Claude Guide for Outreach: 32 Claude skills for opening conversations with people you do not yet know, following one outreach run in eight stages: decide who to reach with an ideal client profile, a target account list and a warm path check; research the company with a sourced fact list and a research brief; research the person with a contact shortlist and an identity check; find the reason to write with a trigger event scan; write it yourself from talking points and a cold email outline; check and send in small runs with a message checklist and a run of ten plan; go from reply to meeting with reply triage, first call prep and a call recap; then review what worked with an outreach log and a review of your own counts. For founders, independents and sellers. Claude researches and prepares; you choose the people, write every word and press send.
Plugin outreach-pack from marketplace 90n-skills in polar-bear-org/claude-skills. Commands read from the repo's manifest — 17 days ago.
reach-buying-signals-watchlistBuilds a buying signals watchlist for the accounts on your list, with the one or two public signs worth watching per account, the page where each would appear, how often you look, the alert words, what you will do when a sign appears and the accounts to stop watching. Use for "run reach-buying-signa
reach-buying-situations-mapMaps the moments that start a need for your work, each written as "when...", marked seen in your work or assumed, with the outside sign you could spot for each and the situations you leave alone. Use for "run reach-buying-situations-map", "buying situations map", "category entry points", "when do cl
reach-call-recapTurns your notes from a first call into a recap, with what they said in their words, what you promised and by when, what they said they would do, the agreed next step and date, points for the recap note you write and what goes into the log. Use for "run reach-call-recap", "call recap", "recap my cal
reach-cold-call-outlineBuilds a cold call outline in keywords, with the opening and "is this a good moment", the reason for the call in one line, two open questions, the ask with two times, what to do with two common refusals and a voicemail of about twenty seconds. Use for "run reach-cold-call-outline", "cold call outlin
reach-cold-email-outlineSets up a cold email outline for one person, with a warm path and past thread check, a five-slot frame you fill in your own words, flags per line and one follow-up date. Use for "run reach-cold-email-outline", "cold email outline", "cold email", "first email to a stranger", "how do I structure a col
reach-company-fact-listCollects up to twelve numbered facts about one organisation from public pages, one claim per line with its date and link, sorted into what the organisation is doing now and recent signals, with the claims dropped for having no source and the unknowns. Use for "run reach-company-fact-list", "company
reach-company-research-briefWrites a half-page company research brief only from your numbered facts, with each sentence citing its fact, what the organisation is doing now, two or three hypotheses each ending in a question, why now or "no reason yet" and the unknowns. Use for "run reach-company-research-brief", "company resear
reach-connection-requestPrepares connection request notes one person at a time, with the true context for each, one specific detail, why connecting is useful to them, no pitch and no link, and the people taken off the list for having no true context. Use for "run reach-connection-request", "connection request note", "Linke
reach-contact-shortlistBuilds a contact shortlist for one organisation, with the roles that live with the problem, the people publicly named in those roles with name, role and source only, the one or two you choose to write to and the warm path for each. Use for "run reach-contact-shortlist", "contact shortlist", "who sho
reach-conversation-openerPrepares the first private note to someone who accepted your request, replied or commented, with the one reason to write, two or three points from the real exchange, an ask that matches how little you know each other and an easy way to decline. Use for "run reach-conversation-opener", "conversation
reach-first-call-prepPrepares one page for a first call, with why they agreed to talk, three open questions taken from your hypotheses, what you will listen for from your red flags, what you will not pitch, a short agenda to propose at the start and the next step you would ask for. Use for "run reach-first-call-prep", "
reach-follow-up-trackerBuilds this week's follow-up tracker, with the replies you owe first, one follow-up per silent thread on a date you set with what it could add, the point where each thread closes and first calls to book with free times from your calendar. Use for "run reach-follow-up-tracker", "follow-up tracker", "
reach-grammar-checkFixes grammar, spelling and punctuation only, with every change listed before and after with the rule, fixes that could change your meaning asked as questions, and your wording, tone and length left alone. Use for "run reach-grammar-check", "grammar check", "check my grammar", "fix typos only", "pro
