in during or after interviews - use hiring-scor...

Labels a keyword's dominant search intent (informational, commercial, transactional, or navigational) from the live SERP and prescribes the page type that can rank for it. Use when someone asks "classify these keywords by search intent", "should this keyword get a blog post or a landing page", "what is the search intent of this keyword", or is screening a keyword list for intent before producing content. Do NOT use for grouping keywords into topical clusters and mapping them to a site archite...

Sets up a PARA-based second brain in any notes app (Notion, Obsidian, Apple Notes, Logseq) - Projects, Areas, Resources, Archives buckets, a frictionless universal capture inbox, weekly organizing, wiki-link and map-of-content linking, progressive summarization for recall, and maintenance rituals. Use when someone says "help me set up a second brain", "my notes are a mess and I can never find anything", "how do I organize Obsidian with PARA", or captures ideas but never uses them. Do NOT use ...

Guides detection, emergency rotation, and prevention of leaked secrets and credentials across source code, git history, CI pipelines, logs, and infrastructure config. Use when someone says "I think I committed an API key", "a secret leaked", "scan the repo for credentials", "how should we store secrets", or is setting up secrets management for an application, CI/CD, or Kubernetes. Do NOT use for detecting or redacting personal data like names, emails, or SSNs - use pii-scrubber instead; for r...

Reviews code for the security flaw classes that cause the most breaches - broken authorization and IDOR, injection, SSRF, mass assignment, and unsafe deserialization - and returns a short, focused findings list with concrete fixes. Use when someone asks "review this code for security issues", "is this endpoint safe", "check this PR for vulnerabilities", or is shipping auth logic, new API endpoints, file handling, or anything that touches untrusted input. Do NOT use for general code quality, s...

Builds a behavioral segmentation system for lifecycle messaging - RFM-based segments, event-driven membership triggers, one next action per segment, size audits, and send-time suppression rules. Use when someone asks "how should I segment my users", "our emails get ignored, who should get what", "how do I message at-risk users differently", or is personalizing lifecycle campaigns to cut unsubscribes and lift click-through. Do NOT use for building ad-platform audiences - use audience-targeting...

Wins listings before competitors are invited by nurturing homeowner leads with quarterly home-value updates, an equity-position letter, lifecycle triggers like a neighborhood sale, and the CMA offer as the conversion event. Use when an agent says "how do I get more listings", "nurture my seller leads", "a homeowner asked what their house is worth", or "how do I stay in front of past clients and my farm". Do NOT use for keeping buyer leads warm - use buyer-nurture-sequence instead - or for the...

Audits and rewrites a page for organic search - title and meta lengths, heading hierarchy, intent match, internal links, schema markup, and Core Web Vitals - and returns a prioritized fix list. Use when someone asks "why isn't this page ranking", "audit my page for SEO", "rewrite my title and meta description", "does this need schema markup", or before publishing a page that must earn organic traffic. Do NOT use for grouping keywords into topical clusters across a site - use keyword-cluster-b...

Audits whether a seed-stage company clears the Series A bar - benchmark metrics, narrative, team, and data room - and produces a red/yellow/green readiness scorecard with a 90-day gap-closing plan. Use when a founder asks "am I ready for Series A", "what metrics do I need to raise an A", "what goes in a Series A data room", "should I raise now or wait two quarters", or is deciding when to open an A process. Do NOT use for a general pre-pitch hygiene check at any stage - use fundraise-readines...

Structures sermons, lessons, and motivational talks around one central idea with the classic teaching shape - a hook, three parallel points each stated, explained, illustrated, and applied, a concrete application, and a bookend close - plus timing and emphasis notes. Use when someone asks "outline my sermon on this passage", "structure a talk with three points", "help me land the close of my message", or has a theme and needs it built into a deliverable outline. Do NOT use for writing a full ...

