القائمة
Ground an unfamiliar repo area, library, API, failure mode, or design question. Writes evidence to .context/scout.md and returns only constraints, risks, unknowns, and the next natural action.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Apply Emil Kowalski-style UI polish: interaction details, component feel, animation restraint, and invisible product quality. Uses progressive disclosure instead of long design essays.
Apply Emil Kowalski-style animation guidance for web interfaces: purposeful motion, correct easing, interruptibility, performance, reduced motion, and interaction feel.
Implement the requested change on the current branch using the best available contract: issue, architecture, user request, or repo evidence. Does not require /architect or /review to have run. Hands naturally to /test.
Triage and address PR review comments. Uses available issue/architecture/context when present, keeps evidence in .context/address.md, and does not require prior workflow phases.
Derive the smallest correct architecture from user intent, repo facts, and available workflow evidence. Writes the full architecture to .context/architecture.md and returns only the decision, tradeoff, risk, and next action.
Review the current PR for correctness, tests, maintainability, security, standards, and prior-findings risk. Keeps reviewer detail in .context/code-review.md and posts concise actionable GitHub review comments.
| name | scout |
| description | Ground an unfamiliar repo area, library, API, failure mode, or design question. Writes evidence to .context/scout.md and returns only constraints, risks, unknowns, and the next natural action. |
Read the shared contracts before output: ../_shared/operator-output.md, ../_shared/attention-budget.md, ../_shared/evidence-record.md, ../_shared/state.md, ../_shared/cognitive-load.md, ../_shared/collaboration.md.
Map facts that would change a later decision.
A concrete topic from the user, current repo context, an issue/PR, or the active uncertainty. If the topic is vague, inspect the repo first, then ask one clarifying question only if needed.
Repo code/tests/docs, git history, installed package source/types, official docs or context7 for library/API behavior, gh_grep/reference repos for usage, exa for current external pages.
.context/scout.md.context/session-state.md.context/scout.md.Return: decision, up to three evidence bullets, risk/unknowns, and next action. Suggest /interview when intent needs pressure; suggest /architect when the problem and direction are already clear.
Stop when new evidence is unlikely to change the next decision, or when one user decision blocks further grounding.