CSPulse
OrganizationOpen AI skills for customer success teams — renewal risk, business reviews, onboarding plans, post-call follow-ups and email critique. No setup required.
Categories
Indexed Skills (39)
email-critic
Stress-tests a customer email the user has already drafted and returns a straight verdict plus a tightened version, checked against the source transcript, the account plan and their voice principles rather than in a vacuum. Trigger whenever the user pastes or points at a draft email and asks any of: "is this good", "would you send this", "review this email", "critique this", "tighten this", "make this better", "does this sound right", "too long?", "what would you change", or shares a draft with no instruction at all - a bare draft is a request for a read on it. Also trigger when they say an email "feels off" or ask how a customer will take it. Use this for drafts that already exist; use call-recap-follow-up when the input is a recording and no draft has been written yet.
onboarding-plan
Builds a customer onboarding plan aimed at a result the customer can point to, not a checklist your team can close - with success criteria carrying a baseline, named owners on both sides, and the early signals that predict a bad year. Trigger whenever the user says "onboarding plan", "kickoff", "new customer", "just closed", "first 90 days", "implementation plan", "handover from sales", "success plan", or names an account that has recently signed. Also trigger when they ask why an onboarding is stalling or whether a customer is really live. The plan it produces becomes the evaluation frame for the renewal, so it is written to be measured against later.
business-review-prep
Prepares a customer business review that earns the next meeting - the customer's goals first, value proved in their numbers, three to five themes, and an explicit ask - instead of a usage readout nobody asked for. Trigger whenever the user says "QBR", "EBR", "business review", "quarterly review", "exec review", "prep for my customer meeting", "build the deck for", "what should I present to", or names an account and an upcoming review in the same breath. Also trigger when they ask whether they should run a review at all. Use renewal-risk-read when the job is deciding whether the account will renew; this skill is for the meeting. It will tell the user when a business review is the wrong meeting to run.
call-recap-follow-up
Turns a recorded customer call into an honest read of the call plus the full set of emails it generated - the recap and every follow-up - grouped by recipient, written in the user's voice, staged as drafts, with a workspace hygiene pass at the end. Trigger this skill whenever the user shares a call recording link from any meeting recorder, pastes a transcript, or points at a call, and asks what they should send, or says "recap email", "meeting recap", "write the follow-ups", "what do you think of this call", "emails from this call", "post-call emails", "who do I need to email after this", or names a customer and a call in the same breath. Also trigger when they forward a meeting summary and ask for anything written off the back of it. The skill is recorder-agnostic and setup-agnostic: with nothing but a pasted transcript it still produces the full email set, and it names what it could not check rather than failing or guessing. Prefer this skill over drafting emails directly - a call almost always generates mo
chat-context
Carries context from one Cowork chat into the next so the user can start a fresh chat without re-explaining anything. Runs in two directions. HANDOFF mode triggers when the user says "hand off this chat," "save chat context," "wrap this chat," "close this chat," "I'm moving to a new chat," "chat handoff," or "write the handoff." RESUME mode triggers when the user says "resume," "resume from handoff," "pick up where we left off," "load chat context," "continue from the last chat," or opens a chat referencing an earlier session. Where files can be written, handoff saves a structured context file and registers it in a master index; where they cannot, it prints the same structure as a block the user pastes into the next chat. Resume reads whichever form it finds, states what was loaded, then continues the work. Use this instead of summarising a chat back to the user in conversation.
optimize-tokens
Token optimization advisor for the user. Triggers in two situations: (1) When the user explicitly says "optimize tokens", "reduce tokens", "token efficient", or asks how to prompt better for efficiency. (2) When a request is detectably token-heavy - e.g., involves processing many files, large rewrites, multi-step research, full document generation, long context dumps - and a lighter approach could achieve the same result. Always prioritize quality over reduction. This skill is about eliminating waste, not restricting output. Use this skill proactively when you sense the request could be restructured to save significant tokens without quality loss.
