New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Official agent skill

Irac Practice

by anthropics in anthropics/claude-for-legal

Grade an IRAC essay for structure, issue-spotting, rule accuracy, analysis depth, and organization.

OfficialApache-2.0Auto-check passed

Install Irac Practice

skills CLI
$ npx skills add anthropics/claude-for-legal --skill irac-practice -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install anthropics/claude-for-legal irac-practice --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/anthropics/claude-for-legal.git skills-src && mkdir -p .claude/skills && cp -r skills-src/law-student/skills/irac-practice .claude/skills/irac-practice && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
irac-practice
GitHub stars
9.6k
Used in
3 other repos
Token cost
~2.6k tokens
SKILL.md length
943 words
Files
1
Skills in repo
147
Repo updated
First seen
Licence
Apache-2.0

At a glance

Grade an IRAC essay for structure, issue-spotting, rule accuracy, analysis depth, and organization.

  • Works in 4 steps: Establish what we're grading → Read the answer closely → Structured feedback → …
  • The user says grade my IRAC
  • SKILL.md covers Real-matter check, Purpose, Confidence discipline and Load context, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Irac Practice is an agent skill from anthropics/claude-for-legal, published by the product's own GitHub organization. Grade an IRAC essay for structure, issue-spotting, rule accuracy, analysis depth, and organization. Does NOT rewrite the essay or show a model answer; tracks patterns across sessions. Use when the user says "grade my IRAC", "check my essay", or "I wrote this, give me feedback".

Its SKILL.md is about 2.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: A suite of plugins for legal workflows. The licence is Apache-2.0.

When your agent uses it

  • The user says grade my IRAC
  • Give me feedback

Example prompts

  • “grade my IRAC”
  • “check my essay”
  • “I wrote this, give me feedback”
  • “/irac-practice”

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Establish what we're grading
  2. Read the answer closely
  3. Structured feedback
  4. Track patterns

What it can do on your machine

Read from SKILL.md and the folder at commit 4a6c651. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Irac Practice loads about 2.6k tokens when it runs. Until then it costs about 73 tokens; SKILL.md has 943 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~73
When it runs · the whole SKILL.md, loaded when a task matches
~2.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from anthropics/claude-for-legal at commit 4a6c651, republished under its Apache-2.0 licence (© anthropics). 943 words, ~2,594 tokens.

Download SKILL.mdSave it as .claude/skills/irac-practice/SKILL.md (or your agent's skills folder).
name
irac-practice
description
Grade an IRAC essay for structure, issue-spotting, rule accuracy, analysis depth, and organization. Does NOT rewrite the essay or show a model answer; tracks patterns across sessions. Use when the user says "grade my IRAC", "check my essay", or "I wrote this, give me feedback".
argument-hint
[paste essay OR path to draft OR --generate-hypo]

/irac-practice

  1. Load ~/.claude/plugins/config/claude-for-legal/law-student/CLAUDE.md → classes, exam formats, outline locations, learning style.
  2. Apply the framework below.
  3. Establish mode: student-provided hypo + answer, OR skill-generated hypo with student's answer.
  4. Read the answer closely. Map against expected IRAC components.
  5. Output structured feedback: issues spotted/missed, rule accuracy, analysis depth, organization, grade band, top 3 fixes, at most 1-2 labeled example phrasings (never a full IRAC model).
  6. Append to ~/.claude/plugins/config/claude-for-legal/law-student/irac-sessions/[student]/tracker.md for pattern detection. Surface patterns after 3+ sessions.

Real-matter check

If the question the student is asking sounds like it's about a REAL situation — their lease, their parking ticket, their family's business, their friend's arrest, a real dollar amount, a real deadline, a real party name — stop.

"This sounds like a real situation, not a hypothetical. I can't give you legal advice, and you can't give it either — you're not a lawyer yet. If this is real, [the person] needs an actual lawyer: legal aid, your school's clinic, a lawyer referral service (your jurisdiction's bar association, law society, or legal aid body), or (if there's money) a private attorney. I'm happy to help you understand the general legal concepts involved, but that's study, not advice."

Watch for: real names, real addresses, real dates, specific dollar amounts, "my landlord/boss/parent/friend," "I got a ticket/letter/notice," deadlines measured in days. Any one of these is a trigger.

Purpose

1L writing is mostly IRAC. 2L-3L writing that touches legal analysis is IRAC under the hood. The exam rewards structure as much as content. This skill grades structure — did you spot the issues, did you state the rules correctly, did you apply rules to facts or just restate both?

Does not rewrite the essay. Ever. The whole point is that you learn by writing, getting specific structural feedback, and rewriting yourself.

