Latest Agent Skills

Design a scope and sequence showing vertical and horizontal curriculum coherence across a programme or year. Use when building new programmes, restructuring subjects, or ensuring progression.

Audit a proposed assessment for construct validity, reliability, and alignment to learning objectives. Use when reviewing or quality-assuring assessments before deployment.

Audit and redesign AI-generated feedback for pedagogical quality, timing, and learning impact. Use when building or reviewing automated feedback in digital learning tools.

Map systemic forces shaping a wellbeing concern without individualising the problem. Uses Bronfenbrenner's ecological model and social determinants to generate structural interventions.

When a learner gets something wrong or feels stuck, require them to diagnose the problem before receiving help. Ensures help targets the actual cognitive breakdown, not just the surface error.

Design a single-point rubric with one criterion and open columns for evidence. Use for student self-assessment, peer feedback, teacher formative feedback, or pre-task planning. Works with any learning target, with or without a band system.

Tier vocabulary from a text or topic into everyday, academic, and technical categories with teaching priorities. Use when pre-teaching vocabulary or identifying language barriers in a text.

Design a fact-checking protocol for AI-generated text, extending SIFT with AI-specific adaptations for hallucination detection. Use when students need to verify AI claims and citations.

Slow down interpretation from observation to action. Use when students or adults need to examine assumptions in conflict, dialogue, or inquiry.

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. Critical for preventing phantom attainment.

Select evidence-based study strategies matched to material type, learning goal, and student habits. Use when advising students on revision techniques, homework, or independent study approaches.

Design an error analysis protocol to diagnose the root cause of student mistakes and misconceptions. Use when error patterns appear in student work and targeted feedback is needed.

Analyse a learning task for cognitive load problems and recommend specific design improvements. Use when tasks overwhelm students, instructions feel complex, or materials need simplifying.

Build students' capacity to compare accounts across multiple historical sources — identifying agreements, contradictions, and gaps. Use when students treat individual documents as complete answers rather than partial perspectives.

Build students' capacity to read historical documents closely — attending to word choice, tone, and rhetoric as evidence of perspective. Use when students summarise sources without analysing language.

Classify curriculum content into Know, Understand, and Do categories to align teaching and assessment approaches. Use when planning units, writing objectives, or selecting assessment methods.

Design a Funhouse Mirror activity where students use their own domain expertise to detect AI distortions, omissions, and overconfidence. Use when students know a subject well enough to evaluate AI claims about it.

Design a diagnostic hinge question that reveals whether students understand enough to move on. Use when planning key checkpoints mid-lesson during explicit or direct instruction.

Design deliberately flawed examples that develop error-detection skills and deepen understanding. Use when students make characteristic errors and need practice spotting mistakes.

Design a wise systems intervention from an existing analysis. Maps proposed actions against Meadows' leverage points, checks for unintended consequences, and generates alternatives.

Design the deeper patterns, structures, artefacts, and mental models needed to grow a desired event. Use when a class imagines a better future.

Capture confidence ratings before and after a learning attempt to identify overconfidence and underconfidence patterns. Use when a student wants to understand how well they actually know something versus how well they think they know it.

Adapt a historical primary source for classroom use — modifying complexity and length while preserving features for sourcing, close reading, and corroboration. Use when a primary source is too complex for the target age group.

Adapt a classroom task for specific learner needs while preserving the core learning objective intact. Use when differentiating for SEND, EAL, gifted, ADHD, dyslexia, or anxiety.

Design a learning sequence teaching prompt quality — comparing vague vs. refined prompts to show why specificity and context transform AI output. Use when students use AI without understanding why output quality varies.

Design a structured protocol for auditing AI-generated text against Ennis's six CT standards. Use when students need to critically evaluate AI output in any subject.

Stage exploration before instruction on complex problems. The learner produces two attempted approaches before consolidation — which builds on those attempts, not from scratch. Use for genuinely hard problems where struggle produces deeper learning.

Design a visual complement to verbal content using dual coding principles for stronger encoding. Use when creating slides, diagrams, posters, or visual explanations of complex concepts.

Design a lesson opening that activates prior knowledge and connects previous learning to today's content. Use when planning lesson starters, retrieval openers, or advance organisers.

Design a project-based learning brief with a driving question, milestones, and assessment criteria. Use when planning PBL units, inquiry projects, or extended investigations.

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 explanation from scratch.

Map a current event below the surface into patterns, structures, and mental models. Use when a class or team needs systemic understanding before action.

Map a complex topic by placing factors on hexagonal tiles where adjacency signals a claimed relationship. Use when students need to surface hidden connections in a system before analysis or action.

Build students' capacity to interrogate a historical source before reading — asking who authored it, when, why, and what this means for reliability. Use when students read documents without attending to authorship.

Unpack a broad standard or competency descriptor into specific, assessable success criteria and sub-skills. Use when interpreting curriculum standards or writing learning objectives.

Compares two or more band-tagged frameworks and produces a framework-neutral topic matrix showing coverage and gaps across all inputs, plus an optional reference-centric PLC crosswalk document when a reference framework is supplied.

