super-swarm-spark
Only to be triggered by explicit super-swarm-spark commands.
54
42%
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 ./skills/super-swarm-spark/SKILL.mdQuality
Discovery
7%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 extremely weak across all dimensions. It provides no information about what the skill actually does, lists no concrete actions or capabilities, and relies entirely on an obscure command name as its only trigger. Without knowing what the skill accomplishes, Claude cannot make an informed decision about when to select it.
Suggestions
Add concrete capability descriptions explaining what the skill actually does (e.g., 'Orchestrates multi-agent task decomposition and parallel execution' or whatever the actual functionality is).
Add a 'Use when...' clause with explicit trigger conditions and natural language terms users might say, rather than relying solely on a specific command name.
Include specific actions the skill performs so Claude can distinguish it from other skills and understand its purpose (e.g., 'Spawns parallel sub-tasks, coordinates results, and merges outputs').
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description contains no concrete actions whatsoever. It does not describe what the skill does—only that it should be triggered by a specific command. 'Super-swarm-spark commands' is abstract and undefined. | 1 / 3 |
Completeness | The description fails to answer 'what does this do' entirely and only vaguely addresses 'when' by saying it should be triggered by explicit commands, without explaining what those commands are or what the skill accomplishes. | 1 / 3 |
Trigger Term Quality | The only keyword is 'super-swarm-spark commands,' which is technical jargon unlikely to be naturally used by a user. There are no natural language trigger terms that a user would say. | 1 / 3 |
Distinctiveness Conflict Risk | The unusual term 'super-swarm-spark' is distinctive enough that it's unlikely to conflict with other skills, but the lack of any capability description means Claude cannot meaningfully distinguish when to use it beyond pattern-matching on that specific phrase. | 2 / 3 |
Total | 5 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-crafted orchestration skill with strong actionability and clear workflow sequencing including validation checkpoints and error recovery loops. The main weaknesses are an internal inconsistency (12 vs 15 max agents mentioned in different places) and some verbosity that could be tightened. The content is appropriately structured but could benefit from splitting templates into separate referenced files.
Suggestions
Fix the inconsistency between '15 concurrent Sparky subagents' in the intro and 'Max 12' used everywhere else in the document
Consider extracting the Task Prompt Template and Execution Summary Template into separate referenced files to improve progressive disclosure
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly long but most content is functional (templates, process steps, scheduling rules). However, there's some redundancy—the max concurrency is stated as both 12 and 15 in different places, and some instructions are repeated across sections (e.g., plan file updating, commit rules). The template and summary sections add bulk but are justified for a complex orchestration skill. | 2 / 3 |
Actionability | The skill provides highly concrete, executable guidance: a complete task prompt template with numbered instructions, specific agent_type requirements, exact scheduling rules, example invocations, and a detailed execution summary template. Claude knows exactly what to do at each step. | 3 / 3 |
Workflow Clarity | The 6-step process is clearly sequenced with explicit validation checkpoints (Step 5 validates every completion, Step 6 performs integration fixes with test runs until green). There are feedback loops for error recovery (retry/escalate on failure, re-run tests until green), and the rolling pool scheduler has clear state management (pending/running/completed/failed). | 3 / 3 |
Progressive Disclosure | The content is well-structured with clear headers and sections, but it's entirely monolithic—everything is in one file with no references to external documentation. The task prompt template and execution summary template could potentially be separate files. For a skill of this complexity (~180 lines), some splitting would improve navigability. | 2 / 3 |
Total | 10 / 12 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 — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- am-will/codex-skills
- Commit
ca2c3b3
- 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.