CtrlK
BlogDocsLog inGet started
Tessl Logo

02-meta-skill-forge-150

[02] META. Create new skills when existing ones don't cover the task. Analyze unique requirements, build framework (Frame → Research → Plan → Execute), integrate risks, and declare new skill. Use when facing novel problems that existing skills can't address.

68

1.62x

Quality

51%

Does it follow best practices?

Impact

96%

1.62x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/data/02-meta-skill-forge-150/SKILL.md
SKILL.md
Quality
Evals
Security

Evaluation results

88%

16%

Cross-Team Code Review Coordination

Gap analysis and framework structure

Criteria
Without context
With context

Skill naming convention

0%

100%

Existing skills evaluated

100%

100%

Gap justified verdict

100%

100%

Four-phase framework present

0%

0%

Unique aspects documented

100%

100%

Core challenges documented

100%

100%

Success criteria defined

100%

100%

Failure modes identified

100%

100%

Frontmatter name field

0%

100%

Core principle stated

100%

100%

When to use and NOT use

100%

100%

No over-engineering simple tasks

100%

100%

Without context: $0.3653 · 2m 13s · 18 turns · 25 in / 6,307 out tokens

With context: $0.5040 · 2m 32s · 21 turns · 370 in / 7,192 out tokens

100%

51%

Incident Post-Mortem Skill for SRE Teams

Risk integration and quality checkpoints

Criteria
Without context
With context

Risk table format

0%

100%

H/M/L likelihood values

0%

100%

H/M/L impact values

0%

100%

Quality gates per phase

80%

100%

150% Rule table

0%

100%

Failure modes table format

0%

100%

Operational rules numbered

100%

100%

Output format section

100%

100%

What This Skill Does section

100%

100%

Safeguards or recovery paths

62%

100%

All required template sections

100%

100%

Without context: $0.5524 · 3m 43s · 19 turns · 1,729 in / 10,688 out tokens

With context: $0.5645 · 3m 13s · 21 turns · 318 in / 9,039 out tokens

100%

43%

Product Requirements Decomposition Skill

Approval proposal, examples section, and evolution planning

Criteria
Without context
With context

Approval proposal present

100%

100%

Proposal has New Skill name

100%

100%

Proposal has Fills Gap section

100%

100%

Proposal has structure summary

30%

100%

Approval question asked

100%

100%

Bad example included

0%

100%

Good example included

100%

100%

Examples contrast visible

12%

100%

Evolution planning present

100%

100%

Seven-step protocol documented

50%

100%

Skill naming with -150

0%

100%

Frame→Research→Plan→Execute in skill

0%

100%

Without context: $0.3747 · 2m 47s · 16 turns · 507 in / 7,789 out tokens

With context: $0.4581 · 2m 34s · 18 turns · 574 in / 7,140 out tokens

Repository
majiayu000/claude-skill-registry
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.