renewal-risk-read
Produces a defensible read on whether an account will renew - the decision, the decider, the mechanism, the evidence, the dollars at stake and the play - rather than a colour on a dashboard. Trigger whenever the user asks "will they renew", "is this account at risk", "renewal risk", "churn risk", "should I be worried about this account", "what's the read on", "health check on", or names an account and a renewal date in the same breath. Also trigger when preparing for a forecast call, a risk review, or a QBR on an account whose renewal is inside two quarters. Use business-review-prep when the job is running the meeting; use this when the job is deciding what is true. The skill works from whatever evidence exists and states plainly what it could not check.
account-context
Captures the shared context every other customer success skill needs, once, so they stop asking for it. Trigger whenever the user says "account context", "set up account context", "set up the CS skills", "first time using these skills", "let me tell you about our product", "onboard me to these skills", or when any other skill in this library needs product, segment, contract or value-metric context that has not been established yet. Also trigger when the user says the skills keep asking the same questions, or that a skill's output felt generic. It interviews once, then writes a context document covering what the product does in the customer's words, how the segments differ, the contract shapes, the value metric the customer actually bought, what healthy usage looks like in this business, the go-to-market motion, and what customer success owns. Runs on whatever the user already knows and marks every gap as a gap rather than stalling.
business-review
Prepares a customer business review that earns the next meeting - the customer's goals first, value proved in their numbers, three to five themes, and an explicit ask - instead of a usage readout nobody asked for. Trigger whenever the user says "QBR", "EBR", "business review", "quarterly review", "exec review", "prep for my customer meeting", "build the deck for", "what should I present to", or names an account and an upcoming review in the same breath. Also trigger when they ask whether they should run a review at all. Use renewal-risk when the job is deciding whether the account will renew; this skill is for the meeting. It will tell the user when a business review is the wrong meeting to run.
call-prep
Prepares a customer call around the one thing it has to produce, rather than around what you plan to say. Trigger whenever the user says "call prep", "prep me for", "I have a call with", "meeting in an hour", "what should I ask", "what do I need to know before", "help me prepare for this call", "agenda for", "talking points for", or names a customer and an upcoming meeting in the same breath. Also trigger when they are walking into an account they have just inherited, or a call they are dreading. It names the outcome, works out who is really in the room, surfaces what changed on the customer's side, finds the landmine, writes the questions including the one they are avoiding, and sets the ask and the fallback ask. Use business-review when the meeting is a QBR or EBR, exec-conversation when the senior person is the point of the meeting, and hard-conversation when the job is delivering bad news. Runs on what the user knows and names what it could not check.
call-recap
Turns a recorded customer call into an honest read of it plus the full set of emails it generated - the recap and every follow-up - grouped by recipient, written in the user's voice and staged as drafts. Trigger whenever the user shares a call recording link from any meeting recorder, pastes a transcript, or points at a call, and asks what they should send, or says "recap email", "meeting recap", "write the follow-ups", "what do you think of this call", "emails from this call", "post-call emails", "who do I need to email after this", or names a customer and a call in the same breath. Also trigger when they forward a meeting summary and ask for anything written off the back of it. Recorder-agnostic: a pasted transcript alone still produces the full email set, and it names what it could not check rather than guessing. Prefer this skill over drafting emails directly - a call almost always generates more than one email, and the ones the user forgets are the expensive ones.
churn-postmortem
Works out why an account actually left, separating the reason the customer gave from the mechanism that caused it, and checks whether the loss was one of a correlated set. Trigger whenever the user says "churn postmortem", "why did we lose them", "post mortem", "churn analysis", "they did not renew", "we lost the account", "what went wrong with", "lessons learned", or names an account in the past tense. Also trigger when several accounts have been lost for the same stated reason, or before a churn review. It reconstructs the timeline, separates the date the account was lost from the date anyone noticed, identifies the earliest signal that was genuinely detectable at the time rather than obvious in hindsight, and asks whether the loss was winnable and when it stopped being so. Runs on whatever record survives and marks what could not be reconstructed.
exec-conversation
Prepares fifteen minutes with a senior person on the customer side who has no context, did not ask for the meeting, and will leave early. Trigger whenever the user says "exec conversation", "meeting their CFO", "meeting the VP", "C-level meeting", "executive sponsor meeting", "I have fifteen minutes with", "talking to my champion's boss", "exec sponsor", "senior stakeholder meeting", "how do I talk to an executive", or names a title two or more levels above their usual contact. Also trigger when a new executive has arrived on the customer side and is reviewing what their predecessor bought. It establishes why the meeting exists, what the executive is measured on, the first sentence, the single ask, the two questions worth their time, how to protect the champion, and the five-line follow-up. Use business-review when the meeting is a QBR, and hard-conversation when the point of the meeting is bad news.
