skill-adapter

Analyzes existing plugins to extract their capabilities, then adapts and applies those skills to the current task. Acts as a universal skill chameleon that learns from other plugins. Activates when you request "skill adapter" functionality.

Install with Tessl CLI

npx tessl i github:jeremylongshore/claude-code-plugins-plus-skills --skill skill-adapter

What are skills?

1.05x

Quality

35%

Does it follow best practices?

Impact

98%

1.05x

Average score across 6 eval scenarios

Optimize this skill with Tessl

npx tessl skill review --optimize ./backups/skill-structure-cleanup-20251108-073936/plugins/examples/pi-pathfinder/skills/pi-pathfinder/SKILL.md

SKILL.md

Review

Evals

Evaluation results

96%

Code Quality Automation for a Node.js Monorepo

Plugin discovery and structured extraction

Criteria

Without context

With context

Searched plugins dirs

25%

75%

Command file extraction

100%

Agent file extraction

100%

Skill file extraction

100%

Script file extraction

100%

Named plugins analyzed

100%

Patterns extracted listed

100%

Adaptation described

90%

100%

Why approach chosen

80%

Limitations stated

90%

100%

Did not modify plugins

100%

Without context: $0.4538 · 1m 47s · 17 turns · 18 in / 6,564 out tokens

With context: $0.7418 · 2m 58s · 30 turns · 117 in / 10,054 out tokens

99%

Automated Deployment Pipeline for a Python Web Service

Multi-plugin synthesis and selection criteria

Criteria

Without context

With context

Multiple plugins examined

100%

Approaches merged

100%

Relevance criterion applied

100%

Quality/simplicity criterion applied

62%

87%

Plugin rejected or downweighted

100%

Syntax/commands adapted

100%

Complexity simplified

77%

100%

Context-specific adaptation

100%

Sources transparently listed

100%

Adaptation limitations noted

100%

No plugin files modified

100%

Without context: $0.3712 · 2m 16s · 11 turns · 60 in / 7,071 out tokens

With context: $0.4870 · 2m 21s · 16 turns · 271 in / 7,577 out tokens

98%

-2%

Automated Alerting and Test Reporting for a Backend Service

Limitations identification and transparency reporting

Criteria

Without context

With context

MCP plugin flagged

100%

MCP limitation stated

100%

API-key plugin flagged

100%

90%

API limitation stated

100%

Compatible plugin used

100%

Plugins analyzed listed

100%

Patterns extracted described

100%

Adaptation method explained

100%

Why approach chosen

100%

88%

All limitations documented

100%

Plugins not modified

100%

Without context: $0.2974 · 1m 33s · 11 turns · 60 in / 4,891 out tokens

With context: $0.4331 · 1m 54s · 17 turns · 66 in / 5,490 out tokens

100%

Log Aggregation Setup for a Distributed Service

Recency, popularity, and script pattern extraction

Criteria

Without context

With context

Recency criterion applied

100%

Popularity/featured criterion applied

100%

Script logic extracted

100%

Script error handling noted

100%

Script best practices identified

100%

Infeasible plugin identified

100%

Multiple plugins compared

100%

Correct output file name

100%

Error count per service

100%

Service prefix in output

100%

Plugins not modified

100%

Without context: $0.4188 · 1m 27s · 19 turns · 20 in / 4,587 out tokens

With context: $0.4577 · 1m 43s · 21 turns · 358 in / 5,480 out tokens

100%

Database Backup Automation for a PostgreSQL Production System

Enhancement and contextualization of adapted skills

Criteria

Without context

With context

Core logic preserved

100%

Port contextualized

100%

Backup directory contextualized

100%

Non-zero exit error handling added

100%

Empty file check added

100%

User feedback on success

100%

S3 upload removed

100%

Adaptation notes: core kept

100%

Adaptation notes: changes explained

100%

Adaptation notes: enhancements described

100%

Cloud-sync plugin addressed

100%

Plugins not modified

100%

Without context: $0.1691 · 49s · 7 turns · 8 in / 2,409 out tokens

With context: $0.2385 · 1m 13s · 9 turns · 10 in / 3,331 out tokens

100%

Plugin Ecosystem Catalog for a New Engineering Team

Meta-learning catalog and ecosystem mapping

Criteria

Without context

With context

All plugins cataloged

100%

Task types identified

100%

Cross-plugin patterns section present

100%

At least one shared pattern identified

100%

Ecosystem relationships section present

100%

At least one relationship described

100%

Recommendation table present

100%

Recommendations have rationale

100%

Script-level patterns referenced

100%

Plugins not modified

100%

Most reusable patterns noted

55%

100%

Without context: $0.2416 · 1m 22s · 8 turns · 9 in / 4,087 out tokens

With context: $0.3036 · 1m 32s · 11 turns · 266 in / 4,348 out tokens

Evaluated: 5 days ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

Code Quality Automation for a Node.js Monorepo Automated Deployment Pipeline for a Python Web Service Automated Alerting and Test Reporting for a Backend Service Log Aggregation Setup for a Distributed Service Database Backup Automation for a PostgreSQL Production System Plugin Ecosystem Catalog for a New Engineering Team

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.