Product & Planning

asiaostrich Bundle

[UDS] Write user stories and requirements that satisfy the INVEST criteria. Use when: turning a feature idea into a user story, defining testable acceptance criteria, checking a backlog item for quality. Not for: full specification documents with design and delta operations — use /sdd; deciding whether the idea is right at all — use /brainstorm. Keywords: requirement, user story, INVEST, acceptance criteria, backlog refinement, 需求, 使用者故事, 驗收條件.

jarle Skill

Learn how Bun's test runner discovers and filters test files in your project

crestapps Bundle

Skill for configuring localization and multi-language support in Orchard Core. Covers culture settings, content localization, PO file contexts and discovery locations, IStringLocalizer, the Liquid t filter, and the admin culture picker. Use this skill when requests mention Orchard Core Localization, Configure Localization and Multi-Language Support, Enabling Localization Features, Localization Settings via Recipe, PO File Format, PO File Location Convention, or closely related Orchard Core implementation, setup, extension, or troubleshooting work.

bookforge-ai Skill

Orchestrate the full customer discovery process — before, during, and after customer conversations — to systematically validate a business idea. This is the hub skill that sequences all other customer-discovery skills. Use this skill whenever the user wants to run customer discovery end-to-end, needs a step-by-step process for validating a product idea through customer conversations, wants to start customer discovery from scratch, wants to know what to do before and after customer meetings, needs a discovery status dashboard showing validation progress, suspects their discovery process is broken or unproductive, wants to diagnose whether they are just going through the motions, needs a customer development or lean validation framework, or asks "how do I validate my idea," "what's the full process for talking to customers," or "what should I do next in customer discovery" — even if they don't explicitly mention "discovery process." Do NOT use for writing specific interview questions (use conversation-question-

bookforge-ai Skill

Choose the right conversation format — casual chat, scheduled meeting, or phone/video call — for a customer discovery interaction. Use this skill whenever the user is deciding between a formal meeting and a casual conversation, wondering how long customer interviews should be, unsure whether to meet in person or do a phone or video call, preparing to talk to potential customers at a conference or event or meetup, asking how to approach someone at a networking event or industry gathering, spending too much time scheduling formal meetings and not getting enough conversations done (the meeting anti-pattern), defaulting to hour-long Zoom calls for every customer interaction, planning the logistics or setting or duration of a customer conversation, or wondering whether a conversation should be structured or informal — even if they don't explicitly mention "format" or "meeting type." This skill is about HOW to have the conversation (format, duration, setting, formality level), not about finding people to talk to (u

bookforge-ai Bundle

Create a plan for finding and reaching people to have customer discovery conversations with, including channel selection, outreach messages, and warm intro strategies. Use this skill whenever the user does not know how to find people to talk to, does not know anyone in their target market, needs to reach potential customers but has no connections, wants to write a cold outreach email or LinkedIn message for customer conversations, needs help with warm introductions or getting introduced to prospects, is struggling to get meetings or conversations with target customers, wants to build a conversation pipeline or outreach cadence, asks "where do I find people to interview" or "how do I get customer meetings," needs to figure out the best channels to reach a specific customer segment, wants to plan cold or warm outreach for customer interviews, or wants to leverage events or communities or online forums to find conversation targets — even if they don't explicitly say "sourcing" or "outreach." This skill is about

bookforge-ai Bundle

Write, rewrite, or audit customer interview questions so they extract honest behavioral data instead of false validation. Use this skill whenever the user needs to prepare a conversation script for customer discovery, draft questions for an upcoming interview, fix questions that keep producing useless or vague answers, rewrite biased or leading questions into past-focused behavior-revealing ones, check whether their interview questions will trigger compliments instead of facts, or build a question list from learning goals — even if they don't mention "question design" or "The Mom Test." Do NOT use this skill to analyze conversation notes after a meeting (use conversation-data-quality-analyzer) or to decide which questions matter most strategically (use question-importance-prioritizer).

crestapps Bundle

Skill for discovering rendered Orchard Core shapes and selecting safe frontend or admin theme overrides. Covers shape debug comments, bindings, alternates, differentiators, display types, field display modes, OrchardCore.Placements, OrchardCore.Templates, OrchardCore.AdminTemplates, OrchardCore.Liquid, and runtime visual theming workflows. Use when an AI must identify the exact shape behind existing HTML, create a targeted template or placement override, or redesign a running Orchard Core tenant without guessing shape names.