hard-conversation
Scripts the customer conversation you are putting off: a price increase, a feature you will not build, a commitment you missed, or a failure that cost them money. Trigger whenever the user says "hard conversation", "difficult conversation", "how do I tell them", "I have to tell the customer", "price increase", "raising their price", "we are not building", "roadmap no", "we missed the deadline", "we slipped", "the outage", "how do I break this to", "they are going to be angry", "I have been putting this off", or describes bad news they owe a customer. Also trigger when they ask you to soften a message that is honestly bad. It works out what is true and what you can offer before a word is said, writes the opening two sentences, sets the concession ladder and the walk-away in advance, and drafts the written record for afterwards. Use email-critic once the record is drafted, and exec-conversation when the conversation has escalated above your contact.
health-read
Audits an account health score rather than reporting it, so the number can be trusted or discounted deliberately. Trigger whenever the user says "health score", "account health", "is this account healthy", "the score says green but", "health check", "why is this account red", "our health scores are wrong", "audit the health score", or asks what an account's health actually is. Also trigger when a green account has just churned, or when someone is deciding whether to act on a score. It separates what is measured from what is inferred, finds the inputs that are proxies wearing the clothes of evidence, checks whether the composite is averaging a growing signal against a dying one, and asks the question nobody asks: has this score ever been tested against accounts that actually left. Runs on whatever the user can describe about their scoring, and says plainly which parts of the read are unsupported.
renewal-risk
Produces a defensible read on whether an account will renew - the decision, the decider, the mechanism, the evidence, the dollars at stake and the play - rather than a colour on a dashboard. Trigger whenever the user asks "will they renew", "is this account at risk", "renewal risk", "churn risk", "should I be worried about this account", "what's the read on", "health check on", or names an account and a renewal date in the same breath. Also trigger when preparing for a forecast call, a risk review, or a QBR on an account whose renewal is inside two quarters. Use business-review when the job is running the meeting; use this when the job is deciding what is true. The skill works from whatever evidence exists and states plainly what it could not check.
stakeholder-map
Maps the people who decide an account's outcome by what they can do to it, not by their job titles. Trigger whenever the user says "stakeholder map", "who are the stakeholders", "relationship map", "who do I need to know", "who actually decides", "who signs", "map the account", "we are single-threaded", "my champion left", or asks who to call about a renewal. Also trigger when an account has gone quiet, when a new executive has arrived on the customer side, or before any first meeting with an inherited account. It sorts people by influence on the outcome rather than seniority, flags who has never actually been met, tests for single-threading, and tracks who is new, who has gone, and who used to respond and stopped. Runs on whatever the user knows and marks every gap as a gap.
escalation
Runs the first four hours of an account on fire: what to say before you know the answer, who to pull in, and what the customer actually wants, which is often not the fix. Trigger whenever the user says "escalation", "the account is escalating", "their VP is involved", "this has gone to their exec", "angry customer", "they are threatening to churn", "account on fire", "major incident with a customer", "they want a call today", "I need to escalate this internally", or describes a customer situation that has just moved above their usual contact. It separates the incident from the relationship damage, sets one owner and one cadence, decides who to pull in and when, and plans the repair step most teams skip. Use hard-conversation when you are the one delivering bad news that has not landed yet, and churn-postmortem when the account has already gone.
expansion-case
Builds the internal business case your champion has to carry without you in the room, rather than the pitch you would give. Trigger whenever the user says "expansion case", "business case", "upsell", "cross-sell", "expand the account", "they want to add seats", "second department", "justify the spend", "my champion needs to sell this internally", "build the case for", "how do I get budget for", or names an account and additional scope in the same breath. Also trigger when a customer asks what it would take to roll out further. It anchors on a problem their leadership already agreed exists, finds where the budget actually comes from, sizes the ask so it can survive one meeting, and answers the objections their finance team will raise before they raise them. Use business-review when the meeting is the value review, and renewal-negotiation when scope and price are being agreed together.
