agent-manager-skill
Manage multiple local CLI agents via tmux sessions (start/stop/monitor/assign) with cron-friendly scheduling.
67
60%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/antigravity-agent-manager-skill/SKILL.mdQuality
Discovery
67%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 concise and specific about its capabilities, clearly naming the technologies involved (tmux, cron, CLI agents) and the actions supported (start/stop/monitor/assign). Its main weakness is the absence of an explicit 'Use when...' clause, which would help Claude know exactly when to select this skill. The trigger terms are somewhat technical and could benefit from more natural language variations.
Suggestions
Add a 'Use when...' clause, e.g., 'Use when the user wants to run multiple agents in parallel, manage background agent sessions, or schedule recurring agent tasks.'
Include more natural trigger terms users might say, such as 'parallel agents', 'background tasks', 'agent orchestration', or 'run agents simultaneously'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'start/stop/monitor/assign' agents via tmux sessions, with 'cron-friendly scheduling'. These are concrete, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers 'what does this do' (manage local CLI agents via tmux with scheduling), but lacks an explicit 'Use when...' clause or equivalent trigger guidance, which caps this at 2 per the rubric. | 2 / 3 |
Trigger Term Quality | Includes relevant keywords like 'tmux', 'CLI agents', 'cron', 'scheduling', 'sessions', but misses common user variations like 'background tasks', 'parallel agents', 'agent orchestration', or 'run multiple agents'. Some terms are fairly technical. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of tmux sessions, local CLI agents, and cron scheduling creates a very distinct niche. Unlikely to conflict with other skills due to the specific technology stack mentioned. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
52%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill is commendably concise and provides real CLI commands, but it reads more like a quick reference card than an actionable skill. It lacks workflow sequencing (e.g., run doctor first, then configure agents, then start), validation/error handling steps, and concrete details about agent configuration. The reference to external documentation is too vague to be useful.
Suggestions
Add a numbered workflow showing the typical sequence: run doctor to verify prerequisites → configure agents in agents/ directory → start agents → monitor output, with explicit validation at each step (e.g., check doctor output before proceeding).
Include a brief example of agent configuration (e.g., a minimal agents/EMP_0001.yaml or similar) so users know what to set up before running commands.
Replace 'see the repo for examples' with specific file references like 'See [agents/example.yaml](agent-manager-skill/agents/example.yaml) for configuration format'.
Add error recovery guidance: what to do if 'doctor' reports issues, if an agent fails to start, or if monitor shows errors.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. No unnecessary explanations of what tmux is or how CLI agents work. Every section earns its place. | 3 / 3 |
Actionability | Provides concrete CLI commands that are copy-paste ready, but lacks detail on agent configuration (the agents/ directory structure), expected outputs, and what 'doctor' checks. The 'see the repo for examples' is vague. | 2 / 3 |
Workflow Clarity | Commands are listed but there's no clear workflow sequence, no validation checkpoints, and no error recovery guidance. For managing multiple agents (a potentially destructive/complex operation), there's no feedback loop for verifying agent status after start, no guidance on what to do if start fails, and no sequencing of doctor → list → start → monitor. | 1 / 3 |
Progressive Disclosure | The content is reasonably short and organized into sections, but the reference to 'see the repo for examples' is vague rather than pointing to specific files. No clear links to detailed configuration docs or advanced usage guides. | 2 / 3 |
Total | 8 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- boisenoise/skills-collections
- Commit
636b862
- 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.