All authors
Claude Skills by polar-bear-org
github.com/polar-bear-org1,179 skills0 installs67 views
- Price Pricing ReviewRuns a quarterly pricing review from your own records, with the floor re-run, margins by client and offer, AI savings and AI costs since last quarter, a fee leakage waterfall, deals won and lost on price, discount requests, and three decisions with owners. Use for "run price-pricing-review", "quarterly pricing review", "where is my fee leaking", "review my prices this quarter", "pricing health check", "am I still charging enough", "fee leakage", part of the Pricing Under AI Pressure Pack by P...Votes: 0GitHub stars: 2
- Price Productized ServiceTurns the service you deliver most often into one fixed offer, producing a Productized Service Sheet with the name, who it is for, the outcome, scope in and out, timeline, a fixed price checked against your own floor, and what triggers a change. Use for "run price-productized-service", "productise my service", "turn my project into a fixed offer", "stop custom quoting every job", "fixed price package", "make a standard offer", "price stops following the hours", part of the Pricing Under AI Pr...Votes: 0GitHub stars: 2
- Price Retainer RedesignRedesigns an hours-based retainer client by client, setting what the retainer buys against what the client values, the options (outcome retainer, capacity with an output floor, fixed-fee 90-day engagement, keep as is) and a conversation outline. Use for "run price-retainer-redesign", "my retainer is sold as hours", "AI made the hours shrink", "should I kill the retainer", "move a retainer to outcomes", "retainer redesign", "the client did the maths on AI hours", "change how a retainer is pric...Votes: 0GitHub stars: 2
- Price Service BlueprintMaps one offer from the client's side, producing a Service Blueprint with frontstage and backstage lanes, every AI step and the role who checks and decides, the line of visibility, failure points, and a client-facing version. Use for "run price-service-blueprint", "service blueprint", "show the client what AI does", "map how my offer is delivered", "where does AI work in my process", "explain my AI use to a client", "frontstage backstage", part of the Pricing Under AI Pressure Pack by Polar B...Votes: 0GitHub stars: 2
- Price Statement Of WorkWrites a Statement of Work with the outcome, deliverables, testable acceptance criteria, the assumptions the price rests on, revision rounds, change triggers, the AI use and client data lines and plain commercial terms, with anything beyond plain terms marked for an adviser. Use for "run price-statement-of-work", "write a statement of work", "SOW for this project", "turn the proposal into a SOW", "stop scope creep", "acceptance criteria for the deliverables", "how many revision rounds", "AI l...Votes: 0GitHub stars: 2
- Price Three Option ProposalWrites the price section of a proposal with one to three real options that differ in scope and outcome, the fee by phase from your own numbers, the assumptions the price rests on, plain terms and dated next steps, with no decoy, anchor or deadline. Use for "run price-three-option-proposal", "give the client options", "good better best proposal", "write the fee section", "how do I present the price", "stop sending one number", "build the options for this client", part of the Pricing Under AI P...Votes: 0GitHub stars: 2
- Price Value Based PricingBuilds a value-based pricing worksheet from the client's stated value drivers, showing the value range in their numbers, your internal cost floor, the gap between them and the price you set with a one-line reason. Use for "run price-value-based-pricing", "price this on value", "move from hours to value", "what should I charge for this outcome", "value price worksheet", "is my price defensible", "price above my day rate", part of the Pricing Under AI Pressure Pack by Polar Bear.Votes: 0GitHub stars: 2
- Price Value Discovery QuestionsPrepares a value discovery question set for one client call, with open questions on the outcome they want, what it is worth in their own numbers, the cost of doing nothing and their next-best alternative (their own AI included), plus an answer grid left blank for the client's words. Use for "run price-value-discovery-questions", "what is this worth to the client", "value discovery call", "questions before I price on value", "find out what the outcome is worth", "how do I ask about budget with...Votes: 0GitHub stars: 2
