get-search-view-results

Get the current search results from the Search view in VS Code

Quality

69%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./extensions/copilot/assets/prompts/skills/get-search-view-results/SKILL.md

Quality

Content

77%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 short, highly actionable instruction for a single-purpose task, with a clear command, tool, and argument specification. The main flaws are a redundant concept-explanation sentence Claude doesn't need and the absence of a concrete example of the tool invocation.

Suggestions

Delete step 1, which states a fact Claude already knows, and fold any necessary context into the instruction itself.

Add a short example of the actual `copilot_runVscodeCommand` call with `command: "search.action.getSearchResults"` and `skipCheck: true` to make it copy-paste ready.

Trim the trailing justification in step 3 ("to avoid checking if the command exists, as we know it does") to just the operative instruction: pass `skipCheck: true`.

Dimension	Reasoning	Score
Conciseness	Step 1 ("VS Code has a search view, and it can have existing search results") explains a concept Claude already knows, and step 3 pads with "as we know it does". It is mostly efficient, but the unnecessary explanation and trailing justification keep it below a 4; it is above a 2 because steps 2-3 are otherwise tight and purposeful.	3 / 5
Actionability	The body gives the concrete command ID (`search.action.getSearchResults`), the exact tool name (`copilot_runVscodeCommand`), and a specific argument with its value (`skipCheck` true). It is not a 5 because no example invocation of the tool call is shown, leaving a minor gap for copy-paste execution.	4 / 5
Workflow Clarity	This is a simple single-action skill and the one action is unambiguous: run the named command via the named tool with the specified argument. The simple-skill exception applies; no destructive or batch operation is involved, so no validation cap applies.	5 / 5
Progressive Disclosure	The skill is under 50 lines, needs no external references, and the body is well-organized as a titled numbered list. Per the scoring note for short, self-contained skills, this merits a 5 without separate reference files.	5 / 5
	Total	17 / 20 Passed

Description

61%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 concise, specific description of a narrow, well-defined task, weakened mainly by the complete absence of 'when to use' trigger guidance and limited keyword variation. Adding an explicit trigger clause and common synonyms would lift it substantially.

Suggestions

Add a 'Use when...' clause, e.g., "Use when the user asks for current search results, find-in-files results, or the contents of the Search view in VS Code."

Include natural trigger synonyms users would say, such as "find in files", "search results panel", or "search results tab".

Optionally mention what the results contain (files, matches, line numbers) to sharpen the 'what' without adding fluff.

Dimension	Reasoning	Score
Specificity	The description names the domain ("Search view in VS Code") and one concrete action ("Get the current search results"), matching the 'names domain and 1-2 concrete actions, but not comprehensive' anchor. It is not a 4 because only a single action is listed, and not a 2 because the action is concrete rather than generic.	3 / 5
Completeness	The description clearly answers 'what' ("Get the current search results from the Search view in VS Code") but has no 'Use when...' clause or equivalent trigger guidance, capping completeness at 3 per the judging guidelines. It is not a 4 because the 'when' is entirely absent rather than just under-specified.	3 / 5
Trigger Term Quality	"search results", "Search view", and "VS Code" are natural phrases a user would say when needing this skill, giving good keyword coverage. It falls short of a 5 because common variations and synonyms (e.g., "find in files", "search panel", "find and replace") are missing.	4 / 5
Distinctiveness Conflict Risk	The scope is a clear niche (VS Code's Search view) with distinct triggers, but the generic phrase "search results" carries minor overlap risk with web-search or code-search skills. It is not a 5 due to that residual overlap risk, and not a 3 because the VS Code + Search view qualifier makes it mostly distinct.	4 / 5
	Total	14 / 20 Passed

Validation

100%

Warnings & errors only

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: posit-dev/positron
Path: extensions/copilot/assets/prompts/skills/get-search-view-results/SKILL.md
Commit: b0258bc

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

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.