offboarding
Runs a departure well: the data handover, the honest exit conversation, and the door left open. Trigger whenever the user says "offboarding", "they are leaving", "they gave notice", "churn process", "wind down", "transition them off", "they are not renewing", "how do I hand this back", "exit conversation", or names an account and a termination in the same breath. It separates what you owe them contractually from what you owe them professionally, gets the exit interview that nobody asks for, and treats the departing champion as a future pipeline event rather than a closed record. Use renewal-risk while the decision is still open and a save is possible, and churn-postmortem afterwards for the internal analysis of why it happened.
renewal-negotiation
Prepares the renewal conversation itself: what you will concede, what you will not, what the walk-away is, and what they are going to ask for. Trigger whenever the user says "renewal negotiation", "they want a discount", "renewal conversation", "they are asking for a better price", "procurement is involved", "negotiating the renewal", "they want to cut seats", "how much should I give", "what do I concede", "they mentioned a competitor", or names a renewal and a number in the same breath. Also trigger when a customer asks for utilisation data, seat counts or contract copies ahead of a renewal, which is negotiation preparation rather than admin. Use renewal-risk when the job is deciding whether they will renew at all, and hard-conversation when the job is delivering a price increase they have not heard yet. This is for the conversation where both sides know a number is being agreed.
account-plan
Writes the durable per-account plan you get measured against later, aimed at someone picking the account up in month four who needs to know what was promised and by whom. Trigger whenever the user says "account plan", "strategic account plan", "plan for this account", "what is our plan for", "write up the account strategy", "twelve month plan", "growth plan for the account", or is asked to produce a plan for a named account. It writes the objective in the customer's words with a measure attached, names owners on both sides, attaches triggers to the risks, and refuses to plan more activity than anyone will do. Use onboarding-plan for the first ninety days, account-context for the business-wide substrate every skill reads, and book-triage for which accounts earn a plan at all.
account-research
Archaeology on an account you inherited or are meeting cold: what was sold, by whom, on what promise, what has happened since, and which of it nobody has questioned in two years. Trigger whenever the user says "account research", "I just inherited this account", "brief me on", "what do I need to know about", "first meeting with", "taking over the account", "get me up to speed on", "who are these people", "why did they buy", "what was promised", or names an account they have not worked before. Also trigger before a first call on a transferred book, and when an account's history stops explaining its present. It separates what is documented from what is folklore, finds the original promise the renewal will be judged against, and produces a list of what must be asked because it cannot be found. Use the sales plugin's own research skill when assessing a prospect you have no relationship with; this one is for an account that already exists.
advocacy-ask
Works out whether to ask a customer for advocacy, whom, when, what exactly to ask for, and what you owe them back. Trigger whenever the user says "advocacy", "reference", "reference call", "case study", "testimonial", "G2 review", "referral", "can we use them as a logo", "sales wants a reference", "who can we ask", "ask for a review", or is asked to produce a customer willing to vouch. It times the ask to realised value rather than to renewal, picks the person who benefited rather than the person who signed, keeps the request small enough to say yes to, surfaces the approval path that kills most case studies, and tracks reference fatigue so the same three accounts are not asked eleven times. Use business-review when the value that justifies the ask has not been established yet.
book-triage
Decides which accounts get your attention this week, against a book too big to cover evenly, and writes down which ones deliberately do not. Trigger whenever the user says "book triage", "which accounts should I focus on", "prioritise my book", "I have too many accounts", "where should my time go", "who needs me this week", "I cannot cover them all", "my book is too big", "triage my accounts", or describes being spread thin across a portfolio. It sorts by what changed and what can still be influenced rather than by size or by health colour, flags the accounts nobody has logged a touch on, and forces an explicit not-this-week list. Use weekly-plan to turn the resulting list into hours, and renewal-risk for the depth read on any one account it surfaces.
