CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-manager-skill

Manage multiple local CLI agents via tmux sessions (start/stop/monitor/assign) with cron-friendly scheduling.

62

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/antigravity-agent-manager-skill/SKILL.md

The canonical home for this skill is agent-manager-skill in sickn33/antigravity-awesome-skills

SKILL.md
Quality
Evals
Security

Quality

Content

87%

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

The body is concise, actionable, and well-organized with copy-paste-ready commands, but it lists commands in isolation rather than as a sequenced workflow with validation checkpoints for multi-agent management operations.

Suggestions

Add a sequenced workflow with explicit validation checkpoints (e.g., doctor -> start -> verify via 'monitor --follow' -> assign) instead of presenting commands as an unsequenced list.

Include a feedback loop for start/assign operations (confirm the agent session is running and check logs for errors before proceeding), since managing multiple agents is a batch-like operation that benefits from verification.

DimensionReasoningScore

Conciseness

The body is lean (~40 lines) with no re-explanation of concepts Claude already knows and no padding; every section (When to Use, Prerequisites, Common commands, Notes, Limitations) earns its place.

3 / 3

Actionability

Provides fully executable, copy-paste-ready commands (e.g., 'python3 agent-manager/scripts/main.py start EMP_0001') including a concrete heredoc-based assign example, matching the anchor for executable code with specific examples.

3 / 3

Workflow Clarity

Commands are presented individually rather than as a sequenced workflow, and there are no validation/verification checkpoints for the batch-like operations of starting, assigning, and monitoring multiple agents, capping workflow clarity at 2 per the guidelines.

2 / 3

Progressive Disclosure

At under 50 lines with no need for external reference files (none exist in references/scripts/assets), the well-organized sectioned structure satisfies the simple-skill allowance for a top score in progressive disclosure.

3 / 3

Total

11

/

12

Passed

Description

60%

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 specific and concrete about capabilities but omits an explicit 'when to use' trigger clause, capping completeness and trigger-term quality. Distinctiveness is decent but weakened by the broad term 'agents' without disambiguating triggers.

Suggestions

Add an explicit 'Use when...' clause with natural trigger phrases (e.g., 'Use when you need to run multiple CLI agents in parallel, manage tmux agent sessions, or schedule recurring agent tasks with cron') to satisfy completeness and trigger coverage.

Expand trigger-term variations with phrasings users would actually say ('parallel agents', 'background agents', 'schedule recurring agent runs') to improve trigger term quality.

Sharpen distinctiveness by contrasting the niche against generic agent skills, emphasizing 'local tmux-based' orchestration rather than remote/cloud agent management.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ("start/stop/monitor/assign") plus a concrete mechanism ("tmux sessions", "cron-friendly scheduling"), matching the anchor for listing several specific concrete actions.

3 / 3

Completeness

Clearly answers WHAT the skill does, but there is no explicit "Use when..." clause or equivalent trigger guidance, so per the judging guidelines completeness is capped at 2.

2 / 3

Trigger Term Quality

Contains relevant natural keywords ("local CLI agents", "tmux sessions", "cron") but lacks common variations (e.g., "parallel agents", "background agents", "scheduled agent runs") and no expanded trigger list, matching the 'some relevant keywords but missing common variations' anchor.

2 / 3

Distinctiveness Conflict Risk

The tmux-plus-cron niche is fairly specific, but "agents" is a broad term and the description lacks explicit distinct triggers, leaving moderate overlap risk with general agent/orchestration skills.

2 / 3

Total

9

/

12

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
boisenoise/skills-collections
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.