reach-ideal-client-profileBuilds your ideal client profile from real past engagements, with the situations and triggers that make someone need you, the job they hire you for, the roles in the decision and red flags you can observe on a first call. Use for "run reach-ideal-client-profile", "ideal client profile", "who should
reach-identity-checkConfirms that your sources are about the right person, with each source tested for same name and same organisation, namesakes set aside, the role confirmed or changed and a verdict of confirmed or not confirmed. Use for "run reach-identity-check", "identity check", "is this the right person", "same
reach-message-checklistChecks the message you wrote against six checks in order, with a pass or a flag per check, the line each flag refers to and the reason, and no replacement wording. Use for "run reach-message-checklist", "message checklist", "check my message", "does this sound like a pitch", "review my cold email",
reach-next-run-testSets up a test of one change over your next runs, with the change you will make, what you expect and why, what you will count, how many runs before you look and what would make you keep it or drop it. Use for "run reach-next-run-test", "next run test", "test one change", "improve my outreach", "A/B
reach-outreach-logKeeps a private outreach log with one row per person you wrote to, holding the date, channel, the reason you used, whether a warm path existed, reply or none, first call or none, open promises and any request not to be contacted. Use for "run reach-outreach-log", "outreach log", "track who I contact
reach-outreach-reviewReviews your outreach from your own log, with your counts by reason, channel and warm or cold, what you expected and what happened, what the small numbers can and cannot tell you, what you would keep and the one thing to change. Use for "run reach-outreach-review", "outreach review", "what worked in
reach-outreach-rules-checkLists the rules questions one message raises, with the channel, where the recipient is and what kind of address it is, the questions each official page raises, what is unknown and the questions to take to an adviser. Use for "run reach-outreach-rules-check", "outreach rules check", "is cold email le
reach-person-research-briefWrites a person research brief from public, work-related sources, with sourced and dated facts about the person's role, talks, interviews and articles, what is out of scope, what you share from your own knowledge, the unknowns and the questions research could not answer. Use for "run reach-person-re
reach-reason-to-writeLays the reasons to write that serve the other person against what you know, with the fact each one rests on, a pitch-in-disguise test and one reason left for you to choose. Use for "run reach-reason-to-write", "reason to write", "why am I reaching out", "what do I say that is not a pitch", "a reaso
reach-reply-triageReads one reply and sets out what it actually says, what it asks of you and by when, the facts it adds to your brief and points for your answer, with "stop" recorded at once so the person is never written to again. Use for "run reach-reply-triage", "reply triage", "they replied what now", "how do I
reach-research-coverage-checkLabels your research as enough to work from, thin or nothing found, with the count of sourced facts, whether identity was confirmed, what a thin result allows you to say honestly and your call to write, wait or ask someone who knows them. Use for "run reach-research-coverage-check", "research covera
reach-run-of-tenPlans one small run of about ten people for this week, with the time block in your calendar, one reason and one status per person about your own actions, what is ready and what waits, and the next run's start date. Use for "run reach-run-of-ten", "run of ten plan", "plan my outreach week", "weekly o
reach-source-checkChecks the source behind each fact for who published it, whether it is the original, the date on the page and whether the page says what the fact claims, with disagreements shown side by side and a keep, fix or drop per fact. Use for "run reach-source-check", "source check", "check my sources", "is
reach-talking-pointsPrepares two or three talking points for the one reason you chose, each three or four sentences, with every fact carrying its source or marked as your history, your offer kept out and no greeting, sign-off or assembled message. Use for "run reach-talking-points", "talking points", "what should I say
reach-target-account-listBuilds a target account list from a two-line brief, with the criteria that show an organisation has the problem, each one checked yes, no or unknown with a linked source, the number you can really work and the drops with reasons. Use for "run reach-target-account-list", "target account list", "build
