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".
53
58%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/08-context-manager/SKILL.mdQuality
Discovery
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 is reasonably well-structured with clear 'what' and 'when' sections and a strong set of trigger terms. Its main weakness is in specificity—it describes capabilities at a general level rather than listing concrete actions, and the domain of 'task and context management' could overlap with other similar skills. The use of third person voice is appropriate throughout.
Suggestions
Increase specificity by listing concrete actions such as 'criar e atualizar checklists em arquivos markdown', 'persistir estado de tarefas entre sessões', 'gerar resumo de progresso' instead of general descriptions.
Improve distinctiveness by clarifying what specific mechanism or tool this skill uses (e.g., specific file formats, specific task storage approach) to differentiate it from generic task management or project tracking skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (task/context management) and mentions some actions like organizing tasks, tracking progress, switching focus, and maintaining summarized history. However, it lacks concrete specific actions—it describes general capabilities rather than listing precise operations like 'create checklists', 'persist task state to files', or 'generate progress reports'. | 2 / 3 |
Completeness | The description clearly answers both 'what' (context and task management with persistence between sessions) and 'when' (explicitly states 'Use quando precisar organizar tarefas, acompanhar progresso, trocar foco de trabalho, ou manter historico resumido') with explicit trigger terms listed separately. | 3 / 3 |
Trigger Term Quality | The description includes a comprehensive 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', 'proxima tarefa', 'historico', 'pipeline'. These are natural, varied, and cover common user phrasings. | 3 / 3 |
Distinctiveness Conflict Risk | While the description carves out a niche around task/context management with session persistence, terms like 'tarefa', 'checklist', 'status', and 'progresso' could overlap with project management skills, todo-list skills, or general workflow tools. The mention of 'mecanismo de task, memoria ou checklist disponivel no ambiente' adds some specificity but remains somewhat ambiguous about what distinguishes it from similar tools. | 2 / 3 |
Total | 10 / 12 Passed |
Implementation
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 role description or process document than an actionable skill for Claude. It lacks concrete examples, executable commands, specific file formats, or tool invocations that would let Claude know exactly what to do. The structure is reasonable but the content is too abstract to be immediately useful without significant interpretation.
Suggestions
Add concrete, executable examples: show exactly what a task list looks like (e.g., a markdown checklist or JSON schema), what a 'current-focus.md' file should contain, and what a handoff summary looks like with sample content.
Replace vague references like 'mecanismo disponivel no ambiente' with specific tool calls or commands Claude should use (e.g., TodoWrite, file creation commands, or specific API calls).
Add a validation/verification step to the task lifecycle—e.g., after updating status, read back the task list to confirm consistency before proceeding.
Consolidate the 'Entradas Esperadas', 'Saidas Esperadas', and 'Evidencia de Conclusao' sections into a single concise section or remove them, as they largely restate the same information in different ways.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is moderately efficient but includes several sections that are somewhat redundant or obvious (e.g., 'Quando Nao Usar' lists things Claude could infer, 'Entradas Esperadas' and 'Saidas Esperadas' are fairly generic). The governance references and structural boilerplate add tokens without much actionable value. | 2 / 3 |
Actionability | The skill is almost entirely descriptive and procedural in the abstract—no concrete code, commands, file formats, or executable examples are provided. Phrases like 'Usar o mecanismo disponivel no ambiente' and 'ferramenta nativa de task ou memoria' are vague and give Claude no specific tool calls, schemas, or commands to execute. | 1 / 3 |
Workflow Clarity | There is a lifecycle sequence (pending -> in_progress -> completed) and a focus-change process with steps, but validation checkpoints are absent. The workflow lacks explicit verification steps (e.g., confirming task state after update) and the lifecycle is described in a single line rather than with clear numbered steps and error recovery. | 2 / 3 |
Progressive Disclosure | The skill references external policies and templates (policies/execution.md, templates/handoff.md, etc.) which suggests layered structure, but no bundle files are provided to verify these exist. The main file itself is somewhat monolithic with many short sections that could be consolidated, and the references are not clearly signaled with descriptions of what each contains. | 2 / 3 |
Total | 7 / 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.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
7577622
Table of Contents
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.