Compares a draft or outline against the pages already ranking for its target query and outputs the missing subtopics, entities, and questions as a prioritized gap table - each gap classified must-have, differentiator, or skip. Use when someone asks "compare my draft against the top ranking pages", "what is my draft missing compared to the pages that rank", "run a content gap analysis on my draft", or has a target query plus 3-5 ranking URLs and wants to close coverage gaps before publishing. ...

Classifies incident severity (SEV1-4) using impact, scope, and urgency signals and decides who to page. Use when an alert fires or a report comes in and a severity call must be made quickly.

Takes a side project from idea to shipped launch with behavior-based validation, a ruthlessly cut MVP, a hard timebox, and explicit kill criteria so nights-and-weekends effort never runs open-loop for months. Use when someone asks "how do I launch my side project", "should I keep building this", "how do I validate before building", "I've been building for months and haven't shipped", or "how do I know when to quit". Do NOT use for the Product Hunt assets and mechanics specifically - use produ...

Use when reviewing, grading, auditing, or improving a whole existing skill or pack - judging whether a skill is good, fixing one that misfires or won't activate, or driving one or many skills to a quality bar. Audits to an absolute A+ bar and hands back ship-ready SKILL.md rewrites, not a report the user must act on. Do NOT use when tightening only a description or trigger in isolation - use skill-description-writer instead; do NOT use when authoring a brand-new skill from scratch - use skill...

The section-by-section anatomy standard every paid-quality SKILL.md must meet. Use when drafting or restructuring the BODY of a skill, deciding what sections it needs, or checking a draft against the house standard - "what sections does a skill need", "structure this SKILL.md", "is this skill body complete". Do NOT use for the end-to-end creation process from a raw idea (use skill-creator), grading a finished skill (use skill-auditor), or writing only the description field (use skill-descript...

Use when authoring a brand-new skill from scratch - turning a capability idea or a "make me a skill that…" request into a complete SKILL.md with a trigger-precise description and the full paid-quality anatomy: procedure, elicitation, thresholds, worked artifact, deliverable, Do NOT, quality bar. Triggers on "write a new SKILL.md from scratch", "turn this capability idea into a complete skill". Do NOT use to review or grade an existing skill (use skill-auditor), to convert an existing prompt (...

Writes the description field that makes a skill fire reliably - WHAT it does, WHEN to invoke it with quoted user phrasing, and what it is NOT for. Use when drafting or improving only the description or trigger of a SKILL.md or catalog entry - "this skill never fires", "fix this description", "write the frontmatter description". Do NOT use to author a whole skill (use skill-creator) or to grade/audit one (use skill-auditor).

Designs the membership and structure of a skill pack - persona, member selection, install sequence, cross-links, and what to add or cut. Use when someone asks "which skills should go in this skill pack", "design the membership of a new skill pack", "decide which skills to add or cut from a pack", or is turning a vertical (an industry or role) into a coherent bundle. Do NOT use to grade or rewrite a finished pack to a quality bar (use skill-auditor) - this designs composition.

Empirically tests a skill with subagent scenarios to verify it fires on the right prompts, stays silent on the wrong ones, and performs its job when loaded. Use when validating a new or modified SKILL.md before publishing - "test this skill", "does this trigger correctly", "verify the skill works". Do NOT use to statically grade or rewrite skill quality (use skill-auditor) - this runs live behavioral tests.

Use the Skill Me catalog from inside any conversation - discover, install, and manage Claude skills through the Skill Me MCP, and load installed skills automatically each session.

Builds a personalized sleep protocol - a fixed wake time held within 30 minutes daily, a chronotype-aligned sleep window, a light-exposure plan, environment settings, evening input rules, and a scripted wind-down routine - from a baseline assessment. Use when someone says "I can't fall asleep", "I wake up at 3am every night", "fix my sleep schedule", or "I'm exhausted no matter how long I sleep". General wellness education, not medical advice - snoring with gasping, suspected apnea, or chroni...

