CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-customization

**WORKFLOW SKILL** — Create, update, review, fix, or debug VS Code agent customization files (.instructions.md, .prompt.md, .agent.md, SKILL.md, copilot-instructions.md, AGENTS.md). USE FOR: saving coding preferences; troubleshooting why instructions/skills/agents are ignored or not invoked; configuring applyTo patterns; defining tool restrictions; creating custom agent modes or specialized workflows; packaging domain knowledge; fixing YAML frontmatter syntax. DO NOT USE FOR: general coding questions (use default agent); runtime debugging or error diagnosis; MCP server configuration (use MCP docs directly); VS Code extension development. INVOKES: file system tools (read/write customization files), ask-questions tool (interview user for requirements), subagents for codebase exploration. FOR SINGLE OPERATIONS: For quick YAML frontmatter fixes or creating a single file from a known pattern, edit the file directly — no skill needed.

74

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

85%

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

A well-organized, token-efficient overview that uses tables effectively and points cleanly to real one-level-deep reference files with a clear creation workflow and validation checkpoint. The main gap is that the central file-creation step pushes concrete templates and frontmatter examples into the references instead of providing inline copy-paste guidance.

Suggestions

Inline a minimal frontmatter template (e.g. a 3-line description/applyTo example) in the 'Create the File' step so the core action is copy-paste ready without opening a reference.

Add a short before/after example of a quoted colon-containing description in the 'YAML frontmatter silent failures' pitfall to make the fix immediately executable.

In the 'Validate' step, add an explicit recovery loop (e.g. 'if frontmatter fails to parse, quote the value and re-verify') so the validation checkpoint has a feedback path.

DimensionReasoningScore

Conciseness

The body is lean: Decision Flow and Quick Reference tables deliver dense information, with no explaining of concepts Claude already knows and no padded prose, so every section earns its place.

3 / 3

Actionability

Paths, decision rules, and validation checks are concrete, but the core "Create the File" step defers detail ("Use the location tables in each reference file", "Add the body content following the templates") rather than providing copy-paste-ready frontmatter or template examples inline, leaving a key detail external.

2 / 3

Workflow Clarity

The Creation Process is a clearly numbered sequence (1-4) with an explicit validation checkpoint in step 4 (confirm location, verify frontmatter syntax, check description); the absent retry loop is not disqualifying since creating customization files is neither destructive nor batch-oriented.

3 / 3

Progressive Disclosure

SKILL.md acts as an overview and signals six one-level-deep references via a markdown-link Quick Reference table; all referenced files were verified to exist, and detailed templates are appropriately split out rather than inlined.

3 / 3

Total

11

/

12

Passed

Description

100%

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 highly specific, well-structured description with explicit positive and negative trigger guidance and clear scoping to VS Code agent customization files. It clearly communicates both what the skill does and when to invoke it while actively reducing conflict risk.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ("Create, update, review, fix, or debug") plus specific operations like "configuring applyTo patterns" and "defining tool restrictions", matching the score-3 anchor for multiple specific concrete actions.

3 / 3

Completeness

Explicitly answers "what" (create/update/review/fix/debug customization files) and "when" via an explicit "USE FOR" trigger list plus "DO NOT USE FOR" negatives and a "FOR SINGLE OPERATIONS" carve-out, satisfying the score-3 anchor for both what and when with explicit triggers.

3 / 3

Trigger Term Quality

The "USE FOR" list surfaces natural phrases a user would say ("saving coding preferences", "troubleshooting why instructions/skills/agents are ignored or not invoked", "fixing YAML frontmatter syntax"), giving good coverage of domain-natural terms.

3 / 3

Distinctiveness Conflict Risk

Niche is sharply scoped to VS Code agent customization files, and the explicit "DO NOT USE FOR" boundary (general coding, MCP, extension dev) makes triggering for the wrong skill unlikely, matching the score-3 clear-niche anchor.

3 / 3

Total

12

/

12

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

15

/

16

Passed

Repository
posit-dev/positron
Reviewed

Table of Contents

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.