Background jobs, long-running processes, and task management
48
36%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./src/skills/bundled/processes/SKILL.mdQuality
Discovery
14%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description is too vague and generic to effectively guide skill selection. It lists broad topic areas without specifying concrete actions or providing any 'Use when...' trigger guidance. The term 'task management' in particular creates high conflict risk with unrelated skills.
Suggestions
Add a 'Use when...' clause with explicit triggers, e.g., 'Use when the user needs to run processes in the background, manage job queues, monitor long-running tasks, or work with cron jobs and daemons.'
List specific concrete actions such as 'Start, stop, and monitor background processes, manage job queues, schedule recurring tasks, and handle async worker processes.'
Replace the generic term 'task management' with more distinctive terms like 'process lifecycle management' or 'job queue orchestration' to reduce conflict with project/task management skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague, abstract language ('background jobs', 'long-running processes', 'task management') without listing any concrete actions like 'start', 'monitor', 'kill', 'queue', or 'schedule'. | 1 / 3 |
Completeness | The description only vaguely addresses 'what' (background jobs, long-running processes, task management) and completely lacks any 'when' clause or explicit trigger guidance. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and the 'what' is also very weak. | 1 / 3 |
Trigger Term Quality | Terms like 'background jobs' and 'long-running processes' are somewhat relevant keywords users might use, but it misses common variations like 'cron', 'daemon', 'queue', 'async tasks', 'worker', 'scheduler', or 'process monitoring'. | 2 / 3 |
Distinctiveness Conflict Risk | 'Task management' is extremely generic and could conflict with project management, to-do list, CI/CD, or DevOps skills. 'Long-running processes' is also broad enough to overlap with many infrastructure or system administration skills. | 1 / 3 |
Total | 5 / 12 Passed |
Implementation
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill excels at providing concrete, executable code examples for every API method, making it highly actionable. However, it reads more like a comprehensive API reference document than a skill file — it's too long for a SKILL.md, lacks progressive disclosure to separate reference material from quick-start guidance, and misses workflow patterns for error recovery in long-running process management.
Suggestions
Extract the detailed TypeScript API reference and use cases into separate files (e.g., API_REFERENCE.md, EXAMPLES.md) and keep SKILL.md as a concise overview with links to those files.
Add an explicit workflow sequence for the common lifecycle: spawn → monitor → detect failure → handle error/restart → cleanup, with validation checkpoints.
Remove the best practices section (generic advice Claude already knows) and the status table (already shown inline in code comments) to reduce token usage.
Add a brief 'Quick start' section at the top showing the most common spawn-monitor-stop pattern in 5-10 lines before diving into the full API.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is fairly well-structured but includes some redundancy (e.g., the use cases section largely repeats patterns already shown in the API reference). The best practices section states obvious advice Claude already knows. The status table is borderline unnecessary given the inline comments already show the status values. | 2 / 3 |
Actionability | The skill provides fully executable TypeScript code examples with complete import statements, configuration objects, and concrete command-line examples. Every API method is demonstrated with copy-paste ready code including realistic parameters. | 3 / 3 |
Workflow Clarity | While individual API operations are clear, there's no explicit workflow sequence for managing the lifecycle of a process (spawn → monitor → handle failure → restart/cleanup). For long-running processes that could fail or consume excessive resources, there are no validation checkpoints or error recovery feedback loops described. | 2 / 3 |
Progressive Disclosure | This is a monolithic wall of API reference content (~200 lines) all in a single file with no references to external files. The chat commands, TypeScript API, use cases, and best practices are all inlined when the API reference and use cases could be split into separate files for better navigation. | 1 / 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 | |
e71a5f6
Table of Contents
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.