chapter-artifact
Skill0 starsChanged 2 months agoMITView on GitHub
ACC-owned conventions and templates for the HTML artifacts generated at runtime, one page per chapter plus one lesson summary. The course-conductor reads references/conventions.md (its absolute path arrives as artifact_conventions_path in the nextChapter envelope) before it writes each artifact. Use when writing, reviewing, or fixing an ACC chapter artifact or summary artifact, or when the user asks "what does an ACC artifact look like", "check this artifact against the conventions", or "regenerate the summary page".
In this repository4 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- course-creatorSkill
- course-engineSkill
- lesson-creatorSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 18
The course-conductor, at runtime: After a chapter's verification command passes, the conductor:
- Very specific: line 25
After the e2e gate, the conductor does the same with templates/summary.html.tmpl and writes summary_artifact_path …
- Distinctive: line 29
Anyone reviewing an artifact: Run the checklist. The most common defects: snippets rewritten instead of copied, a generic diagram instead …
- Very specific: line 34
Read references/conventions.md before you write or judge a page.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Chapter Artifact Skill
ACC never pre-authors artifacts. The conductor generates them at runtime, in the learner's workspace, from the code it just wrote. This skill holds the rules and the templates so every artifact looks and reads the same across courses.
Files:
references/conventions.md: the rules. File rules, visual tokens, fixed section order for the chapter page and the summary page, content rules, and a checklist.templates/chapter.html.tmpl: skeleton for one chapter page.templates/summary.html.tmpl: skeleton for the lesson summary page.
Who uses this and when
The course-conductor, at runtime. After a chapter's verification command passes, the conductor:
- Reads
artifact_conventions_path(the absolute path ofreferences/conventions.md, returned bynextChapter). - Copies the shape of
templates/chapter.html.tmpl, fills every{{ placeholder }}, and removes the template comments. - Writes the result to
artifact_path(<workspace>/artifacts/NN-<id>.html). - Calls
verifyChapter. The MCP records the artifact path in state when the file exists.
After the e2e gate, the conductor does the same with templates/summary.html.tmpl and writes summary_artifact_path (<workspace>/artifacts/summary.html).
Lesson authors, at validation time. Open a generated artifact next to the conventions and check the "Checklist" part. A page that fails the checklist means the chapter brief or the tests need work, not the template.
Anyone reviewing an artifact. Run the checklist. The most common defects: snippets rewritten instead of copied, a generic diagram instead of this chapter's flow, test names invented instead of read from the test files.
Rules
templates/chapter.html.tmplis the chapter page.templates/summary.html.tmplis the lesson summary page.- Read
references/conventions.mdbefore you write or judge a page. Every rule lives there.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

