CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-release-swarm

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

44

2.94x

Quality

13%

Does it follow best practices?

Impact

100%

2.94x

Average score across 3 eval scenarios

SecuritybySnyk

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./.agents/skills/agent-release-swarm/SKILL.md
SKILL.md
Quality
Evals
Security

Evaluation results

100%

74%

Automate Release Publishing for an Open Source Node.js Library

GitHub Actions release workflow

Criteria
Without context
With context

Tag trigger

100%

100%

Full git history

100%

100%

gh CLI auth

0%

100%

Release swarm init

100%

100%

Spawn agents flag

0%

100%

Draft release creation

0%

100%

Release publishing step

0%

100%

Asset upload loop

0%

100%

Changelog generation

0%

100%

Announcement issue

0%

100%

Release assets step

0%

100%

Without context: $0.2991 · 1m 30s · 18 turns · 25 in / 4,538 out tokens

With context: $0.3496 · 1m 15s · 16 turns · 19 in / 3,739 out tokens

100%

37%

Set Up Release Automation Configuration for a Microservices Platform

Release config and changelog generation

Criteria
Without context
With context

Config file location

100%

100%

Semantic strategy

100%

100%

Breaking keywords

0%

100%

Features section labels

100%

100%

Bug fixes section labels

100%

100%

Documentation section labels

100%

100%

ruv-swarm changelog command

50%

100%

Categorize and migration flags

0%

100%

CHANGELOG.md output

100%

100%

PR creation

100%

100%

Changelog PR title prefix

0%

100%

Without context: $0.3254 · 1m 24s · 23 turns · 28 in / 4,425 out tokens

With context: $0.4557 · 1m 30s · 21 turns · 279 in / 4,872 out tokens

100%

86%

Production Safety Scripts for a High-Traffic SaaS Platform

Release validation and rollback configuration

Criteria
Without context
With context

Validate command

0%

100%

Block on failure flag

0%

100%

Version conflict check

0%

100%

API breaking changes check

0%

100%

Security vulnerabilities check

0%

100%

Performance regression check

0%

100%

Rollback command

0%

100%

Error rate threshold

0%

100%

Latency threshold

0%

100%

Availability threshold

0%

100%

Canary stage percentage

100%

100%

Partial stage percentage

0%

100%

Full stage approval

100%

100%

Without context: $0.5918 · 3m 59s · 26 turns · 32 in / 10,488 out tokens

With context: $0.5954 · 1m 51s · 23 turns · 1,794 in / 6,075 out tokens

Repository
ruvnet/claude-flow
Evaluated
Agent
Claude Code
Model
Claude Sonnet 4.6

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.