Product & Planning

swan-gtm Bundle

Implement and operationalize proven sales methodologies across revenue teams, with deep SPICED qualification depth. Use when the user mentions SPICED, MEDDIC, MEDDPICC, BANT, Challenger, SPIN, Gap Selling, sales qualification, deal scoring, sales process design, pipeline qualification, discovery frameworks, deal review, sales coaching, rep onboarding, discount negotiation, discount objection handling, or pricing objections. SPICED depth includes full qualification scoring, buying committee mapping by persona, discovery call structure, pipeline stage gating, and canonical language patterns by customer cluster. Also trigger for structuring discovery calls, scoring deals, running deal reviews, handling discount requests, or operationalizing any sales framework. Covers methodology selection, CRM implementation, and discount negotiation playbooks. BOUNDARY: For change management see revops-change-management. For ICP building see icp-builder. For discount governance policy see deal-desk-operations.

swan-gtm Bundle

Use this skill when the forecast is consistently wrong: over-forecasting, missed quarter-ends, deals slipping unexpectedly. Installs category-based forecasting (Commit, Best Case, Upside), multi-method triangulation combining stage-weighted and historical views, and forecast accuracy diagnostics with benchmarks. Produces a repeatable forecast cadence, the red flags to inspect in forecast calls, and a variance-reduction roadmap. Rule: if a rep cannot explain their Commit deal in 2 minutes, it is not a Commit. Trigger phrases: forecast accuracy, we cannot predict our number, forecast categories, pipeline coverage, forecast call, deals go stale.

swan-gtm Bundle

Use this skill when sales call quality is inconsistent, coaching feedback is vague, reps and managers disagree on what a good call is, or the user asks to "build a call scorecard", "score this call", "review my rep's calls", or "make coaching more consistent". It builds behavior-based scorecards for each key conversation type (prospecting, discovery, demo, pricing, close) and uses them to score real calls, localize where reps get stuck, and run chunked practice. Also fires when the user pastes a call transcript and wants it graded.

swan-gtm Skill

Use this skill when developers love your tool but nobody pays, you have never sold and freeze on the conversation, or deals stall on "let me think about it." Produces a repeatable first-deal motion you run yourself: finding the champion and the buyer, running discovery, demoing their use case, arming the champion, and closing your first paying customers. Triggers on "founder-led sales", "close first customers", "nobody will pay", "how do I sell this", "let me think about it", "sales discovery", "find the champion", "close the deal", "first paying customer".

swan-gtm Skill

Use this skill in the gap between a discovery call and the demo that follows — when you have discovery notes and need to turn them into a demo that proves value instead of dumping features. Run it when a rep is about to "walk through the product," when discovery surfaced several pains and you need to decide what to actually show, when a previous demo fell flat or caused "indigestion" (too much shown, nothing landed), or when you need to justify to the buyer why this demo is worth their time. The agent quantifies each discovered pain in dollars/ARR/time, ties it to a root cause, and maps the exact demo moment that proves the fix — producing a "Why This Demo" plan and an explicit cut-list of features to skip.

swan-gtm Bundle

Use this skill for ongoing monitoring across a fixed target-account list; use trigger-based-outbound when evaluating one already-detected event. Produces a resolved account watchlist, signal definitions, stakeholder coverage plan, ranked action queue, and learning loop.

swan-gtm Bundle

Use this skill when you want every sales meeting to produce its follow-through automatically: transcript pulled, outcome classified, account rescored, and a ready-to-send follow-up drafted in the meeting owner's voice within minutes of the call ending. It runs the full production loop — qualification scoring with a human-in-the-loop deal decision, contact and stakeholder loading, CRM lifecycle updates, and a single review post where the owner answers three Yes/No questions to trigger everything downstream. Built for teams where one person takes many external meetings and the follow-up quality (and CRM hygiene) shouldn't depend on their memory.

swan-gtm Bundle

Use this skill after any meaningful interaction on a complex deal — a call, a stakeholder meeting, a procurement exchange — when the question is not "what's missing" but "what do I actually run next week." Takes a qualification assessment (supplied, or scored here from primary evidence), reads it against what the deal's stage should already have proven rather than against an absolute bar, and converts the single worst blocker into a two-cycle maneuver the rep can save and execute: trigger conditions, a pre-mortem, a go/no-go checklist, a verbatim opening, IF/THEN counter-moves, and explicit abort criteria. Covers deal coaching, deal strategy, forecast defence, stalled and blocked deals, gone-dark champions, procurement stalls, third-party and partner blockers, deal reviews, and "this deal is stuck and I don't know why." Built for enterprise and complex deals; not for transactional velocity motions.

