CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-release-swarm

Agent skill for release-swarm - invoke with $agent-release-swarm

56

2.94x
Quality

33%

Does it follow best practices?

Impact

100%

2.94x

Average score across 3 eval scenarios

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/agent-release-swarm/SKILL.md

The canonical home for this skill is agent-release-swarm in ruvnet/claude-flow

SKILL.md
Quality
Evals
Security

Quality

Content

38%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is a large, monolithic command reference with broad coverage of release-automation tasks but suffers from systematic path corruption that breaks executability, verbosity from inlined config/templates, and no progressive disclosure into bundle files. Validation steps exist but are not woven into a clear sequenced workflow.

Suggestions

Fix the systematic path corruption: replace '$' with '/' throughout (e.g. 'repos/:owner/:repo/compare/', '.github/workflows/release.yml', 'actions/checkout@v3') so commands are executable.

Move the full config YAML, workflow YAML, release-notes template, and per-agent command catalogs into separate reference files under references/ and keep SKILL.md as a concise overview with one-level-deep links.

Reframe the release process as an explicit numbered sequence with validation checkpoints (plan → validate → version → build → test → deploy → monitor/rollback) rather than scattered command examples.

DimensionReasoningScore

Conciseness

The ~580-line body inlines a full reference (entire config YAML, workflow YAML, a complete release-notes template, generic 'Best Practices' bullets, and an embedded tools/hooks frontmatter block) that is noticeably verbose and padded beyond what a SKILL.md overview needs.

2 / 5

Actionability

It provides many concrete gh CLI and npx ruv-swarm commands, but path separators are systematically corrupted ('$' in place of '/', e.g. 'repos/:owner/:repo$compare', '.github$workflows$release.yml', 'actions$checkout@v3') and the core ruv-swarm subcommands/flags rely on an unverified external CLI, so examples are not executable as written.

3 / 5

Workflow Clarity

Validation commands exist (release-validate, compat-test, security scanning, rollback) and a GitHub Actions workflow is shown, but they are presented as scattered command examples rather than a clearly sequenced Claude-followed workflow with explicit checkpoints; because releases are destructive/batch operations, the missing integrated checkpoints cap this at 3.

3 / 5

Progressive Disclosure

No bundle files exist and the body is a monolithic wall inlining content that belongs in separate files; the only 'See also' references point to non-existent files with corrupted paths ('.$workflow-automation.md', '.$multi-repo-swarm.md').

2 / 5

Total

10

/

20

Passed

Description

28%Weight 40%Scale 1-5

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 frontmatter description is meta-instructional rather than capability-oriented: it tells how to invoke the skill but not what it does or when to use it. It names the domain yet omits all concrete actions and trigger phrases.

Suggestions

Rewrite the description to state concrete capabilities, e.g. 'Orchestrate software releases: generate changelogs, bump versions, build multi-platform artifacts, and deploy across npm, Docker, and GitHub.'

Add an explicit 'Use when...' clause with natural trigger phrases such as 'cutting a release', 'generating a changelog', 'version bump', or 'multi-platform deployment'.

Replace the invocation syntax ('$agent-release-swarm') in the description with capability language; invocation details belong in usage docs, not the description field.

DimensionReasoningScore

Specificity

The description names the domain ('release-swarm') but describes no concrete actions — it states only that it is 'an Agent skill for release-swarm' and how to invoke it, with no mention of changelog generation, versioning, or deployment.

2 / 5

Completeness

It gives only a vague 'what' (an agent skill for release-swarm) and no 'when' guidance — there is no 'Use when...' clause, capping completeness well below the explicit-trigger anchor.

2 / 5

Trigger Term Quality

The only keyword present is 'release-swarm' plus the invocation syntax '$agent-release-swarm'; there are none of the natural phrases a user would say (e.g. 'release', 'deploy', 'changelog', 'version bump'), so it sits just above the no-keywords anchor.

2 / 5

Distinctiveness Conflict Risk

'release-swarm' is a reasonably distinct niche name, but because the description conveys no capability detail it could still overlap with other release-automation or deployment skills.

3 / 5

Total

9

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (588 lines); consider splitting into references/ and linking

Warning

relative_links

Relative link issues: 2 missing, 1 suspicious

Warning

Total

14

/

16

Passed

Repository
ruvnet/ruflo
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.