agent-manager-skill
Manage multiple local CLI agents via tmux sessions (start/stop/monitor/assign) with cron-friendly scheduling.
57
48%
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 identifying the domain of managing CLI agents via tmux with cron scheduling. Its main weakness is the lack of an explicit 'Use when...' clause, which caps completeness. Adding natural trigger terms that users might actually say would also improve discoverability.
Suggestions
Add a 'Use when...' clause, e.g., 'Use when the user wants to run multiple agents in parallel, orchestrate background CLI tasks, or schedule agent runs.'
Include more natural user-facing trigger terms like 'parallel agents', 'background tasks', 'run multiple agents', 'agent orchestration', or 'batch agent execution'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'start/stop/monitor/assign' agents, mentions 'tmux sessions' as the mechanism, and 'cron-friendly scheduling' as an additional capability. These are concrete, actionable operations. | 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. The when is only implied by the description of capabilities. | 2 / 3 |
Trigger Term Quality | Includes relevant keywords like 'tmux', 'CLI agents', 'cron', 'scheduling', 'start/stop/monitor'. However, it misses natural user terms like 'background tasks', 'parallel agents', 'agent orchestration', or 'run multiple agents'. Users might not naturally say 'tmux sessions' when asking for this functionality. | 2 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: the combination of 'tmux sessions', 'local CLI agents', and 'cron-friendly scheduling' is very specific and unlikely to conflict with other skills. This is a well-defined operational domain. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
29%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill provides a useful set of CLI commands but lacks the depth needed to be truly actionable. There is no workflow sequencing, no validation/error handling guidance, and no supporting files or references for agent configuration or cron setup. The boilerplate limitations section wastes tokens without adding value.
Suggestions
Add a step-by-step workflow (e.g., 1. Run `doctor` to verify prerequisites → 2. Configure agents in `agents/` → 3. Start agents → 4. Monitor and verify output) with explicit validation checkpoints after each step.
Include a concrete example of an agent configuration file and a cron entry, rather than deferring to 'see the repo'.
Remove the generic 'Limitations' boilerplate and replace it with skill-specific constraints (e.g., max concurrent agents, tmux version requirements, known failure modes).
Add expected output examples for key commands (e.g., what `list` and `doctor` return) so Claude can verify success or diagnose failures.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Mostly efficient, but the 'Limitations' section is boilerplate filler that doesn't add skill-specific value (e.g., 'Do not treat the output as a substitute for environment-specific validation' is generic advice Claude already knows). The 'When to Use' section is slightly redundant with the commands shown. | 2 / 3 |
Actionability | Provides concrete CLI commands which is good, but they are listed without explaining expected outputs, flags, or error cases. There's no executable example of agent configuration, cron scheduling setup, or what the agents/ directory should contain—key details are deferred to 'see the repo' without specifics. | 2 / 3 |
Workflow Clarity | There is no sequenced workflow—commands are listed but not ordered into a coherent process (e.g., doctor → configure → start → monitor → assign). There are no validation checkpoints, no error recovery guidance, and no feedback loops for monitoring or troubleshooting failed agents. | 1 / 3 |
Progressive Disclosure | No bundle files are provided, and the skill references 'see the repo for examples' without any linked files, configuration templates, or structured navigation. There's no layered content organization—everything is in a flat, shallow document with no supporting references. | 1 / 3 |
Total | 6 / 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
431bfad
- 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.