tool-rename-deprecation▌
microsoft/vscode · updated Apr 8, 2026
MDX-style export adds YAML metadata + attribution linking explainx.ai and this canonical listing URL.
When a tool or tool set reference name is changed, the old name must always be added to the deprecated/legacy array so that existing prompt files, tool configurations, and saved references continue to resolve correctly.
Tool Rename Deprecation
When a tool or tool set reference name is changed, the old name must always be added to the deprecated/legacy array so that existing prompt files, tool configurations, and saved references continue to resolve correctly.
When to Use
Run this skill on any change to built-in tool or tool set registration code to catch regressions:
- Renaming a tool's
toolReferenceName - Renaming a tool set's
referenceName - Moving a tool from one tool set to another (the old
toolSet/toolNamepath becomes a legacy name) - Reviewing a PR that modifies tool registration — verify no legacy names were dropped
Procedure
Step 1 — Identify What Changed
Determine whether you are renaming a tool or a tool set, and where it is registered:
| Entity | Registration | Name field to rename | Legacy array | Stable ID (NEVER change) |
|---|---|---|---|---|
Tool (IToolData) |
TypeScript | toolReferenceName |
legacyToolReferenceFullNames |
id |
| Tool (extension) | package.json languageModelTools |
toolReferenceName |
legacyToolReferenceFullNames |
name (becomes id) |
Tool set (IToolSet) |
TypeScript | referenceName |
legacyFullNames |
id |
| Tool set (extension) | package.json languageModelToolSets |
name or referenceName |
legacyFullNames |
— |
Critical: For extension-contributed tools, the name field in package.json is mapped to id on IToolData (see languageModelToolsContribution.ts line id: rawTool.name). It is also used for activation events (onLanguageModelTool:<name>). Never rename the name field — only rename toolReferenceName.
Step 2 — Add the Old Name to the Legacy Array
Verify the old toolReferenceName value appears in legacyToolReferenceFullNames. Don't assume it's already there — check the actual array contents. If the old name is already listed (e.g., from a previous rename), confirm it wasn't removed. If it's not there, add it.
For internal/built-in tools (TypeScript IToolData):
// Before rename
export const MyToolData: IToolData = {
id: 'myExtension.myTool',
toolReferenceName: 'oldName',
// ...
};
// After rename — old name preserved
export const MyToolData: IToolData = {
id: 'myExtension.myTool',
toolReferenceName: 'newName',
legacyToolReferenceFullNames: ['oldName'],
// ...
};
If the tool previously lived inside a tool set, use the full toolSet/toolName form:
legacyToolReferenceFullNames: ['oldToolSet/oldToolName'],
If renaming multiple times, accumulate all prior names — never remove existing entries:
legacyToolReferenceFullNames: ['firstOldName', 'secondOldName'],
For tool sets, add the old name to the legacyFullNames option when calling createToolSet:
toolsService.createToolSet(source, id, 'newSetName', {
legacyFullNames: ['oldSetName'],
});
For extension-contributed tools (package.json), rename only toolReferenceName and add the old value to legacyToolReferenceFullNames. Do NOT rename the name field:
// CORRECT — only toolReferenceName changes, name stays stable
{
"name": "copilot_myTool", // ← KEEP this unchanged
"toolReferenceName": "newName", // ← renamed
"legacyToolReferenceFullNames": [
"oldName" // ← old toolReferenceName preserved
]
}
Step 3 — Check All Consumers of Tool Names
Legacy names must be respected everywhere a tool is looked up by reference name, not just in prompt resolution. Key consumers:
- Prompt files —
getDeprecatedFullReferenceNames()maps old → current names for.prompt.mdvalidation and code actions - Tool enablement —
getToolAliases()/getToolSetAliases()yield legacy names so tool picker and enablement maps resolve them - Auto-approval config —
isToolEligibleForAutoApproval()checkslegacyToolReferenceFullNames(including the segment after/for namespaced legacy names) againstchat.tools.eligibleForAutoApprovalsettings - RunInTerminalTool — has its own local auto-approval check that also iterates
LEGACY_TOOL_REFERENCE_FULL_NAMES
After renaming, confirm:
#oldNamein a.prompt.mdfile still resolves (shows no validation error)- Tool configurations referencing the old name still activate the tool
- A user who had
"chat.tools.eligibleForAutoApproval": { "oldName": false }still has that restriction honored
Step 4 — Update References (Optional)
While legacy names ensure backward compatibility, update first-party references to use the new name:
- System prompts and built-in
.prompt.mdfiles - Documentation and model descriptions that mention the tool by reference name
- Test files that reference the old name directly
Key Files
| File | What it contains |
|---|---|
src/vs/workbench/contrib/chat/common/tools/languageModelToolsService.ts |
IToolData and IToolSet interfaces with legacy name fields |
src/vs/workbench/contrib/chat/browser/tools/languageModelToolsService.ts |
Resolution logic: getToolAliases, getToolSetAliases, getDeprecatedFullReferenceNames, isToolEligibleForAutoApproval |
