agent-migration-plan

Agent skill for migration-plan - invoke with $agent-migration-plan

Install with Tessl CLI

npx tessl i github:ruvnet/claude-flow --skill agent-migration-plan

What are skills?

1.83x

Review — 7%

Does it follow best practices?

If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:

npx tessl skill review --optimize ./path/to/skill

Learn more

Evaluation — 99%

↑ 1.83x

Agent success when using this skill

Validation — 10 / 11 Passed

Validation for skill structure

SKILL.md

Review

Evals

Evaluation results

100%

57%

Modernizing Claude's Automation Toolkit

Agent definition format

Criteria

Without context

With context

YAML frontmatter present

100%

role field present

100%

name field present

100%

responsibilities list

71%

100%

capabilities list

100%

tools.allowed list

37%

100%

tools.restricted list

100%

Pattern trigger format

100%

Keyword trigger present

100%

Priority values valid

100%

All commands converted

100%

Agent files in correct directory

100%

Without context: $0.3618 · 1m 51s · 23 turns · 139 in / 5,268 out tokens

With context: $0.6153 · 1m 48s · 26 turns · 364 in / 5,785 out tokens

97%

16%

Charting the Path to an Agent-Driven Workflow

Migration planning and backwards compatibility

Criteria

Without context

With context

Step 1: agents directory

25%

100%

Step 2: convert commands

100%

Step 3: update patterns

75%

100%

Step 4: test handoffs

87%

100%

Step 5: gradual rollout

100%

Keep command files

100%

Migration warnings

100%

Category mapping

33%

66%

No functionality loss criterion

62%

100%

All commands covered

100%

Success metrics listed

87%

100%

Plan is a deliverable file

100%

Without context: $0.3073 · 1m 53s · 14 turns · 19 in / 5,641 out tokens

With context: $0.6582 · 2m 32s · 21 turns · 184 in / 8,605 out tokens

100%

60%

Building a Focused Agent Team for Acme's Platform

Role-based tool access restrictions

Criteria

Without context

With context

Coordinator restricts Bash

37%

100%

Coordinator restricts Write

37%

100%

Coordinator restricts Edit

37%

100%

Analyst restricts Write/Edit/Bash

30%

100%

Monitor restricts Write/Edit/Bash

37%

100%

GitHub agent allows Bash

75%

100%

GitHub agent restricts Write

25%

100%

GitHub agent restricts Edit

25%

100%

All agents have tool blocks

12%

100%

Tools.allowed non-empty

57%

100%

Tools.restricted non-empty

100%

Role values correct

83%

100%

Without context: $0.3281 · 1m 34s · 22 turns · 25 in / 5,087 out tokens

With context: $0.5803 · 1m 44s · 26 turns · 31 in / 6,023 out tokens

Evaluated: 3 days ago
Agent: Claude Code
Model: Unknown

Table of Contents

Modernizing Claude's Automation Toolkit Charting the Path to an Agent-Driven Workflow Building a Focused Agent Team for Acme's Platform

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.