agent-release-swarm
Agent skill for release-swarm - invoke with $agent-release-swarm
39
6%
Does it follow best practices?
Impact
100%
2.94xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agents/skills/agent-release-swarm/SKILL.mdQuality
Discovery
0%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 is an extremely weak description that provides virtually no useful information for skill selection. It only names the skill and its invocation command without describing any capabilities, use cases, or trigger conditions. It fails on every dimension of the rubric.
Suggestions
Describe what 'release-swarm' actually does with concrete actions (e.g., 'Coordinates multi-agent release workflows, manages version bumps, changelog generation, and deployment orchestration').
Add an explicit 'Use when...' clause with natural trigger terms users would say (e.g., 'Use when the user needs to create a release, publish a new version, coordinate deployment steps, or manage release pipelines').
Remove the invocation instruction ('invoke with $agent-release-swarm') from the description and replace it with functional content that helps Claude distinguish this skill from others.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description provides no concrete actions whatsoever. 'Agent skill for release-swarm' is entirely vague and does not describe what the skill actually does. | 1 / 3 |
Completeness | Neither 'what does this do' nor 'when should Claude use it' is answered. The description only states the invocation command, providing no functional or contextual information. | 1 / 3 |
Trigger Term Quality | The only keyword is 'release-swarm', which is a technical/internal term unlikely to be naturally used by users. There are no natural language trigger terms describing the task domain. | 1 / 3 |
Distinctiveness Conflict Risk | The description is so vague that it's impossible to distinguish it from other agent skills. Without any domain or action specificity, it could conflict with any number of other skills. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
12%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is an extremely bloated, largely non-actionable document that reads more like marketing material for a fictional `ruv-swarm` CLI tool than a practical skill for Claude. The vast majority of commands are not executable since they depend on an unverifiable tool, and the content is massively over-long with repetitive patterns. The few concrete `gh` CLI examples are buried in noise.
Suggestions
Remove or replace all `npx ruv-swarm` commands with actual executable alternatives using `gh` CLI, standard shell commands, or clearly document that ruv-swarm must be installed as a prerequisite with installation instructions.
Reduce content by 70%+ by extracting the config file examples, GitHub Actions workflow, release notes template, and integration examples into separate referenced files.
Add explicit validation checkpoints with concrete commands (e.g., `gh release view --json` to verify release was created) rather than relying on opaque `--block-on-failure` flags.
Focus the main SKILL.md on a single clear workflow (e.g., standard release flow) with a quick-start section, and relegate advanced features, emergency procedures, and platform-specific examples to linked files.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at 400+ lines with massive repetition. Many sections show slight variations of the same `npx ruv-swarm github` commands with different flags. The release notes template, best practices bullet lists, and multiple integration examples are padding that Claude doesn't need. The content could be reduced by 70%+ without losing actionable information. | 1 / 3 |
Actionability | Nearly all commands reference `npx ruv-swarm` which is an unverifiable, likely non-existent CLI tool - none of these commands are executable or copy-paste ready. The `gh` CLI usage is more concrete but is mixed with fictional tooling, making it unclear what actually works. There's no way to verify or run most of this content. | 1 / 3 |
Workflow Clarity | The GitHub Actions workflow and some bash sequences show a reasonable step ordering (init → changelog → build → publish). However, validation steps are mostly delegated to opaque `npx ruv-swarm` commands with `--block-on-failure` flags rather than explicit checkpoints with feedback loops. The 'validate then proceed' pattern exists but is implicit rather than clearly enforced. | 2 / 3 |
Progressive Disclosure | This is a monolithic wall of text with everything inlined. Configuration files, workflow YAML, release notes templates, multiple agent descriptions, integration examples, and emergency procedures are all dumped into a single massive file. References to external files only appear at the very end with no clear navigation structure. Content desperately needs splitting into separate focused files. | 1 / 3 |
Total | 5 / 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 |
|---|---|---|
skill_md_line_count | SKILL.md is long (588 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
- Repository
- ruvnet/ruflo
- Commit
398f7c2
- 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.