CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

add-cursor

Use Cursor (local Agent SDK) as a full agent provider — planning, tool orchestration, MCP tools, session resume — alongside or instead of Claude. Cursor-account sign-in or API key, held by the credential gateway. Per-group via `ncl groups config update --provider cursor`. Distinct from using Cursor as a cloud agent (those run on Cursor VMs and are not this provider).

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

88%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 strongly operational skill: every install, auth, and usage step is executable with exact commands and guarded directives, and the workflow has genuine validation checkpoints and error-recovery loops. The only weaknesses are a few over-dense prose passages and bundle references that cannot be verified against the provided directory.

DimensionReasoningScore

Conciseness

The body is dense with system-specific operational detail and never explains concepts Claude already knows, but a few long prose passages (the runtime-contract paragraph, the HTTP/2 "Traffic and the gateway" troubleshooting bullet, the credentials paragraph) could be tightened or structured — matching the 4 anchor ("minor instances of over-explanation that could be trimmed"), not the lean-everywhere 5.

4 / 5

Actionability

Fully executable throughout: exact commands ("pnpm exec tsx setup/index.ts --step provider-auth cursor"), an exact dependency pin ("@cursor/sdk@1.0.28"), a 20-file copy manifest with exact paths, and per-group ncl commands — copy-paste ready and covering install, auth, use, and removal, matching the 5 anchor.

5 / 5

Workflow Clarity

Clear sequenced workflow (pre-flight → copy → barrels → dependency → build/test → auth → use) with explicit validation checkpoints: the compatibility predicate with "If it prints no, stop", the contract verifier that "goes red if a barrel line is missing", and a troubleshooting section mapping exact errors to fixes — explicit validation with error-recovery feedback loops, matching the 5 anchor.

5 / 5

Progressive Disclosure

Good structure with the bulk payload split into a per-file manifest and one-level-deep, clearly signaled references ([REMOVE.md](REMOVE.md), [docs/provider-migration.md]). Not 5: none of the referenced bundle files (payload/, REMOVE.md) are present in the provided skill directory to verify, and the migration doc reference points outside the skill bundle (../../docs/), leaving minor organization gaps per the 4 anchor.

4 / 5

Total

18

/

20

Passed

Description

75%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 specific, highly distinctive description with concrete capabilities, the exact enabling CLI command, and clear disambiguation from Claude and from Cursor-as-cloud-agent. Its main weakness is the absence of any explicit 'Use when...' trigger guidance, leaving the 'when' only weakly implied.

Suggestions

Add an explicit trigger clause such as "Use when the user wants to run agent groups on Cursor instead of Claude, or asks to switch a group's agent backend to Cursor."

Include the natural user phrasings for triggering (e.g. "switch provider", "use Cursor as the agent", "Cursor account") so the description matches how users actually ask for it.

Trim incidental setup mechanics (e.g. the credential-gateway detail) in favor of the when-to-use guidance, keeping the description focused on what and when.

DimensionReasoningScore

Specificity

Enumerates multiple concrete capabilities ("planning, tool orchestration, MCP tools, session resume"), the exact enabling command ("ncl groups config update --provider cursor"), and both auth paths ("Cursor-account sign-in or API key") — comprehensive coverage of what the provider does and how it is enabled, matching the 5 anchor rather than 4 which expects minor gaps.

5 / 5

Completeness

The "what" is clearly stated (full agent provider with enumerated capabilities), but there is no "Use when..." clause or equivalent explicit trigger guidance — "alongside or instead of Claude" only weakly implies when to use it, which caps completeness at 3 per the judging guidelines. Not 4, which requires an explicit 'when'.

3 / 5

Trigger Term Quality

The core natural term "Cursor" recurs alongside "agent provider", "alongside or instead of Claude", "sign-in", and "API key" — good keyword coverage. Not 5 because common natural phrasings users might say (e.g. "switch the agent backend") are only implied rather than covered as synonyms.

4 / 5

Distinctiveness Conflict Risk

Names a specific tool (Cursor), and explicitly disambiguates both from Claude ("alongside or instead of Claude") and from the confusable sibling concept ("Distinct from using Cursor as a cloud agent (those run on Cursor VMs and are not this provider)") — a clear niche with minimal conflict risk, matching the 5 anchor.

5 / 5

Total

17

/

20

Passed

Validation

81%

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

Validation — 13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

relative_links

Relative link issues: 1 missing, 1 suspicious

Warning

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

13

/

16

Passed

Repository

nanocoai/nanoclaw

Path

.claude/skills/add-cursor/SKILL.md

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.