bookforge-ai Bundle

Reverse-engineer a Commercial Insight from seller strengths and validate it against the four-criteria test. Trigger this skill when you need to: - Build a commercial insight or reframe for a teaching pitch - Figure out "what insight should I teach" in a B2B sales conversation - Find a unique angle for a commercial teaching pitch - Reverse engineer a pitch from your strengths (the "Deb Oler question") - Identify which insight to lead with in an insight-led selling approach - Differentiate your pitch from competitors who sell the same category - Determine whether a proposed reframe qualifies as commercial teaching - Start a sales narrative from your solution's unique differentiator rather than customer pain - Create an insight that "leads to" your strengths rather than "leading with" them NOT for: building the full 6-step pitch choreography (use author-commercial-teaching-pitch), tailoring to specific stakeholders (use tailor-pitch-by-stakeholder), or scoring pitch boldness (use SAFE-BOLD framework).

bookforge-ai Skill

Use this skill to plan monetization experiments for a post-PMF product with stable retention — classify the monetization archetype (subscription / e-commerce / ad-revenue), run cohort revenue analysis to find highest-value customer segments, and propose pricing experiments using pricing relativity (3-tier anchoring), cohort upsell, and penny-gap handling. Produces a monetization-experiment-backlog.md with ordered tests and a revenue-cohort-analysis.md showing where the revenue actually comes from. Triggers when a growth PM asks 'how do I increase revenue per user', 'pricing experiment ideas', 'should I raise my prices', 'how do I structure pricing tiers', 'pricing anchoring', 'cohort revenue analysis', 'freemium to paid conversion', 'penny gap problem', 'our LTV is too low', 'CAC LTV ratio', 'monetization funnel', 'upsell experiments', or 'how do I monetize my free users'. Also activates for 'should we drop the price', 'three tier pricing', 'Qualaroo pricing case', or 'personalization recommendations revenue'

crestapps Skill

Skill for Liquid-based prompt templates, template discovery, and prompt composition in CrestApps.Core.

bookforge-ai Skill

Identify the hidden unknowns that will determine whether your negotiation succeeds or fails before you ever make an offer. Use when someone asks "why is my counterpart acting irrationally?", "why does this deal keep stalling for no apparent reason?", "what am I missing about this negotiation?", "how do I find out what the other side really wants?", or "why won't they just say yes when the deal is clearly good for them?" Also use for: diagnosing a stalled sales cycle where the prospect keeps deflecting, investigating why a candidate rejected an offer that seemed strong, uncovering hidden constraints before entering a high-stakes contract renegotiation, mapping leverage before a complex partnership discussion, or rebuilding a broken negotiation relationship. Produces a black-swan-report.md with a hypothesis map of unknown unknowns in all three categories (worldview mismatches, hidden constraints, hidden agendas), a leverage inventory across all three leverage types, and a prioritized bank of investigation quest

bookforge-ai Bundle

Tailor a Commercial Teaching pitch to each stakeholder role using Functional Bias Cards and route the pitch to avoid the C-suite elevation trap. Trigger this skill when you need to: - Tailor a sales pitch to different roles in a buying committee - Build stakeholder-specific messaging for a multi-stakeholder sale - Create a different message for VP Engineering vs CFO vs procurement - Use a Functional Bias Card to map what each role cares about - Build a stakeholder map for an enterprise deal - Understand who to pitch to first and in what order - Adapt a pitch for different audience roles without losing the core insight - Tailor for resonance with a buying committee - Create per-role pitch variants from a single base pitch script - Build consensus across a buying group before reaching the decision-maker NOT for: building the base pitch (use author-commercial-teaching-pitch first), building the underlying commercial insight (use build-commercial-insight), or diagnosing an existing pitch's structure (use diagnose

crestapps Skill

Skill for using CrestApps AI prompt files and Orchard Core AI profile templates. Covers feature-aware prompt discovery, AIProfileTemplate sources, module and App_Data profile paths, prompt selection, and template rendering. Use this skill when requests mention Orchard Core AI Prompting, prompt templates, profile templates, Templates/Prompts, Templates/Profiles, AITemplates, AIProfileTemplate, SourceCatalogEntry, or INamedSourceCatalogManager.

