CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

code-modification-rules

Regras críticas sobre quando e como modificar código existente

Quality

57%

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/code-modification/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

63%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 clear, actionable policy document with concrete do/don't rules, worked examples, and a usable checklist. Its main weaknesses are redundant restatement of the core rule, the absence of a post-change verification step, and a references section pointing to files not present in the bundle.

Suggestions

Consolidate the repeated statements of the core rule: fold the Regra Fundamental bullets, Proibições Absolutas list, and Checklist into one authoritative section with the checklist as the single verification gate.

Fix or remove the Referências section: the cited paths (skills/backend/fastapi/SKILL.md, skills/backend/django/SKILL.md, core/templates/) are not part of the skill bundle, so either bundle them or describe what they contain and when to consult them.

Add a post-change verification step to the workflow (e.g. re-read the diff against the original request and confirm no unrelated files changed) so the checklist validates the outcome, not just intent.

DimensionReasoningScore

Conciseness

The core rule "SÓ ALTERAR O QUE FOI EXPLICITAMENTE SOLICITADO" is restated across Regra Fundamental, Proibições Absolutas, Quando o Usuário Pede uma Alteração, Quando Há Dúvida, and the Checklist — substantial duplication that could be consolidated. There is no filler explaining concepts Claude already knows, so it sits above anchor 2 but fits 'Mostly efficient but... could be tightened'.

3 / 5

Actionability

Concrete, specific guidance throughout: explicit ✅/❌ do/don't lists, two worked examples (adicionar endpoint, corrigir bug) with correct/incorrect outcomes, a pre-change checklist, and a defined exceptions list. Minor gaps keep it below 5: judgment calls like "alterações mínimas necessárias" lack concrete criteria, and the Referências paths are not part of this bundle.

4 / 5

Workflow Clarity

The policy workflow is clearly sequenced: apply only the explicitly requested change, consult the permitted exceptions, run the pre-modification checklist, and escalate to the user when in doubt ('perguntar ao usuário antes de alterar'). It is not 5 because there is no post-change verification step, and the checklist serves as the sole validation checkpoint.

4 / 5

Progressive Disclosure

Sections are clearly headed and the skill is self-contained, but the Referências section points to paths ('skills/backend/fastapi/SKILL.md', 'core/templates/') that do not exist in this skill bundle and are described only by one-word labels. This matches 'references present but not clearly signaled'; it is not 4 because the only external navigation the skill offers does not resolve.

3 / 5

Total

14

/

20

Passed

Description

33%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 communicates a coherent theme (discipline around modifying existing code) but is thin: no concrete capabilities, no use-when guidance, and only one generic keyword. It would likely fail to trigger reliably or distinguish itself from general coding skills.

Suggestions

Add an explicit 'Use when...' clause in the description, e.g. 'Use when modifying existing code, deciding the scope of a change, or when unsure whether unsolicited improvements are wanted.'

List the concrete capabilities the skill provides (allowed vs. prohibited changes, minimal-change policy, decision checklist) instead of only naming the domain.

Include natural trigger terms and their synonyms in the description itself (modify, edit, change, refactor, update code, unsolicited improvements), not only in the separate 'triggers' frontmatter field.

DimensionReasoningScore

Specificity

The description "Regras críticas sobre quando e como modificar código existente" names the domain (modifying existing code) but offers only the generic action pair "quando e como modificar" with no concrete capabilities, matching the anchor 'Names the domain but actions are minimal or generic'. It does not reach 3 because no specific concrete action is listed.

2 / 5

Completeness

The 'what' is reasonably clear (critical rules about when and how to modify existing code) but the 'when' is entirely absent — there is no 'Use when...' clause or equivalent trigger guidance in the description, capping this dimension at 3 per the judging guidelines. It is not 2 because the 'what' is not vague, and not 4 because no 'when' guidance exists at all.

3 / 5

Trigger Term Quality

The description contains only the single generic keyword phrase "modificar código"; the natural terms users would say (edit code, refactor, fix bug, update, change) exist only in the separate 'triggers' frontmatter field, not in the description itself. This fits 'One or two generic keywords; missing the natural phrases users say' rather than 3, which requires some relevant keyword coverage.

2 / 5

Distinctiveness Conflict Risk

"modificar código existente" combined with triggers like modify/change/alter/edit would match virtually any coding request, creating high overlap risk with refactoring, bug-fixing, and feature-implementation skills. This matches 'Very broad; high overlap risk with many similar skills'; it is not 3 because the description does not establish a distinct niche beyond generic change discipline.

2 / 5

Total

9

/

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/code-modification/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.