src/vs/workbench/contrib/chat/common/tools/languageModelToolsContribution.ts |
Extension point schema, validation, and the critical id: rawTool.name mapping (line ~274) |
src/vs/workbench/contrib/terminalContrib/chatAgentTools/browser/tools/runInTerminalTool.ts |
Example of a tool with its own local auto-approval check against legacy names |
Real Examples
runInTerminaltool: renamed fromrunCommands/runInTerminal→legacyToolReferenceFullNames: ['runCommands/runInTerminal']todotool: renamed fromtodos→legacyToolReferenceFullNames: ['todos']getTaskOutputtool: renamed fromrunTasks/getTaskOutput→legacyToolReferenceFullNames: ['runTasks/getTaskOutput']
Reference PRs
- #277047 — Design PR: Introduced
legacyToolReferenceFullNamesandlegacyFullNames, built the resolution infrastructure, and performed the first batch of tool renames. Use as a template for how to properly rename with legacy names. - #278506 — Consumer-side fix: After the renames in #277047, the
eligibleForAutoApprovalsetting wasn't checking legacy names — users who had restricted the old name lost that restriction. Shows why all consumers of tool reference names must account for legacy names. - vscode-copilot-chat#3810 — Example of a miss: Renamed
openSimpleBrowser→openIntegratedBrowserbut also changed thenamefield (stable id) fromcopilot_openSimpleBrowser→copilot_openIntegratedBrowser. ThetoolReferenceNamebackward compat only worked by coincidence (the old name happened to already be in the legacy array from a prior change — it was not intentionally added as part of this rename).
Regression Check
Run this check on any PR that touches tool registration (TypeScript IToolData, createToolSet, or package.json languageModelTools/languageModelToolSets):
- Search the diff for changed
toolReferenceNameorreferenceNamevalues. For each change, confirm the previous value now appears inlegacyToolReferenceFullNamesorlegacyFullNames. Don't assume it was already there — read the actual array. - Search the diff for changed
namefields on extension-contributed tools. Thenamefield is the tool's stableid— it must never change. If it changed, flag it as a bug. (This breaks activation events, tool invocations by id, and any code referencing the tool by itsname.) - Verify no entries were removed from existing legacy arrays.
- If a tool moved between tool sets, confirm the old
toolSet/toolNamefull path is in the legacy array. - Check tool set membership lists (the
toolsarray inlanguageModelToolSetscontributions). If a tool'stoolReferenceNamechanged, any tool settoolsarray referencing the old name should be updated — but the legacy resolution system handles this, so the old name still works.
Anti-patterns
- Changing the
namefield on extension-contributed tools — thenameinpackage.jsonbecomes theidonIToolData(viaid: rawTool.nameinlanguageModelToolsContribution.ts). Changing it breaks activation events (onLanguageModelTool:<name>), any code referencing the tool by id, and tool invocations. Only renametoolReferenceName, nevername. (See vscode-copilot-chat#3810 where bothnameandtoolReferenceNamewere changed.) - Changing the
idfield on TypeScript-registered tools — same principle as above. Theidis a stable internal identifier and must never change. - Assuming the old name is already in the legacy array — always verify by reading the actual
legacyToolReferenceFullNamescontents, not just checking that the field exists. A legacy array might list names from an even older rename but not the current one being changed. - Removing an old name from the legacy array — breaks existing saved prompts and user configurations.
- Forgetting to add the legacy name entirely — prompt files and tool configs silently stop resolving.
- Only updating prompt resolution but not other consumers — auto-approval settings, tool enablement maps, and individual tool checks (like
RunInTerminalTool) all need to respect legacy names (see #278506).
How to use tool-rename-deprecation on Cursor
AI-first code editor with Composer
Prerequisites
Before installing skills in Cursor, ensure your development environment meets these requirements:
- ›Cursor installed and configured on your development machine
- ›Node.js version 16.0+ with npm package manager (verify with
node --version) - ›Active project directory or workspace where you want to add tool-rename-deprecation
Execute installation command
Execute the skills CLI command in your project's root directory to begin installation:
The skills CLI fetches tool-rename-deprecation from GitHub repository microsoft/vscode and configures it for Cursor.
Select Cursor when prompted
The CLI will show a list of available agents. Use arrow keys to navigate and space to select Cursor:
Verify installation
Confirm successful installation by checking the skill directory location:
Reload or restart Cursor to activate tool-rename-deprecation. Access the skill through slash commands (e.g., /tool-rename-deprecation) or your agent's skill management interface.
Security & Verification Notice
We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.
Skills execute code in your development environment. Always verify the publisher's identity, review recent commits, and test in isolated environments before production deployment.