swan-gtm Bundle

Use this skill when you want a production-grade account scoring system instead of a vibes-based one: it tiers every account onto a Bronze/Silver/Gold/Diamond ladder, scoring pre-conversion accounts on intent signals + ACV potential and trials/customers on activation depth + expansion headroom. It encodes the judgment that makes scoring trustworthy — a hard self-serve gate with LinkedIn headcount verification, an enterprise persona gate, anonymous-signal and social-engagement caps, prior-relationship floors, and never-demote rules — with every threshold exposed as a tunable default. Each run produces a verified tier tag and ACV tag, a prepended signal-stack snapshot in account memory, a CRM lead-score sync, and correctly routed Gold/Diamond alerts with per-stakeholder engagement recommendations.

swan-gtm Bundle

Revenue change management: plan change, design enablement, make it stick, measure adoption. Trigger on change management, enablement design, adoption failure, rollout plan, communication plan, stakeholder management, training that doesn't stick, behavior change, coaching program, process change, system migration, comp plan change, territory change, Kotter, ADKAR, spaced repetition, forgetting curve, reverse salient, traffic light model, Bloom's taxonomy, 'nobody follows the new process,' 'we trained them but nothing changed,' 'the tool is built but nobody uses it,' 'how do we get buy-in,' 'people are pushing back,' AI change management, FOBO, shadow AI, AI adoption, works council AI, AI governance framework, AI rollout, or fear of becoming obsolete. BOUNDARY: For HubSpot adoption, see revops-hubspot. For GTM org change, see gtm-planning.

swan-gtm Skill

Use this skill when a shaped topic list needs scoring and sequencing into a build order — six dimensions (commercial intent, ICP alignment, ranking feasibility, effort, authority leverage, adjacency to wins) into Tier 1/2/3, quick wins first. Fires on "what should we build first", "prioritize the content roadmap", "sequence these topics". Phase 7 of the SEO topic research pipeline; runs standalone if you paste the shaped topics.

internscience Skill

Calculate advanced molecular descriptors including shape indices, connectivity indices, and structural features for QSAR and drug discovery.

dragoon0x Skill

Music app design, playlist UX, album displays, audio player patterns, and music discovery.

dragoon0x Skill

Event listing, seat selection, ticketing flow, calendar integration, and event discovery UX.

dragoon0x Skill

Feature prioritization frameworks, scoring models, roadmap design, and saying no to features.

dragoon0x Skill

Managing design stakeholders, presenting to executives, handling feedback, and building alignment.

dragoon0x Skill

Media and entertainment product design including streaming, content discovery, and media playback.

clowlove Bundle

Skills for working with MCP (Model Context Protocol) servers, tools, and integrations. Documents the built-in native MCP client — configure servers in config.yaml for automatic tool discovery.

clowlove Bundle

Passive domain reconnaissance using Python stdlib. Use this skill for subdomain discovery, SSL certificate inspection, WHOIS lookups, DNS records, domain availability checks, and bulk multi-domain analysis. No API keys required. Triggers on requests like

clowlove Bundle

资深售前工程师，专精技术 Discovery、Demo 设计、POC 执行、竞争技术定位，擅长将产品能力转化为业务成果。在单子进入采购流程之前，先赢下技术决策。

clowlove Bundle

销售方法论专家，辅导团队掌握高阶 Discovery 技巧——问题设计、现状诊断、差距量化和通话结构，挖掘客户真正的购买动机。

bromso Skill

Build a release roadmap with milestones, themes, and timeline

bromso Skill

Build a phased compliance roadmap with milestones, dependencies, and resource needs

bromso Skill

Prepare sprint review — what was done, what wasn't, stakeholder demo plan

bromso Skill

Identify and map stakeholders by influence, interest, and communication needs

bromso Skill

Create and structure the initial product backlog from vision and roadmap

bromso Skill

Generate stakeholder status update with progress, risks, and asks

gaelic-ghost Bundle

Use Hopper on macOS for disassembly, graphs, pseudocode, Objective-C and Swift presentation, procedure and type edits, extensions, and debugging. Use for document setup, navigation, annotation, evidence, comparison, and discovery.

gaelic-ghost Bundle

Test authorized network services with bounded discovery and protocol-aware validation. Use for hosts, ranges, ports, TLS, banners, versions, authentication, exposure, segmentation, configuration, packet evidence, or vulnerability checks.

