CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

cursor-handoff

Regras de transição entre Cursor e Claude Code

Quality

65%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/workflow/cursor-handoff/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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.

The body is a well-organized, efficient policy document: concrete command examples, explicit permission boundaries for risky git operations, and validation checklists gating the commit step. Its main weaknesses are minor — some repetition of the permission rules and an only-implied re-review loop after issue fixes.

Suggestions

Add an explicit re-review step to the issue workflow: after reporting issues and Cursor fixing them, state that Claude Code re-runs the review and tests before re-approving, closing the feedback loop.

Consolidate the permission rules stated in three places ('COM PERMISSÃO' twice in Divisão de Responsabilidades and again in Regras Críticas) into a single authoritative section to remove redundancy.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence — no generic explanations, just role divisions, command examples, and checklists. It is not a 5 because permission rules are stated redundantly ('COM PERMISSÃO' in the responsibilities section is repeated nearly verbatim in 'Regras Críticas'), which could be consolidated.

4 / 5

Actionability

Provides concrete, executable guidance: ready-to-run `claude "..."` command examples, copy-paste issue-report message templates, and explicit allowed/forbidden action lists (`git commit`, `git push`, `git reset`). Not a 5 because some guidance stays high-level — e.g., no concrete command or procedure for 'Execução de testes automatizados'.

4 / 5

Workflow Clarity

The handoff flow is clearly sequenced (implement → handoff → review/test → report issues or approve → commit with confirmation) and both checklists act as explicit validation checkpoints, satisfying the risky-operation requirement for git actions. It falls short of 5 because the error-recovery loop is only implied — after Cursor fixes reported issues there is no explicit re-review step.

4 / 5

Progressive Disclosure

At ~95 lines with no bundle files, all content appropriately lives in one well-sectioned document (roles, flow, rules, checklists) with nothing that clearly belongs in a separate reference file. It is not a 5 because it exceeds the 'under 50 lines' simple-skill threshold and has minor organization overlap — 'Quando Usar' partially duplicates the handoff checklists.

4 / 5

Total

16

/

20

Passed

Description

40%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.

The description identifies its niche (Cursor ↔ Claude Code handoff) distinctly, but is a bare domain label: it states no concrete actions and provides no 'when to use' guidance. The bulk of the trigger signal lives in the separate frontmatter 'triggers' field rather than in the description where it would do the most good.

Suggestions

Rewrite the description to state concrete actions, e.g. 'Define responsibility split and handoff rules between Cursor and Claude Code: code review, test execution, and commit/PR preparation' — currently no verbs or capabilities are mentioned at all.

Add an explicit 'when' clause to the description, such as 'Use when Cursor finishes an implementation and work must transition to Claude Code for review, testing, or commit preparation.'

Include natural user trigger phrases (handoff, transição, review, commit, testes) inside the description text itself rather than relying solely on the separate 'triggers' frontmatter field.

DimensionReasoningScore

Specificity

The description 'Regras de transição entre Cursor e Claude Code' names the domain (transition rules between the two tools) but contains no concrete actions or verbs describing what the skill actually does. It fits anchor 2 ('Names the domain but actions are minimal or generic') better than anchor 1, since the domain is clearly identified rather than entirely vague.

2 / 5

Completeness

The 'what' is vague ('regras' — rules, with no stated actions) and the 'when' is entirely missing; there is no 'Use when...' clause or equivalent in the description. This fits anchor 2 ('Has a vague what and no when') rather than anchor 3, whose example lists multiple concrete actions; it cannot be 1 because the domain is clearly named.

2 / 5

Trigger Term Quality

It contains some relevant, specific keywords users would say ('Cursor', 'Claude Code', 'transição') but misses common variations and synonyms such as 'handoff', 'review', 'commit', or 'testes'. This matches anchor 3 ('Some relevant keywords but missing common variations or synonyms') rather than 4, since natural trigger phrases users would actually utter are absent from the description itself.

3 / 5

Distinctiveness Conflict Risk

Naming the specific tool pair 'Cursor e Claude Code' gives it a clear niche with minimal conflict risk against unrelated skills. It is not a 5 because the workflow territory it covers (review, tests, commit preparation) overlaps with general code-review and commit-message skills, but the risk is minor, matching anchor 4.

4 / 5

Total

11

/

20

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.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

fernandezbaptiste/cursor-multiagent-system

Path

skills/workflow/cursor-handoff/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.