Search
AI & LLM Engineering · GarethManning/education-agent-skills
Skills
Sort:BestMost starsTrending todayTrending this weekTrending this monthNewestRecently updatedName
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Before any explanation or answer, require the learner to produce a free-recall attempt and confidence rating. | GarethManning/ | 840 | — | ~3.8k | Automated safety check: Pass | Unknown | 1 mo ago |
| 2 | After the learner demonstrates understanding of a concept, present near-transfer and far-transfer challenges. | GarethManning/ | 840 | — | ~4.2k | Automated safety check: Pass | Unknown | 1 mo ago |
| 3 | After scaffolded practice, run an unassisted check with no AI help. | GarethManning/ | 840 | — | ~4.1k | Automated safety check: Pass | Unknown | 1 mo ago |
| 4 | Build a library of metacognitive prompts targeting planning, monitoring, or evaluation for a specific task. | GarethManning/ | 840 | — | ~4.3k | Automated safety check: Pass | Unknown | 1 mo ago |
| 5 | Stage exploration before instruction on complex problems. An agent skill from GarethManning/education-agent-skills. | GarethManning/ | 840 | — | ~4.3k | Automated safety check: Pass | Unknown | 1 mo ago |
| 6 | The learner teaches the concept to the AI, which plays a curious novice peer and identifies gaps through authentic questions. | GarethManning/ | 840 | — | ~4.1k | Automated safety check: Pass | Unknown | 1 mo ago |
| 7 | Design a critical thinking task targeting specific skills like evaluating evidence, identifying bias, or analysing arguments. | GarethManning/ | 840 | — | ~6.3k | Automated safety check: Pass | Unknown | 1 mo ago |
| 8 | Design discipline-specific critical thinking tasks grounded in knowledge-contingent reasoning rather than generic skills. | GarethManning/ | 840 | — | ~9.9k | Automated safety check: Pass | Unknown | 1 mo ago |
| 9 | Design a structured outdoor learning sequence embedding curriculum objectives in an available outdoor space. | GarethManning/ | 840 | — | ~5.8k | Automated safety check: Pass | Unknown | 1 mo ago |
| 10 | 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. | GarethManning/ | 840 | — | ~3.8k | Automated safety check: Pass | Unknown | 1 mo ago |
| 11 | Design structured perspective-taking activities with anti-projection guardrails. | GarethManning/ | 840 | — | ~4.5k | Automated safety check: Pass | Unknown | 1 mo ago |
| 12 | Provide graduated assistance from abstract conceptual nudge to concrete procedural step, with reflection required before each escalation. | GarethManning/ | 840 | — | ~3.8k | Automated safety check: Pass | Unknown | 1 mo ago |
| 13 | Require the learner to explain a concept in their own words before the AI evaluates or extends it. | GarethManning/ | 840 | — | ~3.7k | Automated safety check: Pass | Unknown | 1 mo ago |
| 14 | Wrap a learning session in a plan → monitor → reflect cycle. | GarethManning/ | 840 | — | ~4.1k | Automated safety check: Pass | Unknown | 1 mo ago |
| 15 | When a learner gets something wrong or feels stuck, require them to diagnose the problem before receiving help. | GarethManning/ | 840 | — | ~3.7k | Automated safety check: Pass | Unknown | 1 mo ago |
| 16 | Review the week using accumulated session evidence — retrieval rates, hint depths, calibration accuracy, transfer and unassisted results. | GarethManning/ | 840 | — | ~4.2k | Automated safety check: Pass | Unknown | 1 mo ago |