coaching
Runs the one-to-one, the call review and the development conversation so behaviour changes rather than gets described. Trigger whenever the user says "coaching", "coach my team", "call review", "one to one", "1:1", "development conversation", "my CSM is struggling", "how do I give feedback on this call", "performance conversation", "they are not improving", "skill gap on my team", or is preparing to give a colleague feedback on how they work. It diagnoses whether the problem is skill, will, knowledge or environment before choosing an approach, works on one behaviour at a time, asks for self-assessment first, and rehearses rather than advises. Use portfolio-review for the meeting where reads are calibrated, which is not a coaching meeting and should not host one.
coverage-model
Designs who gets a named CSM, who gets pooled, who gets digital only, and states what breaks at each line. Trigger whenever the user says "coverage model", "segmentation", "touch model", "CSM ratio", "how many accounts per CSM", "high touch low touch", "tech touch", "digital CS", "scaled CS", "pooled model", "we cannot cover the long tail", "do we need more headcount", or is designing or defending how a team is deployed across a book. It segments by what accounts need rather than only by what they pay, treats the ratio as an output rather than an input, names what each tier will not get, and tests the model against the accounts that actually churned. Use book-triage for working inside a coverage model that already exists, and renewal-forecast for what the model implies about the number.
csql-motion
Designs how customer success generates and hands off qualified expansion leads without damaging the relationship that produced them. Trigger whenever the user says "CSQL", "customer success qualified lead", "CS sourced pipeline", "should CS sell", "hand leads to sales", "expansion motion", "CS to sales handoff", "how do we count CS influence", "attribution between CS and sales", or is designing or fixing how expansion signals move from customer success to a sales team. It defines what actually qualifies as a signal rather than a hunch, shapes the handoff as a warm introduction rather than a queued lead, settles attribution before the first one is passed, and names the kill criteria. Use expansion-case for the individual business case, and coverage-model for whether the team has capacity for this at all.
customer-update
Writes the proactive message nobody wants to send: an incident, a delay, a deprecation, a price change, planned maintenance, or a change of CSM. Trigger whenever the user says "customer update", "notify customers", "we need to tell them", "announcement to customers", "we are deprecating", "end of life", "maintenance window", "outage notice", "I am handing over my accounts", "changing CSM", "tell them about the delay", or describes news that has to reach a list of customers rather than one person. It segments by impact rather than by mailing list, leads with what changes for them, says plainly whether action is needed, and writes to survive a forward to their executive and their legal team. Use hard-conversation when the news is going to one account by voice, escalation when something is already on fire, and email-critic once a draft exists.
handoff
Runs a handover so the receiving side can actually take it: sales to customer success, customer success to support, or one CSM to another. Trigger whenever the user says "handoff", "handover", "handing over my accounts", "sales to CS handover", "transition the account", "I am leaving and need to hand over", "onboarding a new CSM", "what do I need to pass on", or names an account changing owner. It defines completeness from the receiving side rather than the leaving side, forces out the things that never make it into a system, sets an acceptance step with a date, and separates the internal transfer from what the customer is told. Use customer-update for the message to the customer, and account-research when the handover never happened and the history has to be reconstructed.
internal-escalation
Gets your own company to act, with the ask and the evidence shaped for the people you are asking rather than for you. Trigger whenever the user says "internal escalation", "escalate internally", "I need engineering to look at this", "get leadership involved", "how do I get this prioritised", "nobody is picking this up", "I need an exception", "raise this with my manager", "who do I go to", or describes needing something from another team on a deadline. It works out who can actually decide, states a specific ask rather than a request for attention, refuses to inflate severity, and plans the follow-through. Use escalation when the customer is the one escalating and the first four hours are customer-facing, and product-feedback when the ask is roadmap consideration rather than action now.
nrr-narrative
Turns net and gross revenue retention into a story a board will follow, including what the headline number hides. Trigger whenever the user says "NRR", "net revenue retention", "GRR", "gross retention", "retention narrative", "board update on retention", "explain our retention numbers", "why did NRR drop", "retention story", "prepare the retention slide", or is presenting a retention number to a board, an investor or an executive team. It decomposes the ratio into expansion, price, contraction and churn, insists gross retention appears alongside net, distinguishes cohort from blended, and answers the only question a board is actually asking, which is whether the number is repeatable. Use renewal-forecast for the forward number and portfolio-review for the account reads underneath it.