- Aipm Agent SpecWrites an Agent Spec with the goal and done-state, allowed tools and permissions, stop conditions and a spend budget per session, the approval points carried over from the human-in-the-loop design, and the list of actions the agent must never take alone. Use for "run aipm-agent-spec", "agent spec", "write the limits for our agent", "agent permissions", "where should the agent stop", "agent guardrails", "excessive agency", "spend cap for the agent", part of the Claude for AI Product Managers P...Votes: 0GitHub stars: 2
- Aipm Ai Failure ModesBuilds an AI Failure Modes Map with the failure list per output type, the cost of a false yes and a false no to the user, severity and detection ratings, a graceful failure per mode and a tolerable error rate left blank for a named person. Use for "run aipm-ai-failure-modes", "AI FMEA", "which AI mistakes matter", "leaders expect it to be right every time", "false positives vs false negatives", "graceful failure", "what happens when the AI is wrong", "AI error budget", part of the Claude for ...Votes: 0GitHub stars: 2
- Aipm Ai Impact AssessmentDrafts an AI Impact Assessment covering who is affected and how, intended use and foreseeable misuse, data used, human oversight, mitigations and residual risk with a named owner, with every legal point marked as a question for an adviser. Use for "run aipm-ai-impact-assessment", "AI impact assessment", "algorithmic impact assessment", "the customer wants an impact assessment", "foreseeable misuse of our AI feature", "who does this feature affect", "residual risk sign-off", part of the Claude...Votes: 0GitHub stars: 2
- Aipm Ai Incident ResponseWrites an AI Incident Response Plan for a wrong answer or action that reached customers, with severity levels for AI errors, containment (fallback, switch off, human takeover), a customer correction, an evidence timeline, the fix into the golden dataset and a blameless review. Use for "run aipm-ai-incident-response", "our AI told a customer something wrong", "AI incident playbook", "the chatbot made a promise we cannot keep", "switch off the AI feature", "AI postmortem", "contain an AI failur...Votes: 0GitHub stars: 2
- Aipm Ai Launch ChecklistBuilds an AI Launch Checklist with an owner, a status and an evidence link per line, covering evals passed as run, guardrails on, fallback tested, monitoring and alerts, feedback capture live, support briefed, disclosure in place and rollback rehearsed. Use for "run aipm-ai-launch-checklist", "AI launch checklist", "go-live checklist for an AI feature", "are we ready to launch", "launch readiness review", "what did we forget before launch", "pre-launch checks for our assistant", part of the C...Votes: 0GitHub stars: 2
- Aipm Ai Model SelectionBuilds an AI Model Selection Plan with a side-by-side test plan on 20 to 50 real inputs, a quality, latency and cost table per model tier, a pick per task with the evidence row behind it and a re-check date. Use for "run aipm-ai-model-selection", "which model tier should we use", "justify the model choice", "compare models side by side", "cheaper model or stronger model", "model bake-off", "model cost per task", "pick a model for each step", part of the Claude for AI Product Managers Pack by ...Votes: 0GitHub stars: 2
- Aipm Ai PrdDrafts an AI PRD with the problem and its evidence, the inputs the model sees, the outputs, a three-line behavior summary, failure handling and fallbacks, data needs, a release bar with blank targets and open questions with owners. Use for "run aipm-ai-prd", "write a PRD for an AI feature", "AI feature spec", "spec for our copilot", "PRD template for an LLM feature", "nobody can test this spec", "turn the prototype into a spec", part of the Claude for AI Product Managers Pack by Polar Bear.Votes: 0GitHub stars: 2
- Aipm Ai Prototype BriefWrites an AI Prototype Brief with what the demo tests, a pass line set in advance, a cherry-picked input check, what the demo does not prove and a gap-to-production list with an owner per line. Use for "run aipm-ai-prototype-brief", "leadership thinks the demo is the product", "AI demo to production", "test card for an AI prototype", "what does this AI demo prove", "gap to production", "the demo worked, can we ship", "AI proof of concept plan", part of the Claude for AI Product Managers Pack ...Votes: 0GitHub stars: 2
