CtrlK
BlogDocsLog inGet started
Tessl Logo

framework-migration-legacy-modernize

Orchestrate a comprehensive legacy system modernization using the strangler fig pattern, enabling gradual replacement of outdated components while maintaining continuous business operations through ex

42

Quality

42%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills/skills/framework-migration-legacy-modernize/SKILL.md

The canonical home for this skill is framework-migration-legacy-modernize in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

31%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 body lays out a well-structured phased workflow but suffers from verbosity, non-executable prose prompts, missing validation checkpoints for destructive operations, and a broken external reference. Tightening the prose, adding executable examples, and creating the referenced playbook file would substantially improve quality.

Suggestions

Add explicit validation checkpoints and rollback triggers as feedback loops for destructive steps (decommissioning, traffic cutover) so workflow clarity can exceed the destructive-operation cap of 3.

Replace or supplement prose subagent prompts with concrete, executable examples (commands, config snippets, or code) to raise actionability.

Either create the referenced 'resources/implementation-playbook.md' (or move it under 'references/') and split bulk detail into it, fixing the broken path so progressive disclosure is real.

DimensionReasoningScore

Conciseness

An extended-thinking block explains the strangler fig metaphor ('named after the tropical fig tree that gradually envelops and replaces its host') and rationale Claude already knows, adding noticeable padding beyond what the steps require.

2 / 5

Actionability

Each phase is an elaborate prose prompt for a subagent rather than executable code or concrete commands; guidance is high-level and missing the specific steps to actually execute the migration.

2 / 5

Workflow Clarity

Phases are clearly sequenced with context passing between steps, but destructive/batch operations (legacy decommissioning, database cleanup, traffic cutover) lack explicit validate->fix->retry feedback loops, capping this at 3 per the destructive-operations rule.

3 / 5

Progressive Disclosure

No bundle directories exist and the single referenced file ('resources/implementation-playbook.md') points to a nonexistent path (body says 'resources/' not 'references/'), so the monolithic inlined content is not split across real files.

2 / 5

Total

9

/

20

Passed

Description

53%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 description conveys a clear purpose and a reasonably distinct niche, but it lacks an explicit activation trigger and is truncated mid-sentence, weakening its completeness and specificity. Adding a 'Use when...' clause and completing the sentence would meaningfully raise the score.

Suggestions

Add an explicit 'Use when...' trigger clause listing natural user phrases like 'legacy migration', 'modernize old code', or 'strangler fig migration'.

Complete the truncated description (it currently ends mid-word at 'through ex') so the capability statement is whole.

List a few more concrete actions (e.g., 'assess technical debt, build characterization tests, route traffic via a facade') to move specificity from 1-2 actions toward comprehensive coverage.

DimensionReasoningScore

Specificity

Names the domain ('legacy system modernization') and a couple of concrete actions ('gradual replacement of outdated components', 'maintaining continuous business operations') but is not comprehensive, and the description is truncated mid-word ('through ex'), leaving coverage incomplete.

3 / 5

Completeness

Has a clear 'what' but no explicit 'Use when...' trigger clause, so per the guideline a missing trigger caps completeness at 3.

3 / 5

Trigger Term Quality

Includes relevant domain terms ('legacy system modernization', 'strangler fig pattern', 'gradual replacement') but misses common natural variations a user would actually say ('legacy migration', 'refactor old code', 'modernize').

3 / 5

Distinctiveness Conflict Risk

'strangler fig pattern' combined with 'legacy system modernization' carves a fairly distinct niche with only minor overlap risk against general refactoring or migration skills.

4 / 5

Total

13

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
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.