Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Create VS Code file-based instructions (.instructions.md files). Use when asked to create, scaffold, or add file-based instructions for Copilot. Generates .instructions.md with YAML frontmatter and background knowledge content.
.claude/skills/make-instructions/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-16 | ✗→✓ | ▲ Improved | — | — |
| case-03 | ✗→✓ | ▲ Improved | — | — |
| case-14 | ✗→✓ | ▲ Improved | — | — |
| case-05 | ✗→✓ | ▲ Improved | — | — |
| case-04 | ✗→✓ | ▲ Improved | — | — |
This skill helps you scaffold VS Code file-based instructions (.instructions.md files) that provide background knowledge to Copilot about specific parts of the codebase. These files are applied automatically based on glob patterns or semantic matching, giving Copilot domain-specific context when working on matching files.
.github/copilot-instructions.md or AGENTS.md insteadBuild understanding of the area the instructions should cover. Identify:
If the scope is unclear or overlaps with existing instructions, ask the user for clarification.
Instructions files go in .github/instructions/ by default. Pick a descriptive filename:
.github/instructions/<topic>.instructions.mdExamples: csharp-style.instructions.md, query-pipeline.instructions.md, test-conventions.instructions.md
Create the file with the required YAML frontmatter header:
yaml--- name: '<Display Name>' # Optional. Display name in the UI. Defaults to filename. description: '<Short description>' # Optional. Shown on hover. Also used for semantic matching. applyTo: '<glob pattern>' # Optional. Glob pattern relative to workspace root. Omit to require manual attachment or rely on semantic matching only. ---
Common applyTo patterns:
**/*.cs — all C# filestest/** — files under a specific folderWrite concise, actionable Markdown content. Follow these principles:
Recommended sections (adapt as needed):
After creating the file, verify:
.github/instructions/ (or a configured instructions folder).instructions.md and only contains lowercase letters, numbers, and hyphensapplyTo glob matches the intended files.github/copilot-instructions.md or under .agents/skills/| Pitfall | Solution | |---------|----------| | applyTo too broad | Use specific globs; ** applies to every file and wastes context | | Missing applyTo | Without it, instructions won't auto-apply — they require manual attachment or semantic matching via description | | Vague guidance | Replace "write good tests" with something like "add both positive and negative test cases using [ConditionalFact] methods" |
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-16 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-23 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-03 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-12 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-14 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-05 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-04 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-08 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-07 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-01 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-10 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-11 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-21 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-15 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-17 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-22 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-24 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-02 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-20 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-06 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-09 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-13 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-18 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-19 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-25 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 25 cases were attempted, and 24 counted toward the lift figure. The other 1 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +64 percentage points is the difference between those two pass rates over the 24 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
The per-case answers from this run were removed by the retention sweep, so the case table below shows the verdicts without the text either arm produced. The counts above were recorded at the time and are unaffected. Answers are now kept for 180 days.
Other measured skills in the registry, with their headline benchmark lift.