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/user-research/explore.md
View on GitHub# user-research — explore
Reduce uncertainty about people, their tasks, and their context through proportionate observation.
## 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 whole catalog. Relevant example: understand why users abandon a journey before changing it. Out-of-scope example: apply an already reproduced deterministic fix with no unknown user need.
This extension reduces uncertainty about people, goals, context, and actual experience. It turns assumptions into questions, chooses proportionate methods, includes affected people, and makes findings usable in the contract. Select it during `stip-explore` when problems, audiences, journeys, comprehension, or usefulness are uncertain. Apply/check contributions are available only when selected in the contract. New critical hypotheses after approval require returning to explore and validate and obtaining revised approval before adding them.
It does not replace product analysis, accessibility, statistics, or technical testing. Existing satisfaction surveys do not prove particular journeys usable; automated tests do not explain abandonment. Internal changes with recently evidenced users, tasks, and expected behavior need not trigger it. GOV.UK recommends learning needs during discovery and testing ideas/features in later phases ([Learning about users and their needs](https://www.gov.uk/service-manual/user-research/start-by-learning-user-needs)). This institutional requirement is used here as a reference for careful practice.
## Recognize and reuse existing work
For a new project, look for analytics, tickets, research logs, prior reports, interviews, observations, profiles, journeys, support feedback, and recruitment constraints. For an existing project, verify dates, segments, methods, tested tasks, notes/recordings, decisions, and changes since the research. GOV.UK recommends phase-specific objectives and updating plans as learning progresses ([Plan user research](https://www.gov.uk/service-manual/user-research/plan-user-research-for-your-service)).
Classify results as **established** (verifiable method, participants/source, date, observation, and scope), **inferred** (plausible but unconfirmed signal/feedback), **incomplete** (insufficient group, task, or context), **missing** (explicit investigation found no relevant result), or **not-applicable** (question outside audience/channel). Undocumented claims remain inferred. Silence from research that missed the right group is not absence of need. New projects still need to discover groups and journeys; existing products primarily need behavioral gaps, context changes, and regressions examined.
Participants should represent current or likely users, including disabled people, people with limited digital confidence, and those providing or supporting the service. GOV.UK recommends experience/access-based criteria, data protection, and avoiding repeated dependence on the same participants ([Finding participants](https://www.gov.uk/service-manual/user-research/find-user-research-participants)). Numbers such as four to eight people for a small qualitative round are team guidelines, not general statistical guarantees.
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 a decision to inform, three to five questions, a proportionate round, recruitment criteria, consent, notes, and action-linked synthesis. Go deeper for critical public journeys, underrepresented groups, legal/financial risks, contradictory findings, production behavior changes, or irreversible decisions: multiple rounds, behavioral data, assistive-technology testing, comparison studies, and longitudinal follow-up may be needed. Heavy studies are not justified for text corrections already validated by affected users.
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 decisions/hypotheses; UX supplies prototypes; accessibility verifies inclusion and assistive technologies; content and visual design make stimuli understandable. Avoid recruiting only colleagues, asking whether people like an idea, treating five participants as quantitative proof, or confusing recruitment difficulties with absent needs. Invisible implementation changes already covered by criteria and regression tests need not trigger this extension. GOV.UK describes contextual practices; the process, `AC-UR-*` candidates, and adoption taxonomy are our integration synthesis.
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 |