- Aipm Ai Risk RegisterBuilds an AI Risk Register with each risk worded as cause, event and effect, mapped to the NIST Map, Measure and Manage functions, with an owner, an early-warning trigger, a response and the regulatory questions passed on to legal. Use for "run aipm-ai-risk-register", "AI risk register", "NIST AI RMF risks", "legal and security want our AI risks", "turn these worries into risks", "risk log for an AI feature", "who owns each AI risk", part of the Claude for AI Product Managers Pack by Polar Bear.Votes: 0GitHub stars: 2
- Aipm Ai Success CriteriaWrites AI Success Criteria for a model feature, one specific and measurable criterion per dimension (task fidelity, consistency, tone, privacy, context use, latency, cost), with today's baseline, a target left blank for a named person and how each will be measured. Use for "run aipm-ai-success-criteria", "define success criteria for our AI feature", "what does good mean for this model", "make it good is not a spec", "acceptance criteria for an LLM", "release bar for the assistant", "how do we...Votes: 0GitHub stars: 2
- Aipm Ai Use Case CanvasFills an AI Use Case Canvas for one decision or task, with the canvas fields, a simpler-fix check, a data check and a verdict a named person decides. Use for "run aipm-ai-use-case-canvas", "AI canvas", "do we even need AI for this", "leadership wants an AI feature", "is this a good AI use case", "AI use case template", "should this be rules or a model", "which decision does the AI improve", part of the Claude for AI Product Managers Pack by Polar Bear.Votes: 0GitHub stars: 2
- Aipm Ai Ux ReviewRuns an AI UX Review that checks the 18 human-AI interaction guidelines by phase, records what the AI disclosure shows, traces the correction and human handoff paths and lists fixes in the order you set. Use for "run aipm-ai-ux-review", "AI UX review", "human-AI interaction guidelines", "users keep rephrasing", "what happens when the assistant is wrong", "check our AI disclosure", "review the chat experience", "users swear at the bot", part of the Claude for AI Product Managers Pack by Polar ...Votes: 0GitHub stars: 2
- Aipm Behavior ContractWrites an AI Behavior Contract of must, must never and when-unsure lines, each as a Given-When-Then scenario with a pass rate over repeated runs set by a named person, a guardrail list for what the prompt alone cannot enforce, and a tag to the eval that checks each line. Use for "run aipm-behavior-contract", "behavior spec for our AI", "must never rules for the assistant", "Given When Then for an LLM", "turn helpful and safe into tests", "what should the bot refuse", "guardrails spec", part o...Votes: 0GitHub stars: 2
- Aipm Context EngineeringBuilds a Context Engineering Brief with a register of knowledge sources and their owners, freshness rules, a leave-out list, retrieval spot checks on real questions and a context budget. Use for "run aipm-context-engineering", "context engineering", "which documents should the model read", "the AI answers from stale docs", "knowledge base for our AI feature", "RAG sources", "retrieval is pulling the wrong document", part of the Claude for AI Product Managers Pack by Polar Bear.Votes: 0GitHub stars: 2
- Aipm Data Privacy BriefDrafts an AI Data Privacy Brief with a data flow map from user to model to logs, the personal data in prompts and context with minimisation options, retention and processing region per hop, the vendor terms to read and the questions for legal with the facts attached. Use for "run aipm-data-privacy-brief", "what user data reaches the model", "data flow for our AI feature", "privacy review for an LLM feature", "legal asked about the model's data", "personal data in prompts", "prepare for the pr...Votes: 0GitHub stars: 2
- Aipm Error AnalysisReads 50 to 100 real AI outputs with you and turns them into an error analysis log with open codes, failure types grouped by axial coding, counts per type and the three to fix first. Use for "run aipm-error-analysis", "error analysis", "what is actually going wrong with our AI", "read our transcripts", "build a failure taxonomy", "code these LLM outputs", "our eval scores mean nothing", "where do I start with evals", part of the Claude for AI Product Managers Pack by Polar Bear.Votes: 0GitHub stars: 2
- Aipm Eval PlanTurns the AI success criteria into an eval plan with capability and regression suites, when each runs, what blocks a release and the named owner of quality. Use for "run aipm-eval-plan", "eval plan", "AI eval strategy", "who owns quality", "when should evals run", "regression suite", "capability evals", "what blocks an AI release", part of the Claude for AI Product Managers Pack by Polar Bear.Votes: 0GitHub stars: 2
