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".

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

76%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.

A concise, well-organized instruction skill with concrete file paths and a lifecycle model, but it lacks explicit validation/verification checkpoints for its state-changing operations and keeps core task operations abstract. Adding validate-then-confirm steps for focus switches and archiving would raise workflow clarity.

Suggestions

Add explicit validation checkpoints to the task lifecycle and focus-change flows (e.g., confirm the active context is persisted before archiving, verify the new focus list is non-empty before switching) so state-changing operations have feedback loops.

Replace abstract directives like 'usar o mecanismo disponivel no ambiente' with at least one concrete example invocation or a small code snippet for the most common operation (e.g., creating a pending task), to push actionability from 4 toward 5.

Specify what 'estado atual resumido' must contain (e.g., current focus, in-progress task, top blocker) so the handoff output is unambiguous and verifiable.

Dimension	Reasoning	Score
Conciseness	The body is lean and well-sectioned, assumes Claude's intelligence, and never pads with background concepts (no explanation of what tasks or context are), matching the score-5 'lean and efficient; every token earns its place' anchor.	5 / 5
Actionability	Provides concrete guidance — the task lifecycle arrow, specific file paths ('docs/context/current-focus.md', 'docs/context/history.md'), and an executable YAML frontmatter example for fork sub-skills — but the core task operations rely on 'usar o mecanismo disponivel' rather than concrete commands, leaving minor gaps per the score-4 anchor.	4 / 5
Workflow Clarity	A rough sequence exists (lifecycle states, focus-change steps) but there are no explicit validation checkpoints or feedback loops for state-changing operations like archiving context or switching focus; per the rubric's destructive/batch guidance this caps workflow clarity at 3.	3 / 5
Progressive Disclosure	Sections are well organized and references to external kit files (policies/*.md, templates/handoff.md) are clearly signaled and one level deep, but no bundle files ship with the skill, matching the score-4 'good structure; references mostly clear; minor gaps' anchor.	4 / 5
	Total	16 / 20 Passed

Description

91%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 strong, concise Portuguese description that clearly states capabilities and provides an explicit trigger list. Minor gains possible from more comprehensive capability enumeration, but it already answers both 'what' and 'when' well.

Dimension	Reasoning	Score
Specificity	Names the domain (context/task management) and lists several concrete actions such as 'organizar tarefas, acompanhar progresso, trocar foco de trabalho, ou manter historico resumido', matching the score-4 anchor with minor coverage gaps rather than the exhaustive list required for a 5.	4 / 5
Completeness	Clearly states what the skill does ('gerenciamento de contexto e tarefas usando o mecanismo de task, memoria ou checklist') and an explicit 'Use quando' clause with concrete trigger phrases, satisfying both halves required for a 5.	5 / 5
Trigger Term Quality	Provides comprehensive natural-language triggers users would actually say — 'criar tarefa', 'lista de tarefas', 'status', 'progresso', 'trocar foco', 'o que falta', 'proxima tarefa', 'historico' — covering synonyms and common phrasings, matching the score-5 anchor.	5 / 5
Distinctiveness Conflict Risk	Has a clear niche (context/task continuity and focus management) with distinct triggers, though it could overlap with general task-tooling skills, matching the score-4 'mostly distinct; minor overlap risk' anchor.	4 / 5
	Total	18 / 20 Passed

Validation

100%

Warnings & errors only

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: felvieira/claude-skills-fv
Path: skills/08-context-manager/SKILL.md
Commit: f3492ef

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

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.