Structure a persuasive slide deck - narrative arc, one-idea-per-slide discipline, and headlines written as takeaways not labels. Use when building any presentation that must move an audience to a decision.

Maps engineering controls to SOC 2 Trust Service Criteria, builds a continuous evidence-collection plan with cadences per control family, and produces the control-to-evidence table auditors work from. Use when someone asks "what evidence do we need for SOC 2", "map our controls to the Trust Service Criteria", "how do we prepare for Type II fieldwork", "the auditor asked for access reviews", or is closing findings or standing up a compliance program. Do NOT use for building an incident postmor...

Write one platform-native caption from a topic and brand voice, with a front-loaded hook, native length, and a single earned CTA. Use when the user gives a topic (and optionally brand voice or a described image/video) and asks for an Instagram, LinkedIn, X/Twitter, or TikTok caption. Do NOT use when the user wants a dedicated standalone LinkedIn post - use linkedin-post-writer instead; or a multi-post X thread - use tweet-thread-builder instead; or to adapt one existing piece of content into ...

Builds a 4-week multi-platform posting calendar for a brand or social team, balancing content pillars, per-channel cadence, and real key dates into a week-by-week grid. Use when the user asks to plan, build, or audit a social content calendar or posting schedule across multiple channels (LinkedIn, X, Instagram, TikTok, YouTube Shorts), assign content pillars and ratios, or map a month of posts to launches and events. Do NOT use when planning a solo creator's single-channel video or podcast ca...

Generates 10 labeled opening lines for a written social post, one per hook archetype, so the writer can test instead of guess. Use when drafting or rewriting the first line of a LinkedIn post, X post or thread, Instagram caption, or newsletter intro. Do NOT use when the hook is the spoken or on-screen opener of a short-form video (TikTok, Reels, Shorts) - use video-hook-writer instead.

Reframe and export a finished video for social platforms - 9:16 ↔ 16:9 cropping, burned-in captions, a platform-native first frame, loop design, and per-platform specs (aspect, length, safe areas) for TikTok, Reels, Shorts, X, and LinkedIn. Use when someone says "make this vertical", "crop to 9:16", "format for TikTok/Reels/Shorts", "add captions/subtitles", "why is my video cut off on mobile", "resize for Instagram", or "export for social". Do NOT use when the question is about the storyboar...

Score a video like an editor: beat-match cuts to the music, land SFX on transitions, pace the voiceover so it breathes, source royalty-free tracks safely, and duck the music so the VO sits clearly on top. Use when adding music, sound effects, or voiceover to a video, when asked to "sync cuts to the beat", "the music is drowning out the voice", "add whooshes on the transitions", "where do I get royalty-free music", "mix the audio", or "the VO feels rushed". Do NOT use when wiring audio into th...

Use when a task needs live space or geophysical data - "recent earthquakes near X / above magnitude Y", "NASA picture of the day", "near-Earth asteroids this week", or "latest full-disk Earth image". USGS FDSN is the default for quakes (no key, GeoJSON); NASA's APIs cover astronomy (DEMO_KEY works, free key is instant). Do NOT use for weather, storms, or air quality - use weather-climate instead; do NOT use for maps/geocoding - use geo-places instead; if the request is a vague "I need live da...

Writes and tunes PySpark jobs - join strategy and broadcast size limits, shuffle-partition sizing, skew diagnosis and salting, UDF avoidance, caching, and output file layout - with concrete size and skew thresholds. Use when someone asks "why is my Spark job slow", "should I broadcast this join", "one task takes forever while the rest finish", "my job OOMs during a join", or is writing a new PySpark ETL job. Do NOT use for Kafka topic, consumer-group, or streaming-pipeline design - use kafka-...

Writes full speeches for the ear - a narrative arc from hook to callback close, three story-anchored movements, two or three quotable lines built with antithesis and imagery, and pause and timing markers budgeted at roughly 130 words per minute. Use when someone asks "write my keynote", "draft a wedding toast", "I have 10 minutes on stage, write the speech", or has a talk drafted that reads fine but dies when spoken aloud. Do NOT use for a sermon or teaching outline with application points - ...