bookforge-ai Bundle

Plan a full Challenger model rollout for a sales organization. Use when someone asks: 'implement Challenger model', 'roll out new sales methodology', 'sales transformation plan', 'change management sales', 'pilot Challenger', 'sales methodology adoption', 'implementation roadmap', 'enablement plan', 'sales training rollout', 'sales change management', 'how do I roll out Challenger', 'Challenger implementation plan', 'sales force transformation', 'how to scale Challenger across the team'. Applies Grainger's four-question pilot framework, star/core/laggard adoption sequencing, 80% adoption target, 20–30% attrition planning, and a four-track parallel workstream design (training, tools, coaching, manager enablement). Produces a rollout-plan.md with pilot scope, adoption sequence, 12-month milestone schedule, and attrition/backfill plan.

crestapps Skill

Skill for configuring the Claude chat orchestrator in Orchard Core using the CrestApps AI Chat Claude module. Covers tenant Claude options, encrypted Anthropic credentials, model discovery, Claude model and effort selection on AI profiles, profile templates, and chat interactions, plus permission management. Use this skill when requests mention Orchard Core Claude Orchestrator, ClaudeOptionsConfiguration, Claude Settings, Anthropic API Key, Claude Profiles, Claude Templates, Claude Chat Interactions, or closely related CrestApps implementation, setup, extension, or troubleshooting work. Strong matches include work with CrestApps.OrchardCore.AI.Chat.Claude, ClaudeOptionsConfiguration, ClaudeSettingsDisplayDriver, AIProfileClaudeDisplayDriver, AIProfileTemplateClaudeDisplayDriver, ChatInteractionClaudeDisplayDriver, ClaudePermissionProvider.

bookforge-ai Bundle

Use this skill to choose acquisition channels for a post-PMF product using the Balfour 6-factor scoring matrix (Cost, Targeting, Control, Input Time, Output Time, Scale — each rated 1–10). First runs two diagnostic prerequisites: language/market fit (does your copy resonate?) and channel/product fit (do your channels match how your audience discovers products?). Then classifies candidate channels into viral/word-of-mouth, organic, and paid categories; scores each on the 6 factors; and recommends 2–3 channels for a Discovery phase with explicit graduation criteria to an Optimization phase. Triggers when a growth PM asks 'which acquisition channels should I test?', 'should I do Facebook ads or SEO?', 'help me pick growth channels', 'acquisition channel prioritization', 'channel/market fit', 'Balfour channel framework', 'our paid ads aren't working', 'which channels for B2B SaaS', 'which channels for e-commerce', 'which channels for consumer app', 'acquisition strategy', or 'how do I pick channels'. Also activat

bookforge-ai Skill

Build an active listening summary and emotional validation script before any negotiation, sales conversation, difficult conversation, conflict resolution, or persuasion attempt. Use this skill when you need to prepare a summary statement that triggers genuine agreement from a counterpart, create a listening script before a high-stakes conversation with an emotionally activated person, draft labels and paraphrasing language before a client call, build rapport with someone before making a request, prepare a stalled negotiation recovery plan using validation techniques, write an empathic opening before delivering difficult feedback, plan the listening sequence before a salary negotiation or sales discovery call, or generate a "that's right" trigger statement that signals real understanding — not just acknowledgment.

bookforge-ai Bundle

Author a Commercial Teaching pitch using the six-step choreography and polish it with SAFE-BOLD. Trigger this skill when you need to: - Write a sales pitch using commercial teaching methodology - Build a commercial teaching pitch from a validated insight - Structure a six-step pitch: warmer reframe rational drowning emotional impact new way solution - Author a sales narrative that leads to your solution rather than leading with it - Build a sales deck following challenger selling choreography - Write a challenger pitch or insight-led pitch for a B2B conversation - Draft a pitch script for a sales rep or sales enablement team - Differentiate a sales conversation by teaching customers something new about their business - Apply SAFE-BOLD to sharpen a teaching pitch before delivery NOT for: building the commercial insight itself (use build-commercial-insight first), tailoring the pitch to individual stakeholders (use tailor-pitch-by-stakeholder after), or diagnosing an existing pitch (use diagnose-pitch-for-comme

