CtrlK
BlogDocsLog inGet started
Tessl Logo

manage-agent

Edit, update, or remove an existing custom agent. Shows current config and asks what to change. Also handles listing all custom agents. Triggers: EN: "edit my agent", "update agent", "remove agent", "delete agent", "list agents", "show my agents". IT: "modifica il mio agente", "aggiorna agente", "rimuovi agente", "lista agenti", "mostra i miei agenti". FR: "modifier mon agent", "supprimer agent", "lister les agents". ES: "editar mi agente", "eliminar agente", "listar agentes". DE: "Agenten bearbeiten", "Agenten löschen", "Agenten auflisten". PT: "editar meu agente", "remover agente", "listar agentes".

70

Quality

85%

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

SKILL.md
Quality
Evals
Security

Quality

Content

75%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 well-structured, actionable procedural skill with clear multi-step flows and a confirmation checkpoint on its destructive operation. The main gap is a missing explicit verification step after applying edits in the Edit flow.

Suggestions

Add an explicit 'Verify the change' step in the Edit flow (e.g., re-read the agent file and confirm the requested fields match) before reporting to the user.

Tighten the 'Common changes' list in the Edit flow to the few most likely edits, or move the enumeration to a reference, to improve conciseness.

Consider a short post-it read/verify step noting whether the resumed state still matches the agent being edited, to strengthen the feedback loop.

DimensionReasoningScore

Conciseness

The body is mostly lean procedural lists with domain-specific protocol (post-it, registry markers) rather than concepts Claude already knows; minor explanatory passages like the 'Common changes' enumeration could be trimmed.

4 / 5

Actionability

Concrete, executable guidance throughout — exact file paths (.claude/agents/{name}.md, Meta/agent-log.md), registry markers (MBIFC:CUSTOM_AGENTS_START/END), and the AskUserQuestion tool — with only small gaps for an instruction-only skill.

4 / 5

Workflow Clarity

Three clearly sequenced numbered flows; the destructive Remove flow has an explicit confirmation checkpoint and if-confirmed/if-not branch, satisfying the destructive-operation validation rule. Minor gap: the Edit flow lacks an explicit post-change verify step.

4 / 5

Progressive Disclosure

Well-organized into logical sections (Golden Rule, Post-it Protocol, Edit/Remove/List, Validation Rules) and self-contained with no bundle files; a 110-line multi-flow skill is appropriately kept in one place, though it slightly exceeds the simple-skill threshold.

4 / 5

Total

16

/

20

Passed

Description

95%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 is third-person, concise, and explicitly pairs capabilities with concrete multilingual trigger phrases. It is a strong, well-scoped description with comprehensive trigger coverage.

DimensionReasoningScore

Specificity

Lists several concrete actions — 'Edit, update, or remove an existing custom agent', 'Shows current config and asks what to change', 'handles listing all custom agents' — all in third person, though the verbs stay slightly more generic than the rubric's 5-anchor examples.

4 / 5

Completeness

Explicitly answers both 'what' (edit/update/remove/list, show config, ask what to change) and 'when' via a dedicated 'Triggers:' block with concrete phrases.

5 / 5

Trigger Term Quality

Comprehensive natural trigger phrases across six languages (EN/IT/FR/ES/DE/PT) with synonyms covered — 'remove agent'/'delete agent', 'list agents'/'show my agents', 'edit'/'update'.

5 / 5

Distinctiveness Conflict Risk

Clear niche (custom agent management) with distinct, specific triggers and minimal overlap risk with unrelated skills.

5 / 5

Total

19

/

20

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
gnekt/My-Brain-Is-Full-Crew
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.