one-pager
Writes the summary a sponsor forwards to their boss without editing it, for the person who was not in the room and has forty seconds. Trigger whenever the user says "one pager", "one-pager", "exec summary", "executive summary", "summarise this for their leadership", "something they can forward", "my champion needs to share this", "brief for their boss", "leave-behind", "recap they can pass on", or asks for a short document aimed at someone they will never speak to. It leads with the conclusion and the ask, uses their vocabulary rather than yours, carries no logo, and is tested by whether it survives being forwarded with no covering note. Use expansion-case when the document is specifically a budget case for more scope, business-review when it is the meeting itself, and email-critic on a draft that already exists.
portfolio-review
Runs the meeting where you review your team's account reads rather than their accounts, to find out which reads are wrong before they reach a forecast. Trigger whenever the user says "portfolio review", "account review with my team", "review my team's accounts", "pipeline review for renewals", "how do I run a forecast call", "my team's reads are unreliable", "someone is sandbagging", "everything is green and I do not believe it", or is preparing a recurring review of a team's book. It samples rather than covers, asks the four questions that expose a thin read, catches sandbagging and happy ears by their tells, and keeps the meeting from turning into account problem-solving. Use renewal-forecast for the number itself, and coaching for the individual development conversation this meeting will surface.
product-feedback
Turns customer noise into something the product team will actually act on: the job to be done rather than the requested feature, how many accounts have it, what it is worth, and what happens if nothing changes. Trigger whenever the user says "product feedback", "feature request", "the customer wants", "raise this with product", "log this request", "they are asking for", "submit this to the roadmap", "product gap", "how do I get this built", or forwards a customer request expecting it to reach engineering. Also trigger when the user asks what happened to a request they raised, or says product ignores their input. It separates a request from a bug, a gap and a misunderstanding, refuses to inflate the revenue at stake, and closes the loop back to the customer including on a no. Use internal-escalation when the ask is urgent attention rather than roadmap consideration.
renewal-forecast
Produces a renewal and expansion forecast in dollars with a stated confidence, with contraction sized separately and correlated risks named as one bet rather than thirty. Trigger whenever the user says "renewal forecast", "forecast the quarter", "what will we renew", "gross retention forecast", "commit number", "roll up my team's renewals", "forecast call", "what is the risk to the number", or is preparing a retention number for finance or a board. It sets evidence-based entry criteria for each category, separates timing slip from loss, pulls auto-renewals out of the judgement pool, and tracks per-forecaster accuracy so the number stops being a personality test. Use renewal-risk for the read on any single account, and portfolio-review for the meeting where the reads get challenged.
weekly-plan
Shapes the week around the accounts that move rather than around the calendar that filled itself. Trigger whenever the user says "weekly plan", "plan my week", "how should I spend this week", "my calendar is full", "I have no time for proactive work", "plan Monday", "week ahead", "I am drowning", "everything is reactive", or describes a week where meetings have consumed the time. It starts from what has to be true by Friday, protects one block for the work that has no deadline, batches the reactive load, names the meetings to decline or shorten, and closes the week on what actually moved. Use book-triage first to decide which accounts deserve the time, since that is a different question from how the hours are arranged.
email-critic
Stress-tests a customer email the user has already drafted and returns a straight verdict plus a tightened version, checked against the source transcript, the account plan and their voice principles rather than in a vacuum. Trigger whenever the user pastes or points at a draft email and asks any of: "is this good", "would you send this", "review this email", "critique this", "tighten this", "make this better", "does this sound right", "too long?", "what would you change", or shares a draft with no instruction at all - a bare draft is a request for a read on it. Also trigger when they say an email "feels off" or ask how a customer will take it. Use this for drafts that already exist; use call-recap when the input is a recording and no draft has been written yet.
onboarding-plan
Builds a customer onboarding plan aimed at a result the customer can point to, not a checklist your team can close - with success criteria carrying a baseline, named owners on both sides, and the early signals that predict a bad year. Trigger whenever the user says "onboarding plan", "kickoff", "new customer", "just closed", "first 90 days", "implementation plan", "handover from sales", "success plan", or names an account that has recently signed. Also trigger when they ask why an onboarding is stalling or whether a customer is really live. The plan it produces becomes the evaluation frame for the renewal, so it is written to be measured against later.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.