Tessl • The management layer for AI agent skills

SkillPublic

zoom-out

Mapeia modulos, chamadas e relacoes para entender o sistema. Trigger em: "zoom out", "mapa de modulos", "mapa dos modulos", "estou perdido", "perdido nesse codigo", "como isso encaixa", "como se conecta", "callers principais", "visao geral", "big picture", "neighborhood", "broader context", "higher level perspective".

Quality

85%

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

81%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 lean, highly actionable protocol with a clear fallback workflow and an explicit verification checkpoint against stale graph data. The few weak points are non-executable decoration (inspiration/governance sections), a command that fails as written (rg --type tsx), and handoff references that are not resolvable.

Suggestions

Fix the caller-mapping command: ripgrep has no default 'tsx' file type, so "rg --type ts --type tsx" errors out — use "rg --type ts -g '*.tsx'" or just "--type ts" (which already covers *.tsx).

Make handoffs resolvable by citing skill names or paths (e.g. 'architecture-deepener/SKILL.md') instead of bare numbers like 'skill 38', so the referenced skills can actually be found.

Trim the inspiration blockquote and 'Governanca Global' section or compress them to one line, since neither contributes to executing the protocol and they consume context tokens.

Dimension	Reasoning	Score
Conciseness	The body is terse and imperative with no explanations of concepts Claude already knows, but the inspiration blockquote and the "Governanca Global" section referencing external policy files are tokens that do not serve execution of the skill. This is efficient-with-minor-trimmable-material (anchor 4) rather than the every-token-earns-its-place anchor 5.	4 / 5
Actionability	It supplies concrete, mostly executable commands ("test -f graphify-out/graph.json", the find-based topology scan, the rg import search) plus a complete output template. Minor gaps remain: placeholders like "<alvo>" and "<modulo-X>" require substitution, and "rg --type tsx" is not a default ripgrep file type, so that command fails as written.	4 / 5
Workflow Clarity	The protocol is a clearly numbered sequence (graph first, fallback structural discovery, caller mapping, glossary) with an explicit validation checkpoint and error-recovery handling: "confirmar com um segundo grep... Item que nao confirma no codigo atual sai do mapa ou vira nota 'desatualizado desde X'". This matches the anchor-5 pattern of explicit validation with feedback for stale data.	5 / 5
Progressive Disclosure	This is a single-file skill with well-organized sections and one-level-deep, preference-ordered references to repo files (graph.json, GRAPH_REPORT.md, memory/constitution.md, README.md). However, the handoffs section cites companion skills only by number ("skill 38", "skill 33", "skill 09", "skill 32") without resolvable paths, leaving a minor navigation gap that keeps it at anchor 4.	4 / 5
	Total	17 / 20 Passed

Description

86%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 description with an explicit what-plus-trigger structure and excellent bilingual synonym coverage of natural phrases. Its main weaknesses are limited action specificity in the capability sentence and a few overly broad trigger terms that create minor overlap risk with adjacent exploration skills.

Dimension	Reasoning	Score
Specificity	"Mapeia modulos, chamadas e relacoes" names the domain with one concrete verb over three targets, but coverage is not comprehensive — god nodes, domain glossary, and the map output are never mentioned in the description. It is more concrete than the generic anchor 2 but does not list the several distinct actions required for anchor 4.	3 / 5
Completeness	It explicitly answers both questions: the "what" ("Mapeia modulos, chamadas e relacoes para entender o sistema") and the "when" via a dedicated "Trigger em:" clause with concrete trigger phrases. This matches the anchor-5 example structure exactly; anchor 4 would require the "when" to be less explicit than this enumerated trigger list.	5 / 5
Trigger Term Quality	The trigger list gives comprehensive natural-term coverage with explicit synonyms in two languages ("estou perdido"/"perdido nesse codigo", "mapa de modulos"/"mapa dos modulos", "visao geral"/"big picture"/"broader context"), all phrases a user would plausibly say. File extensions are inapplicable to this task type, so no coverage is missing.	5 / 5
Distinctiveness Conflict Risk	The niche (system-level module/call mapping) is distinct, but broad triggers like "big picture", "visao geral", and "broader context" could overlap with general architecture or code-exploration skills. Minor overlap risk with closely related skills places it at anchor 4 rather than the minimal-conflict anchor 5.	4 / 5
	Total	17 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
metadata_version	'metadata.version' is missing	Warning

	Total	14 / 16 Passed

Repository: felvieira/claude-skills-fv
Path: skills/44-zoom-out/SKILL.md
Revision: 449fb53

Reviewed: 13 days ago

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.

zoom-out

Table of Contents

Is this your skill?