CtrlK
BlogDocsLog inGet started
Tessl Logo

ralplan

Consensus planning entrypoint that auto-gates vague ralph/autopilot/team requests before execution

62

1.19x
Quality

42%

Does it follow best practices?

Impact

98%

1.19x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/ralplan/SKILL.md
SKILL.md
Quality
Evals
Security

Evaluation results

100%

Developer Request Routing Audit

Pre-execution gate routing classification

Criteria
Without context
With context

Vague auth gated

100%

100%

File-path passes

100%

100%

Vague build gated

100%

100%

camelCase symbol passes

100%

100%

Vague improvement gated

100%

100%

Issue number passes

100%

100%

force: prefix bypasses

100%

100%

Vague performance gated

100%

100%

Numbered steps passes

100%

100%

Vague optimize gated

100%

100%

Error reference passes

100%

100%

! prefix bypasses

100%

100%

Vague dashboard gated

100%

100%

PascalCase symbol passes

100%

100%

Code block passes

100%

100%

just-do-it not a bypass

100%

100%

Test runner passes

100%

100%

Vague codebase gated

100%

100%

100%

23%

Backend Infrastructure Selection for a New Microservice

RALPLAN-DR structured plan format

Criteria
Without context
With context

Pending approval status

0%

100%

Principles section present

100%

100%

3-5 principles listed

100%

100%

Decision Drivers section

66%

100%

Exactly top-3 drivers

0%

100%

Viable Options section

100%

100%

At least 2 options

100%

100%

Pros/cons per option

100%

100%

ADR section present

100%

100%

ADR Decision field

100%

100%

ADR Alternatives considered

100%

100%

ADR Why chosen

100%

100%

ADR Consequences

100%

100%

ADR Follow-ups

40%

100%

No implementation actions

100%

100%

96%

27%

Production Authentication Migration Planning

Deliberate mode auto-trigger for high-risk migration

Criteria
Without context
With context

Pending approval status

0%

100%

Pre-mortem section present

100%

100%

Exactly 3 failure scenarios

0%

66%

Failure scenarios are concrete

87%

100%

Test plan section present

100%

100%

Unit tests included

100%

100%

Integration tests included

100%

100%

E2E tests included

50%

100%

Observability included

100%

100%

RALPLAN-DR structure

25%

100%

No implementation actions

100%

100%

Repository
Yeachan-Heo/oh-my-claudecode
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.