Design a multi-round questioning sequence for interrogating AI chatbot answers, tracking how responses shift and distinguishing genuine updates from sycophantic capitulation. Use when teaching students to probe AI critically.

Provide graduated assistance from abstract conceptual nudge to concrete procedural step, with reflection required before each escalation. Teaches help-seeking as a skill and prevents direct-answer shortcuts.

Predicts access barriers in a learning task before delivery, given a learner variability profile. Distinguishes between barriers addressable through design and those requiring specialist support.

Map which elements of an assignment benefit from AI assistance vs. which AI use undermines. Use when redesigning tasks for AI-age classrooms or setting defensible AI use policies for specific assignments.

Review the week using accumulated session evidence — retrieval rates, hint depths, calibration accuracy, transfer and unassisted results. The learner identifies patterns and sets a strategy goal. Use weekly or after a multi-session period.

The learner teaches the concept to the AI, which plays a curious novice peer and identifies gaps through authentic questions. Use when the learner wants to test their understanding — teaching forces a different kind of organisation than studying.

Generates multiple means of engagement, representation, and action/expression for a given learning goal. Produces specific, practical alternatives — not generic options — and recommends the highest-impact single change.

Authors or reviews Know/Understand/Do charts for competency-based learning targets across developmental bands. Handles seven input types from raw curriculum documents to existing LT sets. Routes to upstream skills when stronger inputs are available.

Surface beliefs, assumptions, stories, and values shaping a system. Use when deeper mental models need examining with care and evidence.

Wrap a learning session in a plan → monitor → reflect cycle. Use at the start of any substantial study session to set goals, mid-session to check strategy, and at session end to consolidate what changed. Builds self-regulated learning as a habit.

Before any explanation or answer, require the learner to produce a free-recall attempt and confidence rating. Use when a student wants help understanding or reviewing a topic — this skill ensures the AI works from what the learner already knows.

Audits an existing lesson against UDL's three principles — engagement, representation, and action/expression. Identifies specific access barriers and suggests concrete modifications ranked by impact.

Takes a curriculum framework and a statutory or accreditation requirement list; produces a coverage table, gap summary, and CSV showing which framework content covers each requirement and where gaps exist.

Seven-role depersonalised panel review of framework artefacts (KUD, criterion bank, LT definition, crosswalk, scope-and-sequence) in sequential-isolation mode. Gate rule mean>=88 AND no role<70.

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. Builds epistemic vigilance — treats AI output as a claim to evaluate, not truth to absorb.

After the learner demonstrates understanding of a concept, present near-transfer and far-transfer challenges. Use to test whether learning is portable or task-specific — this is what separates understanding from familiarity.

Track performance across sessions and reduce scaffolding as competence grows. Makes fading visible — the learner knows when scaffolds are removed and why. Use for sustained learning engagement where independence is the goal.

Off-page playbook (Lesson 9, link building). Mines our competitors' backlink profiles via Ahrefs to produce a VETTED link-prospect list — their "superfans" (sites linking to several of a competitor's best-by-links pages), their "power-linkers" (sites linking to multiple competitors but NOT to us), and their fresh new links — filtered for relevance and de-duped against sites that already link to us. The Link Intersect method, encoded. Output is a prospect queue for /outreach; it does NOT send anything.

Knowledge base from "Contagious: Why Things Catch On" by Jonah Berger. Use when applying Berger's STEPPS framework for word of mouth, virality, social currency, triggers, emotion, social proof, practical value, and storytelling, studying the book, or referencing its concepts.

Post-draft pass that expands a drafted article to capture the FULL keyword family — keywords the page already or could rank for, plus the Ahrefs Content Gap (keywords competitors rank for but we don't) — by weaving the worthwhile ones in as natural added paragraphs/sections. NOT keyword stuffing. Triggered after /draft, before /quality-check.

Master orchestrator for the keyword research pipeline. Chains topic-discovery → seed/modifier ideation → competitor + AI-search gap analysis → question mining → BID method → AIO cannibalization check → adversarial redteam → final ranked queue. Same anti-context-bloat pattern as /blog-pipeline (every layer is an Agent dispatch, never a Skill fork).

Find brand products that should be added to an existing article. Compares the article's current product mentions to the brand-config product list and proposes natural insertion points.

Layer 1d of the keyword research pipeline. Mines question-shaped keywords from Semrush phrase_questions (per surviving seed) plus People-Also-Ask strings from the SERP. Appends rows to keyword-ideas.csv with source=question_mining (or merges to source=both when the keyword already exists) and a question_subtype column. Cap of 100 rows per run.

Layer 6 of the keyword research pipeline. Organizes the vetted keyword queue into money clusters (from clusters.md), picks each cluster's keystone vs supporting articles, tracks coverage, and PROPOSES new clusters from high-business-value topics or live products not yet covered — so the blog strategy expands as the company grows. Emits cluster-tagged queue + cluster-map.md + cluster-proposals.md.