List & Monetize Your Skill
Submit your Claude Code skill and start earning
Use Cases▌
User Story & Requirements Generation
Create detailed user stories, acceptance criteria, and feature specs
Example
Generate user stories for 'password reset feature' with acceptance criteria, edge cases, and test scenarios
Reduce spec writing time by 50%, ensure comprehensive coverage
Competitive Analysis
Research competitors, compare features, identify gaps
Example
Analyze 5 competitor products, create feature comparison matrix, suggest differentiation opportunities
Complete competitive research in 2 hours instead of 2 days
Roadmap Prioritization
Evaluate features using frameworks (RICE, ICE, Kano) and create prioritized backlogs
Example
Score 20 feature ideas using RICE framework, generate prioritized roadmap with rationale
Make data-driven prioritization decisions faster
Stakeholder Communication
Draft PRDs, status updates, and stakeholder presentations
Example
Create executive summary of Q3 roadmap, monthly progress report, feature launch announcement
Save 3-5 hours/week on communication overhead
Implementation Guide▌
Prerequisites
- ›Claude Desktop or compatible AI client
- ›Access to product documentation and roadmap tools (Jira, Notion, etc.)
- ›Understanding of product management frameworks (RICE, Jobs-to-be-Done, etc.)
- ›Stakeholder contact information and communication channels
Time Estimate
30-60 minutes to see productivity improvements
Installation Steps
- 1.Install product management skill
- 2.Start with user story generation for known feature
- 3.Progress to competitive analysis: research 2-3 competitors
- 4.Use for roadmap prioritization: apply RICE/ICE scoring
- 5.Draft stakeholder communications and refine based on feedback
- 6.Build template library for recurring PM tasks
- 7.Share effective prompts with product team
Common Pitfalls
- ⚠Not validating competitive research—verify facts before sharing
- ⚠Accepting user stories without involving engineering team
- ⚠Over-relying on frameworks without qualitative judgment
- ⚠Not customizing outputs to company culture and communication style
- ⚠Skipping stakeholder validation of generated requirements
Best Practices▌
✓ Do
- +Validate research and competitive analysis with real data
- +Collaborate with engineering when generating technical requirements
- +Customize frameworks and templates to your company context
- +Use skill for first drafts, refine with stakeholder input
- +Document successful prompt patterns for PM tasks
- +Combine AI efficiency with human judgment and intuition
✗ Don't
- −Don't publish competitive analysis without fact-checking
- −Don't finalize user stories without engineering review
- −Don't make prioritization decisions solely on AI scoring
- −Don't skip customer validation of generated requirements
- −Don't ignore company-specific context and culture
💡 Pro Tips
- ★Provide context: company goals, constraints, customer feedback
- ★Ask for alternatives: 'Show 3 ways to prioritize this roadmap'
- ★Request stakeholder-specific formatting: 'Executive summary vs. engineering spec'
- ★Use skill for 70% generation + 30% customization to company needs
When to Use This▌
✓ Use When
Use for user story writing, competitive research, roadmap prioritization, stakeholder communication, and PRD drafting. Best for reducing repetitive documentation and research work.
✗ Avoid When
Avoid for strategic product vision (requires deep customer empathy), pricing decisions (needs market and financial expertise), or when face-to-face customer discovery is more valuable than speed.
Learning Path▌
- 1Basic: user stories, feature specs, status updates
- 2Intermediate: competitive analysis, prioritization frameworks, PRDs
- 3Advanced: product strategy, go-to-market planning, OKR setting
- 4Expert: product vision, market positioning, business model innovation
Discussion
Product Hunt–style comments (not star reviews)- No comments yet — start the thread.
Ratings
4.7★★★★★62 reviews- ★★★★★Arya Srinivasan· Dec 28, 2024
We added tool-rename-deprecation from the explainx registry; install was straightforward and the SKILL.md answered most questions upfront.
- ★★★★★Ganesh Mohane· Dec 16, 2024
I recommend tool-rename-deprecation for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.
- ★★★★★Aanya Gupta· Dec 4, 2024
Keeps context tight: tool-rename-deprecation is the kind of skill you can hand to a new teammate without a long onboarding doc.
- ★★★★★Yash Thakker· Nov 27, 2024
Useful defaults in tool-rename-deprecation — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.
- ★★★★★Aarav Tandon· Nov 23, 2024
tool-rename-deprecation is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.
- ★★★★★Min Garcia· Nov 19, 2024
tool-rename-deprecation fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.
- ★★★★★Sakshi Patil· Nov 7, 2024
Solid pick for teams standardizing on skills: tool-rename-deprecation is focused, and the summary matches what you get after install.
- ★★★★★Chaitanya Patil· Oct 26, 2024
tool-rename-deprecation is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.
- ★★★★★Dhruvi Jain· Oct 18, 2024
Registry listing for tool-rename-deprecation matched our evaluation — installs cleanly and behaves as described in the markdown.
- ★★★★★Aarav Patel· Oct 14, 2024
Solid pick for teams standardizing on skills: tool-rename-deprecation is focused, and the summary matches what you get after install.
showing 1-10 of 62