- Aipm Eval RubricWrites an eval rubric with one binary pass or fail check per failure type, the grader for each check (code, model or human), real pass and fail examples, and which checks block a release. Use for "run aipm-eval-rubric", "eval rubric", "pass fail criteria for our AI", "how should we grade outputs", "our 1 to 5 scores mean nothing", "code grader or LLM grader", "which failures block a release", part of the Claude for AI Product Managers Pack by Polar Bear.Votes: 0GitHub stars: 2
- Aipm Exec BriefWrites a one-page AI Exec Brief, bottom line first, covering what the feature does, how often it is wrong by severity, what a wrong answer costs, how it is caught, run cost and the decision asked. Use for "run aipm-exec-brief", "how accurate is it", "explain the AI to leadership", "one-pager for execs on the AI feature", "go or no-go memo for the AI", "board update on our AI feature", "bottom line up front", "leaders want one accuracy number", part of the Claude for AI Product Managers Pack b...Votes: 0GitHub stars: 2
- Aipm Feature CardCompiles an AI Feature Card with intended and out-of-scope use, data used, eval results as run with dates, known limits, disclosures, an owner and a review date. Use for "run aipm-feature-card", "model card for our feature", "what does the AI feature do and where does it fail", "AI fact sheet for sales", "document the AI feature for legal", "known limitations of the AI", "AI feature documentation", "one reference for support on the AI", part of the Claude for AI Product Managers Pack by Polar...Votes: 0GitHub stars: 2
- Aipm Feedback SignalsDesigns an AI Feedback Signal Map with the signals an AI feature should log (accept, edit, retry, rephrase, abandon, escalate, rating), what each likely means, the log spec, a weekly readout and the triggers that send a conversation to review. Use for "run aipm-feedback-signals", "users never rate our AI answers", "implicit feedback for an AI feature", "what should we log for our assistant", "thumbs up thumbs down is not enough", "AI feedback loop design", "which conversations should we revie...Votes: 0GitHub stars: 2
- Aipm Golden DatasetBuilds a golden dataset of 20 to 50 real cases with expected outcomes, coverage by failure type and edge case, source and version per case, and add-and-retire rules. Use for "run aipm-golden-dataset", "golden dataset", "build an eval set", "test cases for our AI feature", "did the new prompt actually help", "regression set", "capability set", "turn these failures into tests", part of the Claude for AI Product Managers Pack by Polar Bear.Votes: 0GitHub stars: 2
- Aipm Human In The LoopDesigns Human-in-the-Loop for an AI feature or agent, naming which steps a person approves, edits or takes over, the trigger for each (uncertainty, risk, amount, user request), the handoff message and context passed, a response time staff can actually meet and what is logged. Use for "run aipm-human-in-the-loop", "where should a human approve", "human in the loop design", "AI handoff to a person", "approval step for the agent", "escalation to a human", "when should the bot hand off", part of ...Votes: 0GitHub stars: 2
- Aipm Launch GatesDrafts AI Launch Gates with release stages (internal, small share, wider, all), the eval and live numbers that must hold at each, kill criteria set in advance, the rollback path and the one named person who signs each gate. Use for "run aipm-launch-gates", "AI launch gates", "staged rollout for an AI feature", "canary release plan", "kill criteria for our AI launch", "what would stop the launch", "rollout stages and sign-off", part of the Claude for AI Product Managers Pack by Polar Bear.Votes: 0GitHub stars: 2
- Aipm Legal QuestionsPrepares Questions for Legal, grouped by topic (data, disclosure, liability, output ownership, AI Act category, vendor terms, records), each with the facts legal needs attached and the decision it unblocks, and never answers a legal question. Use for "run aipm-legal-questions", "questions for legal", "prepare for the legal review", "what do I ask legal about our AI feature", "legal sign-off for AI", "what does legal need from me", "AI Act questions for our lawyer", part of the Claude for AI P...Votes: 0GitHub stars: 2