Structures spreadsheet models a second analyst can audit - separated input/calc/output sheets, one-formula-per-row hygiene, built-in error checks, and a documented cover sheet. Use when someone asks "how should I structure this model", "clean up this spreadsheet before the board sees it", "why does my model break when I insert a column", or is building any forecast or calculator others will review. Do NOT use for the SaaS revenue logic itself - use revenue-modeling instead; for a full FP&A op...

Facilitates sprint planning end to end - backlog refinement checks against a Definition of Ready, a one-sentence sprint goal, capacity math from velocity and PTO, story selection and team commitment, task breakdown, and flagged risks with owners. Use when a team asks "plan our next sprint", "how much should we commit to", "write a sprint goal", or keeps blowing sprint forecasts. Do NOT use for running the retrospective after the sprint ends - use sprint-retro-facilitator instead.

Structures and facilitates sprint retrospectives with a timeboxed agenda, format selection, anti-blame ground rules, and owned action items that actually close. Use when someone asks "help me run our retro", "our retros produce the same actions every sprint", "what format should this retrospective use", or "how do I get the team to say what they're really thinking". Do NOT use for incident postmortems with a timeline and root-cause analysis - use postmortem-writer instead. For diagnosing chro...

Diagnoses slow SQL from the execution plan, names the cost driver, and delivers the rewritten query plus index DDL with the expected plan change and write-side cost stated. The general entry point for slow-query work that routes deep cases to specialist skills. Use when someone asks "why is this query slow", "can you optimize this SQL", "what index do I need", "this endpoint got slow and it's the database", or pastes an EXPLAIN output. Do NOT use for deep index strategy across a whole schema ...

Turns SQL query results into a decision-ready business narrative - headline finding, drivers, recommendation - plus the right chart choice for the data shape. Use when someone asks "what does this data actually mean", "summarize these query results for the exec team", "what chart should I use for this", or pastes a result set and wants the so-what for a non-technical audience. Do NOT use to diagnose or speed up the query itself - use sql-query-optimizer instead; do NOT use to build a full mul...

Writes project stakeholder updates readable in under 60 seconds - honest RAG status, decisions made, explicit asks with owners and dates, next milestones - tiered to the audience. Use when someone asks "write my weekly project update", "how do I tell stakeholders we're at risk", "draft a status email for leadership", or "my updates get ignored, fix the format". Do NOT use for aggregating many teams' statuses into one engineering-wide report - use eng-status-rollup instead. For monthly investo...

Writes a dispute-preventing statement of work with explicit inclusions and exclusions, a 2-revision-round limit, acceptance criteria, a 50-percent-upfront or milestone payment schedule, and a change-order clause, from a full template with [FILL] fields. Use when a freelancer or consultant says "write my SOW", "the client keeps adding stuff and I have nothing in writing", "how do I define scope in the contract", "what should my payment terms be", "draft a statement of work for this project", o...

Writes customer-facing incident status updates for each lifecycle stage - investigating, identified, monitoring, resolved - with cadence rules and plain-language templates. Use when someone asks "write a status page update", "what do we tell customers about this outage", "draft the resolved notice", or during an active incident needing customer communication. Do NOT use for the internal post-incident analysis - use postmortem-writer once the incident is closed; for deciding severity and inter...

Integrates the Unsplash, Pexels, and Pixabay APIs in code - auth, search endpoints, rate limits, attribution, hotlinking versus caching rules, and the compliance obligations that get apps deactivated when skipped. Use when someone says "integrate the Unsplash API", "pull images from Pexels in my app", "build an image picker on a stock photo API", "how do I trigger the Unsplash download endpoint", or is wiring stock imagery into a CMS, blog pipeline, or placeholder service. Do NOT use to choos...

