CtrlK
BlogDocsLog inGet started
Tessl Logo

context-manager

Skill de gerenciamento de contexto e tarefas usando o mecanismo de task, memoria ou checklist disponivel no ambiente, com persistencia enxuta entre sessoes quando fizer sentido. Use quando precisar organizar tarefas, acompanhar progresso, trocar foco de trabalho, ou manter historico resumido. Trigger em: "criar tarefa", "lista de tarefas", "status", "progresso", "trocar foco", "resetar contexto", "o que falta", "proxima tarefa", "historico", "pipeline de tarefas".

53

Quality

58%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./skills/08-context-manager/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

35%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill reads more like a process description or role definition than an actionable skill for Claude. It clearly delineates scope and responsibilities but lacks concrete examples, executable commands, specific file templates, or validation steps that would make it truly actionable. The content is moderately well-organized but could be significantly tightened and made more concrete.

Suggestions

Add concrete examples of task list format, handoff output, and persistence file content (e.g., show what docs/context/current-focus.md should look like with sample content)

Replace the abstract task lifecycle arrow with a numbered workflow including explicit validation steps (e.g., verify task count < 15, confirm no duplicate in_progress items)

Provide a concrete example of a focus-change scenario showing before/after state, including the exact resumo format to persist

Remove or drastically shorten the 'Skills Utilitárias' section — the external reference and explanation of fork context is tangential and adds token cost without clear actionable guidance

DimensionReasoningScore

Conciseness

The skill is moderately efficient but includes several sections that are somewhat redundant or overly descriptive for Claude (e.g., 'Quando Usar/Nao Usar' lists, 'Entradas Esperadas/Saidas Esperadas' that largely restate obvious context). The 'Skills Utilitárias' section with the external reference and explanation of fork context adds bulk without clear actionable value. Some tightening is possible.

2 / 3

Actionability

The skill is almost entirely descriptive and procedural in the abstract — it describes responsibilities, rules, and lifecycle stages but provides no concrete commands, executable code, specific file formats, or copy-paste examples. The task lifecycle is a vague arrow diagram, not an executable workflow. There are no concrete examples of what a task list, handoff, or persistence file should look like.

1 / 3

Workflow Clarity

There is a recognizable lifecycle (pending → in_progress → completed) and a focus-change procedure with steps, but validation checkpoints are missing. There's no explicit verification step after creating/updating tasks, no error recovery if persistence fails, and the 'Ciclo de Vida' is a single-line arrow rather than a sequenced workflow with checkpoints.

2 / 3

Progressive Disclosure

The skill references multiple external policies (execution.md, persistence.md, etc.) and templates, which is good structure. However, no bundle files are provided, so we can't verify these references resolve. The content itself is somewhat monolithic — the 'Skills Utilitárias' section and governance references could be better signaled. The file paths like 'docs/context/current-focus.md' are mentioned but not linked or described.

2 / 3

Total

7

/

12

Passed

Description

82%

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 does a good job of explicitly stating both what the skill does and when to use it, with a comprehensive list of trigger terms in Portuguese. Its main weaknesses are moderate specificity in describing concrete actions (it stays somewhat abstract about what operations are performed) and some potential overlap risk with other task/project management skills. The use of third person voice is maintained appropriately.

Suggestions

Add more concrete action verbs describing specific outputs or operations, e.g., 'cria checklists com itens acionáveis, gera resumos de progresso, persiste estado entre sessões em arquivos markdown'.

Clarify boundaries with related skills by specifying what this skill does NOT cover, or by narrowing the scope — e.g., distinguish from general project management or note-taking skills.

DimensionReasoningScore

Specificity

Names the domain (context and task management) and some actions (organize tasks, track progress, switch focus, maintain summarized history), but the actions are somewhat general and not deeply concrete — e.g., it doesn't specify what 'persistência enxuta entre sessões' entails in practice or what specific outputs are produced.

2 / 3

Completeness

Clearly answers both 'what' (context and task management with persistence between sessions) and 'when' (explicit 'Use quando...' clause with specific trigger scenarios and a 'Trigger em:' list). Both dimensions are explicitly addressed.

3 / 3

Trigger Term Quality

Provides an explicit list of natural trigger terms in Portuguese that users would actually say: 'criar tarefa', 'lista de tarefas', 'status', 'progresso', 'trocar foco', 'resetar contexto', 'o que falta', 'próxima tarefa', 'histórico', 'pipeline de tarefas'. These are concrete, varied, and cover common user phrasings well.

3 / 3

Distinctiveness Conflict Risk

While the trigger terms are fairly specific to task/context management, the description is broad enough ('gerenciamento de contexto e tarefas') that it could overlap with general project management, to-do list, or checklist skills. The mention of 'checklist' and 'memória' adds some ambiguity about boundaries with other skills.

2 / 3

Total

10

/

12

Passed

Validation

100%

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

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository
felvieira/claude-skills-fv
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.