Apply the Gestalt principle of Figure-Ground Relationship — the perceptual separation of what''s perceived as the figure (the focus, the object) from the ground (the surrounding…
Structure a direct experience into a full learning cycle with concrete experience, reflection, and conceptual transfer.
Post-ship doc sync across project markdown. Use when: sync docs, update docs, document changes, release notes.
Unpack a broad standard or competency descriptor into specific, assessable success criteria and sub-skills.
Generate retrieval practice questions at varied difficulty levels for a topic or concept. Use when creating quiz starters, revision activities, or low-stakes testing materials.
Design a teacher think-aloud that models historical thinking strategies with a specific document. Use when planning explicit strategy instruction or when students follow a…
Use when the user's video is on disk — VidSeeds MCP probe, frame/clip extraction, ffmpeg recipes, precision trim, and midroll analysis.
Design a structured outdoor learning sequence embedding curriculum objectives in an available outdoor space.
Provide graduated assistance from abstract conceptual nudge to concrete procedural step, with reflection required before each escalation.
Generate a criterion-referenced rubric with descriptive performance levels for a task or objective. Use for marking guides and general curriculum contexts.
Track project blockers, bugs, and gaps across sessions — use when issues pile up or need triage
Trace codepaths in diffs, map against tests, auto-generate missing coverage — use before shipping PRs
Extract a small sample of rows from a dbt output port using a non-production profile, scrub anything classified as PII or sensitive in the data contract, and upload the scrubbed…
Design a mastery experience sequence that systematically builds student confidence in a skill they avoid.
Use when user wants to update .pre-commit-config.yaml hooks to their latest versions from GitHub
Quick execution for ad-hoc tasks without full workflow overhead — use for small, self-contained requests
After any AI-generated explanation, require the learner to identify one place it could be wrong, one thing to check, and one source to consult.
Build students' capacity to compare accounts across multiple historical sources — identifying agreements, contradictions, and gaps.
Select the right formative assessment technique for a specific learning moment, purpose, and age group.
Map the epistemic structure of a subject to determine knowledge types and inform curriculum sequencing.
Design a variation theory task using contrast, separation, and fusion to teach critical features of a concept.
Build a five-level rubric with coherent logic for a learning target within a developmental band. Use for Manning methodology programmes where Competent = success.
Apply Ockham''s Razor — given a choice between functionally equivalent designs, prefer the simplest. Use when comparing design approaches, evaluating whether a feature is…
Design an uninterrupted work cycle with choice-based activities structured within a realistic time block.
Generate a coaching conversation guide with questions, protocols, and follow-up actions for a teaching focus.
Track performance across sessions and reduce scaffolding as competence grows. Makes fading visible — the learner knows when scaffolds are removed and why.
Peer Review Ralph Loop — combines Cavekit kits with a Ralph Loop and true cross-model peer review using Codex (OpenAI). Claude builds from specs; Codex reviews adversarially.
Design a focused lesson observation protocol with specific look-fors and evidence collection methods.
Audit and redesign AI-generated feedback for pedagogical quality, timing, and learning impact. Use when building or reviewing automated feedback in digital learning tools.
Select evidence-based study strategies matched to material type, learning goal, and student habits. Use when advising students on revision techniques, homework, or independent…
Apply figure-ground separation specifically for overlays — modals, dialogs, drawers, popovers, dropdowns, toasts.
Prune accumulated complexity from a product — features, options, settings, code paths that no longer earn their place.
Set line length (measure) for prose — capping the maximum width of body text so lines stay in the 45–75 character range that supports comfortable sustained reading.
Use when executing an existing HOTL workflow file — reads steps, loops until success criteria met, auto-approves low-risk gates, pauses at high-risk gates.
Redesign a lesson to centre students' cultural backgrounds, community knowledge, and lived experience.
Codex-native Amazon PPC setup workflow using Wilco's exact-match and analytics-first strategy. Use when the user wants stricter keyword control, exact-match campaigns, and a…
Require the learner to explain a concept in their own words before the AI evaluates or extends it. Ensures the AI works from the learner's understanding rather than providing an…
Design a Montessori three-period lesson for introducing concepts through concrete materials and naming.
Generate a Socratic questioning sequence that develops conceptual understanding through guided inquiry.
Step-by-step process for adopting Cavekit on an existing codebase. Covers the 6-step brownfield process, bootstrap prompt design, spec validation against existing behavior, and…
Use Chrome DevTools MCP for frontend performance work such as slow page loads, LCP, CLS, INP, Lighthouse regressions, scripting hotspots, or layout thrash.
Debug issues methodically — use when stuck on errors, test failures, or unexpected behavior
List the teams configured in Entropy Data so the user can pick one as the owner (`team.name` in ODPS) of a data product.
Run and monitor PapersFlow DeepScan jobs. Use when the user wants long-running research progress, intermediate findings, final reports, or plotting from a completed run.
Используй только когда пользователь явно просит запустить Codex Project Autopilot, продолжить проект из .codex-agent или в текущем workspace уже есть активный .codex-agent.
Apply layered control — designing interfaces that serve novice and expert users in the same product without forcing one audience into the other''s interface.
Switch to Knowledge Work mode for research and writing — use when task is non-code focused
Design for flow specifically — calibrate challenge to skill, provide immediate feedback, set clear goals, foreground the activity.
Optimise a learning activity for flow by balancing challenge level, skill, clear goals, and immediate feedback. Use when students are bored, anxious, or disengaged during a task.
Package and finalize completed work for delivery — use when a feature is done and ready to ship
Map systemic forces shaping a wellbeing concern without individualising the problem. Uses Bronfenbrenner's ecological model and social determinants to generate structural…
Frappe DocType creation and form UX guidance. Use when creating, reviewing, or redesigning DocTypes, including field choice, tabs, sections, columns, required fields, naming,…
After scaffolded practice, run an unassisted check — a problem with no AI help. Separates what the learner can do with support from what they can do independently.
Implement Zagrosi Forge section files with test-first development, focused review, documentation updates, and git hygiene.
Write an AI-optimized PRD using multi-AI orchestration — use when scoping a new feature or product
Temporary inboxes for agent signup QA — create disposable addresses, wait for verification email, extract OTP or magic links.
Use when Codex is working on a repo or task that is scoped to an OrgX initiative, workstream, milestone, task, blocker, or decision and needs to use OrgX MCP as the source of…
Evidence before claims — run verification commands before declaring work complete, fixed, or passing
Design a sequence where students compare AI's handling of the same question across disciplines, developing a mental model of where AI is reliable vs.
Design forms that exploit closure — suggesting shapes through partial outlines, negative space, or strategic gaps so the user''s perception completes them.