Source the right stock photograph for a brief by picking the best library and crafting the search. Use when you need a real photo or image for a hero, blog post, ad, slide, mockup, social post, or thumbnail and you are not sure where to look or what to search, or when someone says "find me a photo of...", "where do I get images for this", "I need a hero image", or "good free stock photos for X". It covers free libraries (Unsplash, Pexels, Pixabay), curated and boutique sources (Stocksy, Still...

Use when plotting or outlining a novel or screenplay, structuring its acts/chapters/sequences, fixing a sagging middle or broken pacing, mapping a character arc onto plot beats, planting setups and their payoffs, or deciding scene order. Produces the macro architecture - arc, beat sheet, tension curve - not prose. Do NOT use to write the actual prose of a scene (use Fiction Scene Writer, which sits downstream of this), to establish or mimic a narrative VOICE (use Ghostwriter), or to write a n...

Use when someone starts lifting, hits a strength or hypertrophy plateau, restructures a lifting program, or wants to build strength or muscle - designing a progressive resistance program with splits, compound movement patterns, sets/reps, progressive overload, and deloads from barbells and dumbbells. General fitness guidance, not medical advice. Owns resistance/strength training only. Do NOT use to program high-intensity interval conditioning or circuits (use fitness-program), a steady-state ...

Builds a personalized one-page stress toolkit - mapped triggers, three rehearsed in-the-moment interventions, a recovery menu, and prevention habits - from a week of trigger tracking. Use when someone says "I'm constantly stressed", "I can't switch off after work", "help me deal with anxiety before meetings", or "I keep snapping at people". General wellness education, not medical or mental-health treatment. Do NOT use when the primary complaint is poor sleep - use sleep-optimizer instead; for...

Implements Stripe payments, subscriptions, and webhooks so billing state stays correct - Checkout Sessions, signature-verified idempotent webhook handlers, dunning, and SCA handling. Use when someone asks "add Stripe subscriptions to my app", "why is my webhook signature verification failing", "my database says subscribed but Stripe says canceled", "how do I avoid double-charging on retries", or "how should I handle failed payments". Do NOT use for choosing price points, tiers, or packaging -...

Writes specific, growth-oriented feedback on student work using the Glow-Grow-Go structure - evidence from the actual work, one improvement priority, and a concrete next action - sized to the context from draft comments to progress reports. Use when someone asks "write feedback on this essay", "help me comment on these lab reports", "draft progress report narratives", or "make this comment more useful to the student". Do NOT use for feedback to colleagues or direct reports at work - use feedb...

Converts a syllabus or topic list into an evidence-based study plan - material atomized into testable units, a spaced-repetition flashcard schedule with expanding intervals, active recall and Feynman-technique prompts instead of rereading, interleaved weekly sessions, and a practice-testing cadence with an error log. Use when someone says "help me study for this exam", "build me a study schedule", "I keep rereading and forgetting everything", or wants to learn a curriculum efficiently. Do NOT...

Builds secure Supabase apps - Row Level Security policies as the authorization layer, schema design against auth.users, Edge Functions for service-role work, realtime subscriptions, and versioned migrations. Use when someone asks "set up RLS for my tables", "is my Supabase app secure", "anyone can read my table with the anon key", "when do I need an Edge Function", or "why is my realtime subscription not receiving rows". Do NOT use for general Postgres schema design without Supabase - use dat...

Maps a product's supply chain across tiers, scores concentration risk - supplier, geographic, sub-tier, and logistics - and surfaces qualified alternatives with switching cost and qualification lead time for each critical node. Use when someone asks "where are our single points of failure", "map our supplier dependencies", "what happens if this supplier or region goes down", or is building a resilience, dual-sourcing, or nearshoring plan. Do NOT use for mapping competitors rather than supplie...

Designs a reusable macro and canned-response library that stays human and on-brand. Use when building, auditing, or expanding a support team's template playbook.