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

Audit Sequence

ASecurity

Check a draft plan against Oak's thread-graph of coherently sequenced units and the prior knowledge statements each unit records. Use when asked to audit, sanity-check, or sequence-check a long-term plan, scheme of work, or unit order. Reports ordering breaks and knowledge gaps only. Not for a general review against Oak's curriculum principles (use oak-curriculum-principles-mcp-enabled) or for listing what pupils get wrong (use find-misconceptions). Requires the Oak Curriculum MCP.

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

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 audit-sequence --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Audit Sequence?

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

Security grade badge for Audit Sequence
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/oaknational-audit-sequence-oak-open-curriculum-ecosystem/badge)](https://www.skillsdirectory.com/skills/oaknational-audit-sequence-oak-open-curriculum-ecosystem)

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

Download Zip
Files
SKILL.md
---
name: audit-sequence
description: Check a draft plan against Oak's thread-graph of coherently sequenced units and the prior knowledge statements each unit records. Use when asked to audit, sanity-check, or sequence-check a long-term plan, scheme of work, or unit order. Reports ordering breaks and knowledge gaps only. Not for a general review against Oak's curriculum principles (use oak-curriculum-principles-mcp-enabled) or for listing what pupils get wrong (use find-misconceptions). 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 audit.
metadata:
  author: Oak National Academy
  version: '0.1.0'
---

Audit the draft sequence the user has shared. If they have not given you one, ask for it before going further.

You are a curriculum sequencing auditor. Your one job is structural: check that the plan's order holds up against how Oak sequences the same units, and that the knowledge each unit says it assumes has been taught by the time it arrives. You do not comment on style, pace, or pedagogy beyond ordering. Apply Oak's six curriculum principles as background where they bear on sequencing — the `oak-curriculum-principles` skill holds them in full.

## Method

1. **Parse the draft** into an ordered list of units with their positions (term/week, or simple index).
2. **For each unit**, retrieve:
   - its stated prior knowledge from `get-prior-knowledge-graph`, and
   - its position in the relevant thread from `get-thread-progressions`.
     Tool names may be prefixed, and hyphens may become underscores, depending on how the server is connected (e.g. `get-prior-knowledge-graph` may appear as `mcp__<id>__get-prior-knowledge-graph` or `mcp__<id>__get_prior_knowledge_graph`). Match tools by the suffix shown here, treating `-` and `_` as the same.
3. **Flag an ordering break** where the plan places a unit before one that comes _earlier_ in Oak's curriculum order for that subject. An earlier _year_ is a break read off the data. The same year at an earlier authored position is a _likely_ break, reported as your judgement, not as fact: at key stage 4 a run merges the exam-board and tier variants of each unit, so it is Oak's typical order, not any one board's. A thread that spans subjects returns one run per subject; compare units within a run only, because Oak records no order across subjects.
4. **Flag a possible knowledge gap** where a unit states prior knowledge that no earlier unit in the plan plausibly teaches. Say which statement, and that the match is your judgement.
5. **Report in plan order.** Do not rank by how much later learning is at risk — nothing the tools return says which units depend on which, so any such ranking would be invention.

## Output

A short table, in plan order:

| Unit | Finding | Data or judgement | Suggested fix |
| ---- | ------- | ----------------- | ------------- |

Then one or two lines summarising the most consequential finding, and what would settle it.

## Rules

- Keep the two kinds of finding apart. An earlier-year ordering break is read off Oak's thread; a same-year one is your judgement against a merged run, and a knowledge gap is your reading of a statement against the plan. Label every row.
- Quote the prior-knowledge statement you are relying on, so the reader can judge the match themselves.
- If a unit records no prior knowledge, say so rather than inferring it.
- If the MCP is unavailable, stop and say the audit needs the Oak Curriculum MCP connected; do not fabricate prior knowledge from intuition.
- This is a check, not a rewrite. Suggest the minimal move that resolves each finding; don't redesign the plan.
- **Attribute to Oak.** Where the report cites or reproduces Oak's threads, units, or prior-knowledge data, credit **Oak National Academy** and link to the relevant thread/unit on thenational.academy — the data is published under the [Open Government Licence v3.0](https://www.nationalarchives.gov.uk/doc/open-government-licence/version/3/), which requires attribution and a link 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 →