CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

make-instructions

Create and evaluate VS Code file-based instructions (.instructions.md files). Use when asked to create, scaffold, or add file-based instructions for Copilot. Generates scoped instructions and a paired Vally harness eval.

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

—

The risk profile of this skill

The canonical home for this skill is make-instructions in dotnet/efcore

SKILL.md
Quality
Evals
Security

Quality

Content

78%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A tight, well-structured skill body: a five-step workflow with checklists, concrete file paths and templates, and an explicit when-not-to-use section. The main residual gaps are minor redundancy between the pitfalls table and checklists, and the absence of an inline error-recovery loop after the Step 5 verification checklist.

Suggestions

Add a one-line feedback loop after the Step 5 checklist (e.g., 'If any check fails, fix the file and re-run the full checklist') to earn full workflow-clarity credit.

Trim overlap between the 'Common Pitfalls' table and the Step 1/Step 5 checklist items by keeping each point in only one place.

Include a minimal inline eval.yaml skeleton (2-3 lines) in Step 5 so the harness-eval step is executable without opening the external README.

DimensionReasoningScore

Conciseness

Efficient overall — concrete rules, tables, and templates with almost no padding — but the 'Common Pitfalls' table partially repeats checklist items from Steps 1 and 5 (applyTo breadth, vague guidance), and the 'Recommended sections' template is lightly padded.

4 / 5

Actionability

Mostly executable: exact paths ('.github/instructions/<topic>.instructions.md'), a concrete YAML frontmatter template, example applyTo globs, and a deterministic eval-id naming rule. The Vally eval step, however, defers execution to an external 'eng/harness-evaluation/README.md' rather than giving even a minimal inline skeleton.

4 / 5

Workflow Clarity

Clear five-step sequence with explicit investigation checkboxes (Step 1) and a verification checklist (Step 5), but there is no feedback loop saying what to do when a checklist item fails (fix and re-verify), and eval validation is delegated to the external README.

4 / 5

Progressive Disclosure

No bundle files exist and none are needed at this scale; sections are well-organized with clear headers, and the single deeper material (harness eval rules) is correctly pushed to a one-level-deep, clearly signaled reference ('eng/harness-evaluation/README.md') rather than inlined.

5 / 5

Total

17

/

20

Passed

Description

87%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: third-person, specific, with an explicit 'Use when' trigger clause covering natural user phrasings and the .instructions.md extension. Only minor gains available from trimming redundancy between sentence one and three and adding one or two synonym triggers.

DimensionReasoningScore

Specificity

Names the domain ('VS Code file-based instructions (.instructions.md files)') and several concrete actions ('Create and evaluate', 'Generates scoped instructions and a paired Vally harness eval'), but the coverage is slightly redundant rather than comprehensive — evaluation scope beyond 'evaluate' is not elaborated.

4 / 5

Completeness

Explicitly answers both: what ('Create and evaluate VS Code file-based instructions (.instructions.md files)') and when ('Use when asked to create, scaffold, or add file-based instructions for Copilot'), with concrete trigger phrases.

5 / 5

Trigger Term Quality

Good natural phrases users would say ('create, scaffold, or add file-based instructions for Copilot') plus the concrete file extension '.instructions.md', but a few common variations like 'Copilot instructions' or 'custom instructions' are missing.

4 / 5

Distinctiveness Conflict Risk

Clear niche — VS Code file-based .instructions.md files for Copilot, including a paired Vally harness eval — with triggers distinct from adjacent skills like Agent Skills or copilot-instructions.md; minimal conflict risk.

5 / 5

Total

18

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

dotnet/dotnet

Path

src/efcore/.agents/skills/make-instructions/SKILL.md

Revision

1aed6a1

Reviewed

Table of Contents

DiscoveryImplementationValidation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.

Claim skill