gaelic-ghost Bundle

Maintain ROADMAP.md as the planning member of the canonical four-document repository suite.

robsonkades Bundle

Selecting the least-perturbing JVM evidence source that matches the question: JFR events and timeline versus async-profiler sampling, CPU versus elapsed/off-CPU, allocation versus retention, lock versus queue/I/O, startup versus steady state, and one-off versus continuous capture. Covers adequacy, positive controls, target scope, version discovery, container access, overhead, artifact integrity, and cross-tool reconciliation. Use before a JVM profile is collected or when an empty/disagreeing recording may be a configuration artifact. Graph interpretation, JFR internals, async-profiler engines, and fleet operations have separate owners.

robsonkades Bundle

Deciding when a shortcut is a legitimate trade and when it is just damage: separating deliberate and inadvertent debt, constraints delivery pressure does not waive, containing a shortcut so it can be undone, recording it where someone will find it, and choosing which debt to repay by its carrying cost rather than by how much it annoys you. Use when a deadline or an incident is pushing work to be cut, when someone proposes shipping now and cleaning up later, when a spike is about to become production code, when "technical debt" is being used to justify a rewrite, when a debt backlog has grown into a list nobody reads, or when deciding whether to fix something you have just noticed. Does not cover the refactoring mechanics of repaying it (java-refactoring), how to detect the problem (java-code-smells), how to communicate the trade (engineering-communication), or which gates may be skipped (quality-gates).

robsonkades Bundle

Composable stage shapes for event-driven pipelines — copier, filter, splitter, sharder, merger — with ordering, semantic parallelism, state, shuffle and recovery boundaries; exactly-once scope across source, state and sinks; bounded joins and windows; watermarks, late-data policy, backlog versus flow control, and reproducible replay. Use when a stage is parallelised, when a join grows state without bound, when a stage re-keys the stream, when late events arrive after a window closed, when a windowed test uses wall-clock, or when reprocessing gives a different answer. Not whether to be event-driven (event-driven-architecture), ordering scope (message-ordering-and-partitioning), barriers (distributed-aggregation-and-barriers), skew (hot-partitions-and-rebalancing), the consumer (kafka-consumers-in-java), or in-process demand (reactive-backpressure).

robsonkades Bundle

Deciding what to ask the user about a feature, when to ask it, and what stops work until it is answered: proving the repository cannot answer it first, pricing each question by what changes if the answer is the other one, batching questions into rounds instead of interrogating, and marking the few that are genuinely blocking. Use when a feature request is ambiguous and the choice is between asking and assuming, when a long list of questions is about to be sent at once, when work is stalled on a question that has no consequence, when implementation is about to start on a guessed answer, or when a question is being asked that a grep would have answered. Does not investigate the repository itself (feature-context-analysis), does not classify what is known from what is guessed (feature-discovery), and does not own the ambiguity catalogue or acceptance-criteria format (requirements-and-acceptance).

robsonkades Bundle

Distributing work to a pool of interchangeable workers through a queue: the lease and visibility-timeout model, and why an expired lease duplicates work instead of failing it; sizing the timeout from processing plus prefetch wait; heartbeats and their failure mode; admission and retention bounds; priority starvation; and age, backlog, arrival and drain rate as autoscaling signals. Use when two workers process one message although nothing retried or failed, when a lease is relied on for mutual exclusion, when a handler outlives its lease, when a queue has no maximum depth, when autoscaling is driven by queue depth, or when a poll loop feeds an unbounded executor. Not ack placement (delivery-semantics), repeat-safe handlers (idempotency), the message that never succeeds (poison-messages-and-dlq), queue arithmetic (littles-law-and-queueing), the concurrency limit (concurrency-limiting-and-bulkheads), shedding (rate-limiting-and-load-shedding), or the Kafka consumer group, a log (kafka-consumers-in-java).

melodic-software Bundle

Produce a Product Requirements Document that locks product intent. Problem, users, success metrics. Before any engineering plan, with tiers (one-pager / consumer-feature / b2b-internal), a synthesize path, and a review mode. Use when: 'write a PRD', 'spec out a feature', 'product brief', 'product requirements doc', 'define the requirements', 'what are we actually building', 'acceptance criteria', 'how will we know it worked', or any user-facing business-driven change needing written alignment; skip for refactors, infra, bug fixes, and engineering-internal work (route to /planning:interview or /planning:plan).