- Aipm Llm JudgeWrites an LLM-as-a-judge prompt for one failure type and the check that proves it, a labelled agreement set, agreement with human labels on a held-out split, and bias checks for position, length and self-preference. Use for "run aipm-llm-judge", "LLM as a judge", "judge prompt", "automate our eval grading", "can we trust the LLM grader", "model-graded evals", "validate our judge against humans", part of the Claude for AI Product Managers Pack by Polar Bear.Votes: 0GitHub stars: 2
- Aipm Model MigrationWrites a Model Migration Plan for moving off a model with a retirement date, with the deadline from the deprecation notice, breaking changes to check, an eval rerun per failure type, the cost difference, behaviour diffs to read and a rollout with fallback. Use for "run aipm-model-migration", "our model is being retired", "deprecation notice for our model", "migrate to the replacement model", "model upgrade plan", "re-test before the retirement date", "what breaks when we switch models", part ...Votes: 0GitHub stars: 2
- Aipm Prompt Regression TestRuns a Prompt Regression Test on a prompt, context or setting change, with a change note, the cases to re-run, before and after results per failure type and a ship or hold recommendation for a named person. Use for "run aipm-prompt-regression-test", "did this prompt change break anything", "regression test a prompt edit", "before and after eval for our prompt", "the fix broke another case", "check the new system prompt", "ship or hold this prompt", part of the Claude for AI Product Managers P...Votes: 0GitHub stars: 2
- Aipm Quality ReviewRuns a Weekly AI Quality Review on live transcripts, with a sample plan, review notes against the failure taxonomy, new failure types, cases added to the golden dataset and decisions with owners. Use for "run aipm-quality-review", "weekly AI quality review", "read our AI transcripts", "it worked for weeks then broke", "review production conversations", "transcript review for our assistant", "who reads the transcripts", "AI quality check this week", part of the Claude for AI Product Managers P...Votes: 0GitHub stars: 2
- Aipm Red Team PlanDrafts an AI Red Teaming Plan with attack cases by risk class (prompt injection, data leak, excessive agency, system prompt leak, misinformation, runaway cost), who runs each one, a pass line per class and the fixes owed before launch. Use for "run aipm-red-team-plan", "red team our AI feature", "prompt injection test plan", "the agent reads emails from strangers", "OWASP LLM top 10 checklist", "security test for our agent", "can someone hijack the assistant", "attack cases before launch", pa...Votes: 0GitHub stars: 2
- Aipm Synthetic Test DataGenerates synthetic test cases only for the gaps a real golden dataset cannot cover, each marked synthetic, checked by a person against real cases and reported apart from the headline score. Use for "run aipm-synthetic-test-data", "synthetic test data", "generate edge cases", "we do not have enough test cases", "test cases for rare inputs", "fake data for evals", "cover other languages in our evals", part of the Claude for AI Product Managers Pack by Polar Bear.Votes: 0GitHub stars: 2
- Aipm System PromptDrafts a System Prompt Brief with the role, audience, task, rules, examples, output format, refusals and handoffs, plus a line-by-line critique of the current prompt against the behavior contract. Use for "run aipm-system-prompt", "write the system prompt", "clean up our prompt", "system prompt template", "which line of the prompt does what", "the prompt grew by patches", "review my system prompt", "rewrite the prompt for our AI feature", part of the Claude for AI Product Managers Pack by Pol...Votes: 0GitHub stars: 2
- Aipm Tool DescriptionsWrites Tool Descriptions for an agent with each tool's name, purpose, inputs, outputs and error messages, a namespacing scheme, an overlap check between tools and three realistic test tasks. Use for "run aipm-tool-descriptions", "write tool descriptions", "the agent picks the wrong tool", "tool definitions for our agent", "MCP tool descriptions", "name our agent tools", "the agent misreads what the tool returns", part of the Claude for AI Product Managers Pack by Polar Bear.Votes: 0GitHub stars: 2
- Aipm Unit EconomicsBuilds an AI Unit Economics Model with cost per call, per task and per successful outcome (retries and context included), a heavy-user scenario, caching and batch levers and a comparison with the current way of doing the task. Use for "run aipm-unit-economics", "cost per task", "cost per successful outcome", "what does each AI answer cost us", "finance wants to stop the feature", "token cost model", "heavy users are eating the margin", "is the AI cheaper than a person", part of the Claude for...Votes: 0GitHub stars: 2
