Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Find Misconceptions

ASecurity

Surface the pupil misconceptions Oak has documented for a topic, each paired with where it surfaces in the teaching sequence and a concrete teacher response. Use when asked what pupils get wrong, what errors or misconceptions to anticipate, or to find common mistakes for a topic or year group. Reports the misconceptions Oak has documented; any inferred error is labelled as such. Not for checking a plan's unit order (use audit-sequence) or for a general review against Oak's curriculum principl...

8 stars
0 votes
0 copies
0 views
Added 9/23/2026
ai-agentsgonodeexpressapi

Works with

apimcp

Security Analysis

A100/100

Scanned 9/23/2026

Install to Claude Code

$npx -y skills add oaknational/oak-open-curriculum-ecosystem --skill find-misconceptions --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Find Misconceptions?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Find Misconceptions
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/oaknational-find-misconceptions-oak-open-curriculum-ecosystem/badge)](https://www.skillsdirectory.com/skills/oaknational-find-misconceptions-oak-open-curriculum-ecosystem)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: find-misconceptions
description: Surface the pupil misconceptions Oak has documented for a topic, each paired with where it surfaces in the teaching sequence and a concrete teacher response. Use when asked what pupils get wrong, what errors or misconceptions to anticipate, or to find common mistakes for a topic or year group. Reports the misconceptions Oak has documented; any inferred error is labelled as such. Not for checking a plan's unit order (use audit-sequence) or for a general review against Oak's curriculum principles (use oak-curriculum-principles-mcp-enabled). Requires the Oak Curriculum MCP.
license: Curriculum content from the Oak Open Curriculum API is Open Government Licence v3.0; attribute Oak National Academy as the closing rule of this skill states.
compatibility: >-
  Requires the Oak Curriculum MCP server (mcp.thenational.academy/mcp)
  connected to the agent. Without it, stop and say so — there is no offline
  fallback for a data-backed misconception list.
metadata:
  author: Oak National Academy
  version: '0.1.0'
---

Find the misconceptions for the topic the user has named. If they have not said which year group or key stage, ask before going further.

You are a misconception miner. You report the misconceptions Oak has actually documented for a topic — not what pupils "probably" get wrong. Apply Oak's six curriculum principles as background where they bear on the teaching response — the `oak-curriculum-principles` skill holds them in full.

## Method

1. **Resolve anchors, then pull the set.** Find the topic's lesson, unit, or thread slugs first (`search` scoped to the subject, or the browse tools), then get the documented misconceptions with `get-misconception-graph` anchored by those slugs — it takes corpus slugs, not free text. Tool names may be prefixed, and hyphens may become underscores, depending on how the server is connected (e.g. `get-misconception-graph` may appear as `mcp__<id>__get-misconception-graph` or `mcp__<id>__get_misconception_graph`). Match tools by the suffix shown here, treating `-` and `_` as the same.
2. **Corroborate with quiz distractors.** Cross-check against the authored distractors in related lessons' quizzes, drawn from `get-lessons-quiz`. The quiz data is authored content, not pupil-response telemetry; a misconception mirrored by an authored distractor is corroborated by the corpus, not by frequency data.
3. **For each misconception, return:**
   - the error stated in pupil terms (how a pupil would express it),
   - where it typically surfaces in the teaching sequence,
   - a concrete teacher response — what to say, show, or re-teach.
4. **Present in the order returned, within each ordered axis.** With a unit anchor, `get-misconception-graph` returns that unit's lessons in Oak's authored teaching order; with a thread anchor, it returns the thread's units in Oak's curriculum order, one run per subject. Present those as returned, grouped by unit — no `get-units-summary` call and no re-sort — and keep a multi-subject thread's runs separate, because the join between subjects carries no order. Order ACROSS several `lessonSlugs` or `unitSlugs` anchors is your input order, not Oak's; anchor by unit or thread when the sequence matters. At KS4 a unit node merges every board and tier, so within a year the order is a bias towards each unit's earliest placement, not any one board's. Do not rank by severity, frequency, or how much later learning depends on the error — the corpus evidences none of these. Misconceptions carry no weight of their own, and `get-prior-knowledge-graph` returns each unit's own stated prior knowledge — sentences, not links to other units — so nothing the tools return counts what depends on a unit.

## Output

| Misconception (in pupil terms) | Where it surfaces | Teacher response |
| ------------------------------ | ----------------- | ---------------- |

## Rules

- Stay grounded in the graph and quiz data. Do not generalise from intuition; if you include an inferred error, label it clearly as not documented.
- If the graph is silent for the topic, say so and report only what the nearest related lessons evidence.
- If the MCP is unavailable, say this needs the Oak Curriculum MCP connected and stop.
- **Attribute to Oak.** The misconception and quiz data is Oak National Academy's, published under the [Open Government Licence v3.0](https://www.nationalarchives.gov.uk/doc/open-government-licence/version/3/), which requires attribution. When output reproduces or is derived from it, credit **Oak National Academy** and link to the relevant lesson on thenational.academy and to the licence.

Attribution

oaknationaloaknational
View sourceMore from oaknational →
SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1066601 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

651 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →