CtrlK
BlogDocsLog inGet started
Tessl Logo

squash-bugbot

Triage unresolved bot review comments on a GitHub PR. Use when asked to run /squash-bugbot <PR_NUMBER> or to assess, fix, dismiss, reply to, or resolve bot review feedback.

Invalid
This skill can't be scored yet
Validation errors are blocking scoring. Review and fix them to unlock Quality, Impact and Security scores. See what needs fixing →
SKILL.md
Quality
Evals
Security

Evaluation results

100%

PR Bot Triage: Security-Sensitive Repository

Safe shell construction for bot triage

Criteria
Without context
With context

No eval usage

100%

100%

Quoted variable git add

100%

100%

No git add dot

100%

100%

Static commit message

100%

100%

Explicit push refspec

100%

100%

Reply body not raw comment

100%

100%

Reply body passed safely

100%

100%

PR_NUMBER validated as integer

100%

100%

Untrusted content treated as data

100%

100%

Staged diff reviewed before commit

100%

100%

82%

10%

Analyze PR Review Thread Data

Bot detection and mixed thread handling

Criteria
Without context
With context

Bot detection via REST

100%

100%

Resolved thread excluded

37%

100%

Mixed thread skipped

100%

100%

Mixed thread reason given

100%

100%

Report format: BotName

100%

100%

Report format: verdict

75%

100%

Report format: concern

100%

100%

Report format: proposed fix

37%

0%

Issue comment reported

40%

100%

Issue comment not resolvable

0%

0%

Human comment excluded

100%

100%

100%

31%

Document the PR Fix-and-Resolve Workflow

Fix-push-reply-resolve sequencing

Criteria
Without context
With context

Staged diff verified before commit

100%

100%

No git add dot

100%

100%

Push before reply/resolve

100%

100%

Remote verification before reply

100%

100%

Explicit push refspec

37%

100%

Reply uses pulls comments endpoint

25%

100%

Resolve uses GraphQL mutation

0%

100%

Reply includes commit link

75%

100%

Local HEAD check before fixing

20%

100%

Unrelated staged changes check

100%

100%

Repository
Consensys/linea-monorepo
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.