- Aipm Usage And Pricing TestRuns an AI Usage and Pricing Test that measures calls, tokens and retries per task on a small set of real tasks, estimates monthly usage at light, normal and heavy use and tests price options against those estimates, as an estimate to test and never pricing advice. Use for "run aipm-usage-and-pricing-test", "what will this feature cost to run", "estimate AI usage before launch", "seat or usage pricing for AI", "credits pricing test", "how many tokens per task", "heavy users and flat pricing",...Votes: 0GitHub stars: 2
- Aipm Workflow Or AgentWrites a Workflow or Agent Decision comparing the candidate patterns from a single call to an autonomous agent, with cost, latency and failure trade-offs, the simplest pattern that passes and the trigger that would justify the next step up. Use for "run aipm-workflow-or-agent", "do we need an agent", "workflow vs agent", "agent or prompt chain", "agentic architecture choice", "the team wants an agent", "simplest AI pattern", "router or orchestrator", part of the Claude for AI Product Managers...Votes: 0GitHub stars: 2
- Flink Ai Tells CheckReads a draft against your Personal Voice Guide and produces an AI Tells Check, with tells flagged by type (content, language, style), a line by line read-aloud test and a suggested cut for each flag, never a rewrite. Use for "run flink-ai-tells-check", "does this sound like AI", "check my draft for AI tells", "does this sound like me", "flag the generic bits", "read this against my voice guide", "make it sound less generated", part of the Claude Playbook for Authentic LinkedIn Presence Pack ...Votes: 0GitHub stars: 2
- Flink Ai Use StatementWrites your AI Use Statement, how you actually use Claude in your writing, in your own words as one line and one paragraph, checked against policy, audience, context, expectations and degree of use, and never hiding AI use. Use for "run flink-ai-use-statement", "did AI write this", "how do I disclose AI use", "should I say I use Claude", "AI disclosure for my profile", "honest answer about AI in my posts", "write my AI use line", part of the Claude Playbook for Authentic LinkedIn Presence Pac...Votes: 0GitHub stars: 2
- Flink Buying Situations MapMaps the moments a buyer starts needing your kind of help, marks which ones you can speak to from real work, and gives one post theme per situation plus the ones you leave alone. Use for "run flink-buying-situations-map", "buying situations", "category entry points for me", "what should my posts be about", "post themes", "be remembered when the need comes", "content pillars", part of the Claude Playbook for Authentic LinkedIn Presence Pack by Polar Bear.Votes: 0GitHub stars: 2
- Flink Claim CheckTraces every story, client mention, number and quote in a draft to your own source and produces a Claim and Permission Check, with a claims table, client permission for this channel recorded, a confidential sweep and a do-not-claim list. Use for "run flink-claim-check", "check my claims", "can I say this about a client", "is this number safe to post", "check permission before I post", "fact check my LinkedIn post", "what should I not claim", part of the Claude Playbook for Authentic LinkedIn ...Votes: 0GitHub stars: 2
- Flink Client Questions LogBuilds a Client Questions Log from the threads and call notes you choose, with each question as asked, the question behind it, client details removed, and which ones deserve a public answer. Use for "run flink-client-questions-log", "what do my clients keep asking", "turn client questions into posts", "I answer the same question every call", "pull the questions from my calls", "log questions from my inbox", part of the Claude Playbook for Authentic LinkedIn Presence Pack by Polar Bear.Votes: 0GitHub stars: 2
- Flink Connection RequestPrepares Connection Request Notes, one short note per person you actually met or talked with, carrying the real context (the event, the comment, the shared client problem) and no pitch, for a small run you send by hand. Use for "run flink-connection-request", "connection request note", "I met people this week", "what do I write when I connect", "a blank request will be ignored", "notes for people I met at the event", "connect with someone from a comment thread", part of the Claude Playbook fo...Votes: 0GitHub stars: 2