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

81%

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.

An exemplary operational runbook: fully executable steps, an explicit gating pre-flight, validation at every stage, and error-recovery guidance tied to exact failure signatures. The only weaknesses are mild verbosity in two long passages and references to bundle files that are not actually present alongside SKILL.md.

DimensionReasoningScore

Conciseness

The body is dense and almost entirely project-specific (seam versions, gateway route scoping, directive fences) with no teaching of known concepts, but a few passages — the credential-gateway paragraph and the HTTP/2 troubleshooting bullet — are long clause-chains that could be tightened without losing information.

4 / 5

Actionability

Every step is an exact executable command: the 'node -e' compatibility predicate, the full nc:copy file manifest, the nc:append barrel imports, the '@cursor/sdk@1.0.28' pin, vitest/bun test invocations, the contract-verifier command, and platform-specific restart instructions — copy-paste ready with no gaps.

5 / 5

Workflow Clarity

A pre-flight compatibility guard ('If it prints no, stop and tell the operator') gates every later directive via 'when:cursor_core_ready=yes', and the install → build/test → authenticate → use sequence carries explicit validation (registration/conformance/gateway-proxy suites, the contract verifier) plus a troubleshooting section with exact error strings and their remediations.

5 / 5

Progressive Disclosure

Well-organized sections with clearly signaled one-level links ('[REMOVE.md](REMOVE.md)', '[docs/provider-migration.md](../../docs/provider-migration.md)'), but those referenced files and the 'payload/' tree are absent from this bundle, and the deep HTTP/2/egress troubleshooting detail is inlined where a separate reference file would serve better.

4 / 5

Total

18

/

20

Passed

Description

70%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, well-disambiguated description with concrete capabilities and an exact command, weakened only by the absence of explicit 'when to use' trigger guidance. Adding a 'Use when...' clause with natural trigger phrases would lift it into the top band.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the operator wants to run agent groups on Cursor, switch a group's provider from Claude to Cursor, or asks about Cursor sign-in/API keys for NanoClaw.'

Include common natural phrasings and synonyms ('Cursor agent', 'switch agent backend to Cursor', 'use Cursor instead of Claude') so the description matches how users actually ask for this.

DimensionReasoningScore

Specificity

Lists several concrete capabilities ('planning, tool orchestration, MCP tools, session resume') plus an exact configuration command ('ncl groups config update --provider cursor'), but coverage of the skill's full scope (install, build, auth walk-through) has minor gaps, so it is not comprehensive.

4 / 5

Completeness

The 'what' is clear ('Use Cursor (local Agent SDK) as a full agent provider'), but there is no 'Use when...' clause or equivalent explicit trigger guidance — the 'when' is only weakly implied by 'alongside or instead of Claude', which caps completeness at 3 per the rubric guideline.

3 / 5

Trigger Term Quality

Good natural-keyword coverage — 'Cursor', 'agent provider', 'instead of Claude', 'API key', 'sign-in' — matching what a user would say when wanting this skill, though common variations like 'Cursor agent' or 'switch agent backend' are missing.

4 / 5

Distinctiveness Conflict Risk

The description carves out a clear niche and explicitly disambiguates the nearest conflict: 'Distinct from using Cursor as a cloud agent (those run on Cursor VMs and are not this provider)', giving minimal conflict risk.

5 / 5

Total

16

/

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.