bookforge-ai Skill

Use this skill to score and rank a growth experiment backlog using the ICE framework (Impact, Confidence, Ease — each rated 1–10 and averaged) and select the top experiments for the next sprint. Reads an experiment-backlog.md file, applies the ICE rubric with explicit definitions for each dimension, ranks all experiments, separates 'launch now' from 'pipeline with target date' from 'drop', and emits a scored backlog the team can bring to their weekly growth review. Triggers when a growth PM asks 'help me prioritize my experiment ideas', 'which test should I run next', 'ICE score my backlog', 'rank these growth experiments', 'how do I pick experiments for this sprint', 'impact confidence ease', 'ICE framework', 'growth experiment prioritization', or 'I have 40 test ideas, which ones first'. Also activates for 'score this backlog', 'my experiment queue is a mess', 'we keep running low-impact tests', 'growth experiment ranking', or 'how to rank A/B test ideas'.

bookforge-ai Skill

Generate a bank of open-ended strategic questions (how/what questions) for a negotiation, sales conversation, difficult discussion, or conflict situation. Use when someone asks "what questions should I ask in my negotiation?", "how do I get more information without seeming pushy?", "how do I find out who else is involved in this decision?", "what should I ask to understand their constraints?", or "how do I stop the other side from stonewalling me?" Also use for: designing interview questions that reveal unstated priorities, discovering hidden stakeholders who could kill a deal, identifying deal-breaking issues before they surface, uncovering the real decision-making process behind a stated position, or preparing questions for any high-stakes conversation where you need the other party to think and talk. Produces a situation-specific question bank organized by category (value-revealing, behind-the-table stakeholder, deal-killing issue), with follow-up label templates and deployment sequencing. Works for sales

bookforge-ai Skill

Decompose a system into well-defined components using structured discovery techniques. Use this skill whenever the user is designing a new system from requirements, breaking down a monolith into modules, deciding how to organize code into packages/services, asking "what components should this system have?", or struggling with component granularity — even if they don't use the word "component."

duc01226 Bundle

[Planning] Use ONLY when the user explicitly requests a product roadmap, roadmap update, or milestone selection — outcome milestones, MVP scope, non-goals, risks, evidence gates.

oimiragieo Bundle

Therapeutics Data Commons. AI-ready drug discovery datasets (ADME, toxicity, DTI), benchmarks, scaffold splits, molecular oracles, for therapeutic ML and pharmacological prediction.

gptomics Bundle

Estimates SNP heritability and partitions it across functional annotations, cell types, and loci from GWAS summary statistics or individual-level genotypes. Implements LDSC, stratified LDSC with the baseline-LD model, Finucane 2018 cell-type prioritization, LDAK SumHer, HDL, HESS local heritability, BOLT-REML, GCTA-GREML, graphREML, and Popcorn cross-population genetic correlation. Use when computing total h2_SNP from summary stats, partitioning heritability across functional categories, prioritizing trait-relevant tissues or cell types from ENCODE/Roadmap chromatin marks, reconciling LDSC vs LDAK enrichment estimates, computing local heritability with HESS, estimating genetic correlation between traits, or producing publication-grade enrichment with calibrated sensitivity to model assumptions.

gptomics Bundle

Chooses a bulk multi-omics integration strategy before any tool runs by mapping the biological question (subtype discovery, shared axis of variation, predictive signature, pairwise correlation) to a method class, naming the sample correspondence (paired-vertical, horizontal, mosaic, diagonal), enforcing the n<<p discipline that makes a held-out cohort the endpoint instead of in-cohort cross-validation, and running the per-view variance-imbalance diagnostic. Covers the early/mixed/intermediate/late taxonomy, why vertical and horizontal integration are different problems, and why a shared factor dominated by one omic is not integration. Use when deciding which integration method fits a question, whether data is paired or mosaic, supervised or unsupervised, or how to validate an integrated result. For unsupervised factors see mofa-integration; for supervised signatures see mixomics-analysis; for stratification see similarity-network; for single-cell see single-cell/multimodal-integration.

