documentation by evgeniiperov
Scaffold Exercises evgeniiperov/scaffold-exercises
Create exercise directory structures with sections, problems, solutions, and explainers that pass linting.
What it changes View full report → Passed 12 of 16 test cases with the skill, and 5 of 16 without it.
Without skill 32%
With skill 73%
Checks it passed that the model alone missed and 9 more in the full report
10 fixed6 passed either way5 still failing1 broke
Pass-rate lift +41 pp
Tokens +3%
Agent turns 0%
Response time -65% Model gemini-3.6-flashMeasured 8/6/2026 v1 16 of 22 cases passed with skill · 16 comparable
Use this skill Claude Code DecimalAI agent CLI & files
Save it into your project's skills folder. Claude Code picks it up in its next session.
curl -fsSL --create-dirs -o .claude/skills/evgeniiperov-scaffold-exercises/SKILL.md https://app.decimal.ai/s/evgeniiperov-scaffold-exercises/SKILL.md Copy command Copy SKILL.md
Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add evgeniiperov-scaffold-exercises, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"
Linked stays up to date: your agents get the author's new versions automatically.
Editable copy is yours to change; the author's updates won't reach it.
Install linked skill Create editable copy
1 · One-time — install the CLI (
docs ↗ )
$ pip install "decimalai>=0.15"Copy
2 · Get the skill — writes .agents/skills/evgeniiperov-scaffold-exercises/ and pins it in .decimal/skills.lock
$ decimalai skills add evgeniiperov-scaffold-exercisesCopy
Copy link Copy README badge Copy SKILL.md No CLI? Get the same file — curl · raw file $ curl -fsSL --create-dirs -o .claude/skills/evgeniiperov-scaffold-exercises/SKILL.md https://app.decimal.ai/s/evgeniiperov-scaffold-exercises/SKILL.mdCopy
Safety checks: 3 of 3 passed
Code scan Clean Intent Passed Content Clean
Overview Benchmark Contents Activity Versions 1 Ratings 0
See it in action One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.
Prompt How should section 05 exercise 03 titled 'Context Windows' be named inside section `exercises/05-context/`?
What was checked, without and with the skill Checked Without skill With skill Formats exercise directory name as 05.03-context-windows
Show both answers
What's inside The instructions your model reads when the skill loads.
SKILL.md 101 lines single file
Scaffold Exercises
Create exercise directory structures that pass pnpm ai-hero-cli internal lint, then commit with git commit.
Directory naming
Sections : XX-section-name/ inside exercises/ (e.g., 01-retrieval-skill-building)Exercises : XX.YY-exercise-name/ inside a section (e.g., 01.03-retrieval-with-bm25)Section number = XX, exercise number = XX.YY
Names are dash-case (lowercase, hyphens)
Exercise variants
Each exercise needs at least one of these subfolders:
problem/ - student workspace with TODOssolution/ - reference implementationexplainer/ - conceptual material, no TODOs
When stubbing, default to explainer/ unless the plan specifies otherwise.
Required files
Each subfolder (problem/, solution/, explainer/) needs a readme.md that:
Is not empty (must have real content, even a single title line works)
Has no broken links
When stubbing, create a minimal readme with a title and a description:
# Exercise Title
Description here
If the subfolder has code, it also needs a main.ts (>1 line). But for stubs, a readme-only exercise is fine.
Workflow When it activates Automatically, when a task matches.
Use when user wants to scaffold exercises, create exercise stubs, or set up a new course section.
Track record Benchmark 12 / 16
test cases passed, vs 5 / 16 without
Adoption
Users 1
Times used 18 View activity → Safety and source details
SkillSafety ✓ 3 of 3 passed ✓ Code scan 15 of 15 checks clean
0 critical · 0 warning · 0 info — scanner v4 — 8/2/2026
View 15 scanner checks live_secret remote_code_execution reverse_shell data_exfiltration ssrf_metadata agent_snooping anti_refusal destructive_commands obfuscated_unicode unicode_homoglyph opaque_blob suspicious_url tool_overreach trigger_abuse prompt_injection_phrasing
✓ Intent Safe
LLM judge · does the skill do what it claims
✓ Content Clean
LLM judge · policy & harmful-content review
Source Imported License MITImported 8/2/2026Version v1