/capstone
Use when the user is ready to apply what they learned to something real: scope a project sized to what they have cleared, write the brief with milestones and a done test, then judge the finished work against it. For single-concept exercises and quizzes, use drill.
$ npx -y skills add OutlineDriven/odin-claude-plugin --skill capstone --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/capstone
Context preview
The summary Claude sees to decide when to auto-load this skill.
Use when the user is ready to apply what they learned to something real: scope a project sized to what they have cleared, write the brief with milestones and a done test, then judge the finished work against it. For single-concept exercises and quizzes, use drill.
SKILL.md
capstone.SKILL.mdname: capstone
description: 'Use when the user is ready to apply what they learned to something real: scope a project sized to what they have cleared, write the brief with milestones and a done test, then judge the finished work against it. For single-concept exercises and quizzes, use drill.'
argument-hint: "What should the project build?"
Turn what the learner has cleared into something runnable, readable, or usable. One project per run.
Scope it
Read `PROGRESS.md` for what is **cleared** (its independent rung passed with no hints). The project may use only cleared concepts plus at most one unfamiliar one; two or more and it is a tutorial. Ask for the domain when the argument does not carry it. No `PROGRESS.md` means ask what the user can already do, once, and size to the answer.
The brief
Write the brief to `capstone-<slug>.md` at the workspace root, per [references/BRIEF-FORMAT.md](references/BRIEF-FORMAT.md). The brief carries the done test, the milestones, and the concepts exercised.
Review it
When the learner brings the finished work back, judge it against the done test and the concept list item by item, then name the concepts the work shows they have not cleared. Hand those to `drill`, which owns the record; this skill writes no progress lines.
Rules
- The done test is observable by someone else. "Understand X" is not a done test.
- The project produces something runnable, readable, or usable. Anything smaller is an exercise; send it to `drill`.
- Review against the brief's done test and concept list, item by item.
- Order milestones so each one leaves something that works.
Read more
name: capstone description: 'Use when the user is ready to apply what they learned to something real: scope a project sized to what they have cleared, write the brief with milestones and a done test, then judge the finished work against it. For single-concept exercises and quizzes, use drill.' argument-hint: "What should the project build?"
Turn what the learner has cleared into something runnable, readable, or usable. One project per run.
Scope it
Read `PROGRESS.md` for what is **cleared** (its independent rung passed with no hints). The project may use only cleared concepts plus at most one unfamiliar one; two or more and it is a tutorial. Ask for the domain when the argument does not carry it. No `PROGRESS.md` means ask what the user can already do, once, and size to the answer.
The brief
Write the brief to `capstone-<slug>.md` at the workspace root, per [references/BRIEF-FORMAT.md](references/BRIEF-FORMAT.md). The brief carries the done test, the milestones, and the concepts exercised.
Review it
When the learner brings the finished work back, judge it against the done test and the concept list item by item, then name the concepts the work shows they have not cleared. Hand those to `drill`, which owns the record; this skill writes no progress lines.
Rules
- The done test is observable by someone else. "Understand X" is not a done test.
- The project produces something runnable, readable, or usable. Anything smaller is an exercise; send it to `drill`.
- Review against the brief's done test and concept list, item by item.
- Order milestones so each one leaves something that works.
Formerly known as the ODIN Claude Plugin. The repo URL stays the same; the brand has matured.
Repo: OutlineDriven/odin-claude-plugin
Other skills on odin.
- /ai-collab-protocols
Surface in-task AI collaboration protocols one tactic at a time, replacing ambiguous references with durable, recoverable handles.
Open skill - /askme
Explore intent with Verbalized Sampling before planning. Use when the task is ambiguous, you need maximum clarifying questions, or you want collaborative or adversarial mode via `/askme`.
Open skill - /ast-grep
Run code analysis and refactoring with ast-grep. Use when doing AST-based modifications, structural search, linting across code shape, or replacing regex-fragile transformations.
Open skill - /atomic-issues-prs
Publish a change-set as atomic GitHub issues or PRs. Use when the user says "atomic PRs" or wants one issue/PR per logical change.
Open skill - /audit-project
Run an iterative multi-agent code audit until critical and high findings are resolved. Use when the user says "audit my code", "find all the bugs", "deep code audit", "iterative review", or "review until clean".
Open skill - /autolearn
Compound a solved problem into a durable in-repo learning doc. Use when a verified non-trivial fix lands, the user says "compound this", "document this fix", or "remember this". This is the automatic-capture entry point; for an explicitly requested one-off write-up, use compound.
Open skill