gptomics Bundle

Stratifies patients into multi-omics subtypes by building one patient-by-patient similarity network per omic, fusing them with SNF's cross-network diffusion, and spectral-clustering the fused graph - then defending the clusters with stability, survival separation, and replication. Covers why spectral clustering always returns the requested cluster count so a subtype is a claim not a discovery, why the eigengap is a graph property not a biological truth, why fusion is not automatically better than the best single omic, why SNF needs complete data while NEMO handles mosaic cohorts, and the SNFtool API gotchas (dist2 returns squared distance, affinityMatrix width is sigma, spectralClustering K is the cluster count). Use when discovering patient subtypes from multiple omics, choosing a cluster number, validating subtypes, or handling partial multi-omic data. For feature-space factors see mofa-integration; for supervised signatures see mixomics-analysis; for survival see clinical-biostatistics/survival-analysis.

oimiragieo Bundle

Pythonic wrapper around RDKit with simplified interface and sensible defaults. Preferred for standard drug discovery including SMILES parsing, standardization, descriptors, fingerprints, clustering, 3D conformers, parallel processing. Returns native rdkit.Chem.Mol objects. For advanced control or custom parameters, use rdkit directly.

gptomics Bundle

Call structural variants (>=50 bp deletions, insertions, inversions, duplications, translocations) from short- or long-read data by reconstructing four orthogonal signals (discordant pairs, split reads via the SA tag, read depth, local assembly). Covers Manta, DELLY, LUMPY/smoove, GRIDSS2, SvABA for short reads and Sniffles2, cuteSV, pbsv, dipcall/PAV for long reads, each mapped to the signals it fuses and the blind spots that follow. Use when choosing an SV caller from its signal set and failure modes, decoding the SVLEN-sign / symbolic-vs-BND / CIPOS VCF representation minefield, force-genotyping a cohort matrix instead of unioning discovery VCFs, merging populations with sequence-aware Truvari vs position-only SURVIVOR, parameterizing a Truvari benchmark, or deciding when short-read insertion recall forces a switch to long reads. Not for pure copy-number dosage (see copy-number/cnvkit-analysis).

gptomics Bundle

Quality control, filtering, and normalization for spatial transcriptomics (Visium, Visium HD, Xenium, MERFISH/MERSCOPE, CosMx, Slide-seq) with Squidpy and Scanpy. Use when setting QC floors that do NOT delete real low-count imaging cells (an scRNA min_counts=500 floor deletes nearly every Xenium cell, whose vector is tens-to-low-hundreds of transcripts); deciding whether to normalize at all when library size carries spatial biology rather than pure technical depth; choosing cell-volume/area normalization over Pearson residuals for skewed targeted panels; reading negative-control-probe / blank-barcode false-discovery rates; and inspecting QC spatially on the tissue rather than only in violins.

oimiragieo Bundle

PyTorch-native graph neural networks for molecules and proteins. Use when building custom GNN architectures for drug discovery, protein modeling, or knowledge graph reasoning. Best for custom model development, protein property prediction, retrosynthesis. For pre-trained models and diverse featurizers use deepchem; for benchmark datasets use pytdc.

oimiragieo Bundle

Benchmark external agent frameworks, auto-detect source type, scan for prompt injection, and convert findings into a concrete TDD upgrade backlog for agent-studio evolution.

oimiragieo Bundle

Access RCSB PDB for 3D protein/nucleic acid structures. Search by text/sequence/structure, download coordinates (PDB/mmCIF), retrieve metadata, for structural biology and drug discovery.

oimiragieo Bundle

Access ZINC (230M+ purchasable compounds). Search by ZINC ID/SMILES, similarity searches, 3D-ready structures for docking, analog discovery, for virtual screening and drug discovery.

oimiragieo Bundle

Query ChEMBL bioactive molecules and drug discovery data. Search compounds by structure/properties, retrieve bioactivity data (IC50, Ki), find inhibitors, perform SAR studies, for medicinal chemistry.

oimiragieo Bundle

Query STRING API for protein-protein interactions (59M proteins, 20B interactions). Network analysis, GO/KEGG enrichment, interaction discovery, 5000+ species, for systems biology.