Confidence discipline

  • Structure grading (did you IRAC? did you organize? did you use topic sentences?) — confident. Structure is structure.
  • Issue-spotting feedback (did you spot the issue presented?) — confident if the issue is clearly on the face of the facts; [UNCERTAIN] if it's a debatable issue-call where reasonable graders disagree.
  • Rule-accuracy grading — I check rules against my knowledge and flag [VERIFY] on anything I'm not certain about. I do not silently fail your correct rule statement because I wasn't sure.
  • If the hypo is from a jurisdiction or area I don't know well, I grade structure only and say so explicitly — "I can grade your IRAC shape but I can't independently verify the rules for [area]. Cross-check with your outline."

Load context

  • ~/.claude/plugins/config/claude-for-legal/law-student/CLAUDE.md → current classes, exam formats, outline locations, learning style
  • ~/.claude/plugins/config/claude-for-legal/law-student/irac-sessions/[student]/tracker.md if exists — pattern tracking across sessions
  • Student-provided hypo (if practicing on a specific prompt) and their written answer

Workflow

Step 1: Establish what we're grading

Two modes:

  • Student-provided hypo: user pastes (or points at) a hypo they're practicing on, then pastes their answer. Skill grades against the hypo.
  • Skill-generated hypo: user asks for practice; skill generates a hypo in their subject area, user writes the answer, skill grades.

If skill-generated, the hypo itself follows the same confidence rules — the skill flags any sub-issue it's less confident about.

Show full SKILL.md (431 more words)Show less
Step 2: Read the answer closely

Don't skim. Read the student's answer as if grading it. Map it against expected IRAC components:

  • Issues: what issues did they spot? (List them.) What issues are in the hypo that they didn't spot?
  • Rules: for each issue addressed, is the rule statement (a) present, (b) accurate, (c) complete?
  • Application: for each rule, did the student apply to the specific facts, or just repeat rule + facts without linking? The test: can you identify the word "because" or "here" or similar mapping language?
  • Conclusion: did they reach one? Is it responsive to the call?
  • Organization: IRAC / CRAC order? Topic sentences? Paragraph breaks that make sense?
Step 3: Structured feedback

Output per component. No rewriting. Specific, not generic.

markdown
# IRAC Grade — [date]

**Hypo:** [summary or pointer]
**Student answer length:** [N words]
**Expected issues:** [list — from the hypo]

---

## Issue spotting

**Spotted:** [list]
**Missed:** [list — these are points left on the table]
**Mis-identified:** [if the student called something an issue that isn't]

[If an issue is [UNCERTAIN: debatable issue-call], note: "your grader might agree or disagree here; defensible read."]

## Rule statements

For each issue addressed:

- **[Issue 1]:** [Accurate / partially correct / wrong / missing element] — [what's off, one sentence] — [VERIFY if skill less than confident on rule]
- **[Issue 2]:** ...

## Analysis

For each rule the student stated:

- **[Issue 1] — did you apply?** [Yes, applied to [specific facts] | Partially — you mentioned [facts] but didn't link to rule element | No — you restated rule then facts without mapping]
- [If not applied well: "what you needed to do: connect [specific fact] to [specific rule element]. Not 'defendant acted negligently because of the facts' — 'defendant breached the duty of care because [specific fact] means [specific conclusion about the element].'"]

## Organization

- **Order:** IRAC? CRAC? Something else?
- **Paragraph structure:** topic sentence leading? Or buried?
- **Transitions:** do issues flow, or is it a wall of text?
- **Call responsiveness:** did you answer what was asked?

## If graded

A rough calibration — not a precise score, but a band:

- **If this were graded today: [Pass / borderline / not yet]** — reasoning in one sentence

## Top three fixes

Rank-ordered, one sentence each. What to rewrite if you only had time for three changes.

1.
2.
3.

## Citation check

Any cases, statutes, or rules referenced in this feedback were generated by an AI model and have not been verified. Before you rely on them in a rewrite or a graded essay, look them up on Westlaw, CourtListener, or your school's research tool. AI-generated citations are sometimes fabricated or misquoted.

## Writing sample — labeled example only (do not copy)

If there's a specific structural move the student missed (e.g., rule-application mapping), show ONE example sentence or paragraph that illustrates the move. Explicitly label it:

> "Here's one way to frame an analysis sentence — write your own version, don't copy this:
> [example]"

Use sparingly. One per grade, max two. Never a full IRAC example.

**Never on the student's actual substantive issue.** Example phrasings illustrate the structural move in generic placeholder form (e.g., "[fact] means [conclusion about element] because [reasoning]"). They cannot show what an analysis sentence or paragraph would look like on the exact hypo or issue the student is writing about — that crosses from "seeing the move" into "being handed the answer." If the student is writing about negligence in a car accident hypo, the example must use a different subject area or abstract placeholders, not a negligence analysis sentence.
Step 4: Track patterns

Append to ~/.claude/plugins/config/claude-for-legal/law-student/irac-sessions/[student]/tracker.md:

markdown
## [date] — [subject / hypo topic]
- Issues missed: [list]
- Rule accuracy: [% or qualitative]
- Analysis gap: [specific pattern — e.g., "restates rule without applying"]
- Organization: [ok / weak / strong]

After 3+ sessions, surface patterns:

  • "You keep missing counterarguments — three sessions in a row."
  • "You're strong on Issue + Rule but consistently weak on Application."
  • "Your organization is strong; the gap is at rule-accuracy. Drill black-letter rules with /law-student:flashcards."

Pattern detection is the long-term value of this skill. One-off feedback helps one essay; pattern feedback changes how you study.

Integration with other skills

  • legal-writing: for non-IRAC writing (memos, briefs, papers), use /law-student:legal-writing instead
  • socratic-drill: if issue-spotting is the recurring gap, /law-student:socratic-drill on issue-spotting for the subject before more essay practice
  • flashcards: if rule accuracy is the gap, flashcards are the right tool
  • outline-builder: if the student's rule is genuinely wrong in their outline, fixing the outline fixes many future IRACs

Close with the next-steps decision tree

End with the next-steps decision tree per CLAUDE.md ## Outputs. Customize the options to what this skill just produced — the five default branches (draft the X, escalate, get more facts, watch and wait, something else) are a starting point, not a lock-in. The tree is the output; the lawyer picks.

What this skill does not do

  • Rewrite the student's answer. Ever. No exceptions. Labeled example phrasings (one or two, clearly marked) are permitted to illustrate a structural move; they cannot be copied into the student's answer.
  • Show a model answer. The student has to build the model in their head. Showing one short-circuits the learning.
  • Grade content correctness on jurisdictions or areas the skill doesn't know well. In those cases, skill grades structure only and says so — "I can grade your IRAC shape but can't verify rules here."
  • Give a precise numeric score. Pass/borderline/not-yet bands only. Grading is qualitative; precision is false precision.
  • Substitute for a professor's grading. Professors have rubrics and preferences this skill doesn't know. Use feedback to improve; don't treat it as the final word.

© anthropics, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in law-student/skills/irac-practice of anthropics/claude-for-legal.

Open the folder on GitHubat commit 4a6c651

Used in 3 other repositories

We found 3 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 3 other GitHub owners. This page covers the copy in anthropics/claude-for-legal, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Irac Practice next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Irac Practice compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Irac Practice this skillanthropics/claude-for-legal9.6k3 repos~2.6kAutomated safety check: PassApache-2.0
Codex Rules Referencecode-yeongyu/oh-my-openagent70k—~269Automated safety check: PassCustom licence
Rules Distillationaffaan-m/ECC275k2 repos~2.3kAutomated safety check: PassMIT
Crossframe Essaysickn33/agentic-awesome-skills47k1 repos~2kAutomated safety check: PassMIT
Hookify Rulesaffaan-m/ECC275k—~605Automated safety check: NotesMIT
Rules Distillaffaan-m/ECC275k—~1.5kAutomated safety check: PassMIT

Similar skills

  • Codex Rules Reference

    code-yeongyu/oh-my-openagent

    Explains how the Codex Rules plugin injects project instructions and file-specific rules into a session, which rule files it reads and which settings control it.

    70k GitHub stars~269 tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Rules Distillation

    affaan-m/ECC

    Scans installed skills for principles that recur across them and proposes rule-file changes: append, revise, add a section, create a file or leave as covered.

    275k GitHub starsUsed in 2 repos~2.3k tokens
    Agent WorkflowsAuto-check passed

  • Crossframe Essay

    sickn33/agentic-awesome-skills

    A skill your agent uses when explicit CrossFrame work needs a Chinese critical insight essay, commentary, concept essay, public piece, or structure-to-article draft after diagnosis.

    47k GitHub starsUsed in 1 repo~2k tokens
    Writing & ContentAuto-check passed

  • Hookify Rules

    affaan-m/ECC

    当用户要求创建hookify规则、编写hook规则、配置hookify、添加hookify规则或需要关于hookify规则语法和模式的指导时，应使用此技能。

    275k GitHub stars~605 tokensUpdated 3 days ago
    Agent WorkflowsAuto-check: notes

  • Rules Distill

    affaan-m/ECC

    スキルをスキャンしてドメイン横断的な原則を抽出し、ルールに蒸留する——既存のルールファイルへの追記、修正、または新規作成

    275k GitHub stars~1.5k tokensUpdated 3 days ago
    Auto-check passed

  • Rules Distill

    affaan-m/ECC

    扫描技能以提取跨领域原则并将其提炼为规则——追加、修订或创建新的规则文件

    275k GitHub starsUsed in 1 repo~1.3k tokens
    Auto-check passed

More from anthropics/claude-for-legal

All 147 skills in this repo

  • Legal Clinic Client Intake

    anthropics/claude-for-legal

    Official

    Structures a legal clinic client intake interview and produces a case summary with cross-area issue spotting, conflict flags and triage classification.

    9.6k GitHub starsUsed in 3 repos~3.2k tokens
    Auto-check passed

  • Supervisor Review Queue

    anthropics/claude-for-legal

    Official

    Holds student work in a queue for a legal clinic professor to approve, edit-then-approve or return before anything reaches clients or courts.

    9.6k GitHub starsUsed in 3 repos~1.1k tokens
    Auto-check passed

  • Tabular Document Review

    anthropics/claude-for-legal

    Official

    Builds a review grid with one row per document and one column per data point, each cell cited to a verbatim quote, built for M&A diligence and other batch reviews.

    9.6k GitHub starsUsed in 3 repos~4.3k tokens
    Auto-check passed

  • Product Launch Legal Review

    anthropics/claude-for-legal

    Official

    Runs a category-by-category legal review of a product launch from a PRD or tracker ticket, calibrated to your team's framework, and writes a review memo in house format.

    9.6k GitHub starsUsed in 2 repos~5k tokens
    Auto-check passed

  • Legal Skills Registry Browser

    anthropics/claude-for-legal

    Official

    Searches watched registries for community legal skills, shows matches with descriptions and offers the full SKILL.md before anything is installed.

    9.6k GitHub starsUsed in 2 repos~620 tokens
    Auto-check passed

  • Contract Renewal Tracker

    anthropics/claude-for-legal

    Official

    Shows which contracts renew soon and when notice must be sent by, working from a maintained renewal register, and warns about missed cancellation windows.

    9.6k GitHub starsUsed in 2 repos~3.1k tokens
    Auto-check passed

Questions about Irac Practice

What does Irac Practice do?

Grade an IRAC essay for structure, issue-spotting, rule accuracy, analysis depth, and organization. Irac Practice is an agent skill from anthropics/claude-for-legal, published by the product's own GitHub organization. Grade an IRAC essay for structure, issue-spotting, rule accuracy, analysis depth, and organization.

When should I use Irac Practice?

Irac Practice fits situations like: the user says grade my IRAC; give me feedback.

How do I install Irac Practice in Claude Code?

Run `npx skills add anthropics/claude-for-legal --skill irac-practice -a claude-code`. Or copy the skill folder (law-student/skills/irac-practice in anthropics/claude-for-legal) into .claude/skills/irac-practice in your project. Claude Code loads it when a task matches its description.

How do I install Irac Practice in Codex?

Run `npx skills add anthropics/claude-for-legal --skill irac-practice -a codex`. Or copy the skill folder (law-student/skills/irac-practice in anthropics/claude-for-legal) into .agents/skills/irac-practice in your project. Codex loads it when a task matches its description.

Can I use Irac Practice in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add anthropics/claude-for-legal --skill irac-practice -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/irac-practice, .gemini/skills/irac-practice, .github/skills/irac-practice and .opencode/skills/irac-practice in your project.

What does Irac Practice need to run?

SKILL.md names no scripts, command-line tools or credentials: Irac Practice is instructions for the agent only.

Does Irac Practice access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Irac Practice safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Irac Practice use?

Irac Practice is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Irac Practice use?

About 2.6k tokens (SKILL.md is roughly 10k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Irac Practice?

Skills that share tags, products or a category with Irac Practice: Codex Rules Reference (code-yeongyu/oh-my-openagent, 70k stars), Rules Distillation (affaan-m/ECC, 275k stars), Crossframe Essay (sickn33/agentic-awesome-skills, 47k stars) and Hookify Rules (affaan-m/ECC, 275k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Irac Practice?

anthropics (a GitHub organization, an official publisher) maintains it in anthropics/claude-for-legal, which has 9,617 GitHub stars. The repository holds 147 skills in this directory. The repository was last updated on September 29, 2026.

Source: anthropics/claude-for-legal on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.