BRYANN2K/stipulate-skills / skills/stip-bootstrap
stip-bootstrap
VerifiedAdopt Stip in a new or existing repository, preserving project conventions and assessing applicable domains.
assets/extensions/storytelling/explore.md
View on GitHub# storytelling — explore
Connect intent, a supportable promise, messaging, and consistent narrative across product surfaces.
## Decide whether this domain is relevant
Availability in configuration does not activate this domain. During `stip-explore`, select it only when its responsibility affects the change or a decisive unknown. Do not activate the entire catalog. Relevant example: align landing-page, onboarding, and demo promises with delivered capabilities. Out-of-scope example: fix an internal calculation without changing product positioning or messages.
This extension makes a product understandable and credible through **intent → promise → messages → product narrative → content consistency**. It positions experiences, explains problems and value, and translates that understanding into landing pages, onboarding, demos, changelogs, or documentation. Marketing promises are allowed when supported by capabilities, observations, measurements, or decisions; unsupported promises, exaggeration, and selectively convenient evidence are excluded.
Select it during `stip-explore` for positioning, message hierarchy, cross-surface product stories, or decisions that multiple audiences must understand. Intercom's product marketing connects market and product perspectives from development to launch through insights, strategy, positioning, and go-to-market work ([Keeping the market in mind](https://www.intercom.com/blog/product-marketing-at-intercom/)). This is company practice, not a universal standard. It does not replace product strategy's outcome decisions, user research observations, content design's operational text/testing, or UX journeys. Internal corrections without audiences, default slide decks, or hypotheses disguised as slogans do not trigger it. New audiences, channels, or goals after approval require explore, validate, and revised approval; no silent activation.
## Recognize and reuse existing work
For a new project, identify problems, desired outcomes, segments, alternatives, proposed promises, available evidence, and message surfaces. For an existing project, review positioning, acquisition pages, onboarding, value labels, demos, decision notes, changelogs, support, and reader feedback. Compare messages before use, during first use, and after delivery: a landing-page promise missing from the product is a substantive inconsistency, not a style issue.
Classify elements as **established** (verifiable message, capability, or evidence), **inferred** (interpretation from an indication), **incomplete** (narrative/surface without context, evidence, or action), **missing** (explicit search found no relevant artifact), or **not-applicable** (no affected audience, promise, or surface). Presentations do not establish comprehension, slogans do not prove value, and absent pages do not prove absent intent. Verify dates, product versions, measurement limits, and permission to use quotations/testimonials.
Intercom recommends framing problems around customers' desired outcomes, reasons, and pain with the status quo rather than requested features ([For better products, start with a problem statement](https://www.intercom.com/blog/how-to-write-problem-statements/)). This can anchor promises, but teams must confirm their own evidence. Its onboarding practice starts from the user's job, demonstrates value, and removes nonessential steps ([Hook trial users from their first use](https://www.intercom.com/blog/trial-users-first-use/)).
Consult the bootstrap map, then seek only evidence relevant to the change. Classify each finding as **established, inferred, incomplete, missing, or not-applicable**, with evidence or justification. Missing documentation does not mean a practice is absent. Decide whether to reuse, complete, or replace existing work; an already satisfied step may require no further work.
## Scope the contribution to the shared contract
The MVP includes intent, audience, supported promise, central message, two or three supporting messages, evidence, and translation onto the main surface. A sentence and short demonstration may suffice for a small evolution. Go deeper for multiple segments, acquisition/activation journeys, sensitive brands, complex data, coordinated launches, or overpromising risks: audience variants, comprehension tests, cross-channel consistency maps, objections, accessibility, localization, and revision history. Do not produce a full deck when a message page and evidence answer the decision.
Propose only necessary properties and how to verify them, using the candidates in [check.md](check.md). The agent adapts and remaps them to `AC-1`, `AC-2`, etc., unique within the **shared specification**; the engine does not remap domain IDs. Do not create a parallel specification or approval. Each criterion must state the outcome, context, and expected evidence. A new requirement after approval requires revising the contract and obtaining renewed approval.
## Boundaries
Product strategy supplies problem/outcome/priority; user research supplies needs/observations; UX checks feasibility of the promised experience; content design translates messages into interface language; visual design makes hierarchy perceptible; build-in-public handles authorization for a publishable version. Avoid brand stories as value evidence, team-centered narratives, out-of-context quotations, undelivered promises, and variants that obscure the central idea. Marketing positioning must remain bounded by capabilities and evidence. Internal migrations without audiences or strictly machine-to-machine contracts do not trigger it. Duarte, Storytelling with Data, and Intercom describe their practices; sequence, evidence statuses, and criteria are our Stip integration.
Other domains mentioned here are possible collaborators, never automatically activated dependencies. Cloud-only work does not activate UX/design. Detailed sources are in [sources.md](sources.md); they inform decisions and do not create additional implicit acceptance criteria.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack." | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |