build-artifacts
Skill114 starsChanged 8 months agoMITView on GitHub
Generate SKILL.md and TOC.md for a documentation package. Use standalone to regenerate artifacts without re-downloading.
In this repository5 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- web/CLAUDE.mdCLAUDE.md
- build-docsSkill
- download-docsSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 1 is distinctive, and 4 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 32
If contents/ not found:
- Very specific: line 43
Check for --force flag
- Very specific: line 57
If both exist and no --force flag:
- Distinctive: line 78
Read the appropriate template based on tier:
- Very specific: line 91
Create vault/packages/{config_name}/{version}/TOC.md following the template structure.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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
Build Artifacts
Generate SKILL.md and TOC.md for an existing documentation package.
Usage
/build-artifacts prisma@latest # Generate artifacts
/build-artifacts prisma@latest --force # Regenerate even if existsInput
$ARGUMENTS format: {config_name}@{version} (e.g., prisma@latest, nextjs@16.1.3)
Optional flags:
--force- Regenerate even if artifacts already exist
Prerequisites
The contents/ directory and olore-lock.json must already exist at vault/packages/{config_name}/{version}/. Run /download-docs first if they don't.
test -d vault/packages/{config_name}/{version}/contents && echo "OK" || echo "NOT_FOUND"If contents/ not found:
error: {config_name}@{version} contents/ not found - run /download-docs firstExecution Steps
Step 1: Parse Arguments and Load Metadata
Parse $ARGUMENTS:
- Extract
config_nameandversionfrom{config_name}@{version} - Check for
--forceflag
Read metadata:
cat vault/packages/{config_name}/{version}/olore-lock.json
cat vault/configs/{config_name}.jsonStep 2: Check if Already Built
test -f vault/packages/{config_name}/{version}/SKILL.md && test -f vault/packages/{config_name}/{version}/TOC.md && echo "EXISTS" || echo "NOT_FOUND"If both exist and no --force flag:
skip: {config_name}@{version} artifacts already built (use --force to rebuild)Return early.
Step 3: Determine Tier
file_count=$(find vault/packages/{config_name}/{version}/contents -type f \( -name "*.md" -o -name "*.mdx" \) | wc -l)
total_size=$(du -sk vault/packages/{config_name}/{version}/contents | cut -f1)| Tier | Criteria |
| 1 | < 30 files AND < 500KB |
| 2 | 30-100 files OR 500KB-2MB |
| 3 | > 100 files OR > 2MB |
Step 4: Generate TOC.md
Read the appropriate template based on tier:
# Tier 1
cat vault/packages/docs-packager/1.0.0/templates/toc-tier1.md
# Tier 2
cat vault/packages/docs-packager/1.0.0/templates/toc-tier2.md
# Tier 3
cat vault/packages/docs-packager/1.0.0/templates/toc-tier3.mdCreate vault/packages/{config_name}/{version}/TOC.md following the template structure.
Step 5: Generate SKILL.md
IMPORTANT: The name field MUST be olore-{config_name}-{version} to match the installed folder name.
Read the appropriate template based on tier:
# Tier 1
cat vault/packages/docs-packager/1.0.0/templates/skill-tier1.md
# Tier 2
cat vault/packages/docs-packager/1.0.0/templates/skill-tier2.md
# Tier 3
cat vault/packages/docs-packager/1.0.0/templates/skill-tier3.mdCreate vault/packages/{config_name}/{version}/SKILL.md following the template structure.
Step 6: Return Summary
Return ONLY a brief summary:
done: {config_name}@{version} artifacts built (SKILL.md + TOC.md), tier {tier}Outputs
vault/packages/{config_name}/{version}/SKILL.md- Skill definitionvault/packages/{config_name}/{version}/TOC.md- Table of contents
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.