reach-trigger-event-scanScans for recent public events for one person and their organisation, each with date and link, sorted inside your window or too old, with private events left out, both readings of each event and a pitch-hook test. Use for "run reach-trigger-event-scan", "trigger event scan", "trigger events", "reaso
reach-useful-material-matchMatches your own materials to one person's facts, with each item checked against what the research found, none, one or two that fit with the fact that makes them fit, and what you must not send. Use for "run reach-useful-material-match", "useful material match", "what can I share with them", "which
reach-voice-guideBuilds your writing voice guide from messages you wrote and sent yourself, with how you open, ask and sign off, the words you use and never use, an AI-tell checklist and one real message before and after. Use for "run reach-voice-guide", "writing voice guide", "voice guide", "make my messages sound
reach-warm-path-checkChecks each account for a warm path from your own connections export, inbox and notes, with who you already know there, how well you know them in your own words and a verdict per account. Use for "run reach-warm-path-check", "warm path check", "who do I know at this company", "check my connections",
42 skills for the whole product job, stage by stage, from the vision to the weekly update, in eight stages: set direction, discover, decide, define, deliver, launch, prove, and run the product. Each skill is named as an action and keeps one framework inside, with the inputs it needs, where it breaks, a fixed output template, a finish line and the next skill to run.
42 skills
41 skills for the documents product people write, from the first brief to the post-launch review: setting up your voice and templates, discovering, shaping the vision, defining the work, deciding, aligning, reporting up, shipping and learning, running the team, and reviewing and editing. Each skill produces one finished document with a named reader and a length budget.
41 skills
The Complete Claude Guide for L&D: 40 Claude skills for the whole L&D job, in eight stages: diagnose the need with the request triage, the performance gap and the action map; work with the experts through the interview, the task breakdown and the review plan; design the learning with objectives, an evaluation plan, a design document and a curriculum map; build and test scenarios, a storyboard, a knowledge check, the check of an AI draft and a learner walkthrough; run the room with a session plan, slides, a facilitator guide and a pilot; carry it into work with a job aid, spaced practice and a manager briefing; measure what changed with a feedback form, an ROI estimate and the one-page report; and lead L&D through the year plan and the business case. For L&D managers and specialists, instructional designers, trainers and facilitators, and L&D leaders. Claude drafts and checks, people decide: nothing a learner does in training is used to grade, rank or build a case against them.
40 skills
Claude for Consultants · Team in Claude: 39 Claude skills for winning and shaping client work when the client has AI too, from their brief to the signed scope, as eight desks in order: Intake reads the client's brief, qualifies the opportunity and records the bid or no-bid decision; Discovery prepares the call, keeps the notes and sends the recap email; Problem writes the problem statement, the issue tree and the hypothesis test plan; Strategy builds options and the recommendation memo; Pricing shapes good-better-best options, fees and a MoSCoW scope; Proposal writes the consulting proposal, the AI use statement and the statement of work; the Client room prepares the walk-through deck, the AI objection answer and the negotiation plan; Follow-through covers follow-up emails, the mutual action plan and the win/loss review. For independent consultants and partners in advisory practices. Claude structures, drafts and checks; it never invents a reference, a result, a number or a client quote, and you run the conversation, make the recommendation and send everything yourself.
39 skills
39 skills for running the whole product cycle with Claude, in seven phases that each hand a named artifact to the next: set Claude up and connect it, frame the question, discover the evidence, decide, build and ship, communicate the call and run the week. Each skill teaches one named, checkable method, with the inputs it needs, where it breaks, a fixed output template and the next skill to run.
39 skills
36 skills for deciding if AI fits, testing it before launch and keeping it honest after: deciding if AI fits, speccing it as tests, briefing the model and the agent, building the evals from real outputs, shipping it safely, running and improving it, and its cost, price and explanation to leaders. Each skill is one named method or one artifact, with the inputs it needs, where it breaks and a fixed output template.
36 skills
Talk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.
1 skill
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
Package any website or local web build into a lightweight desktop app with Pake CLI.
1 skill
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.