Find plugins

by Wondel.ai

Code quality and software design skills including Clean Code (Robert C. Martin), Refactoring patterns (Martin Fowler), A Philosophy of Software Design (John Ousterhout), The Pragmatic Programmer (Hunt & Thomas), Domain-Driven Design (Eric Evans), Working Effectively with Legacy Code (Michael Feathers), and Google's Developer Documentation Style Guide (technical-documentation)

by Carlos Araujo

Diagnostico diagnose-only: reproduz falhas, coleta evidencias, testa hipoteses e entrega relatorio de causa raiz sem executar correcoes.

by Carlos Araujo

Diagnostico diagnose-only: reproduz falhas, coleta evidencias, testa hipoteses e entrega relatorio de causa raiz sem executar correcoes.

by Seth Hobson

Documentation generation, code explanation, and technical writing with automated doc generation and tutorial creation

by Skylar

Adaptive, multi-agent engineering workflows for any codebase: audit, security/privacy threat assessment, remediation, feature discovery & build, performance, tests, dependencies, local review gates, doc alignment, onboarding, and code and concept normalization. Developer-in-the-loop, behavior-preserving, with shared conventions.

by Skylar

Adaptive, multi-agent engineering workflows for any codebase: audit, security/privacy threat assessment, remediation, feature discovery & build, performance, tests, dependencies, local review gates, doc alignment, onboarding, and code and concept normalization. Developer-in-the-loop, behavior-preserving, with shared conventions.

by Mojo AI Services, LLC

Splitting an oversized file without changing what it does: moving code rather than rewriting it, keeping every name and its callers, and ending in evidence a reader can check rather than a claim. Four cleanup skills were written for this pack and given an eval case each, run three times with the plugin and three times without it; this is the one whose runs beat their own baseline. The other three are recorded in docs/not-shipped with what was measured, because their cases could not tell the difference.

by Seth Hobson

Code cleanup, refactoring automation, and technical debt management with context restoration

by David Allada

Automated pull-request review on every harness: parallel reviewers from five lenses, confidence scoring that drops anything under 80, one comment posted with gh.

by Anthropic

Automated code review for pull requests using multiple specialized agents with confidence-based scoring.

by Carlos Araujo

Code review de PR com veredicto GO/NO-GO por finding sobre o merge e fluxo de backlog para findings diferiveis.

by Carlos Araujo

Code review de PR com veredicto GO/NO-GO por finding sobre o merge: NO-GO = merge bloqueado, corrigir nesta PR; GO = merge pode seguir, finding diferível registrado no backlog global (~/.backlog/backlog.json via skill /backlog, após confirmação). Fork do plugin oficial code-review da Anthropic (Apache-2.0).

Reviews your PRs every weekday morning, posts findings to Slack, files Linear issues for blockers

by William Hung

Principle-aware PR review. Layers a repo-specific review-mindset agent on top of pr-review-toolkit's 4+6 perspectives, with configurable principle-directory roots.

by Renford Nelson

A standalone code review skill for Claude Code — evidence-tiered findings, a required decision model, combined-findings anti-blur rules, and a single-clarifying-question resume contract, independent of any other plugin. Renders via ReportFindings and an optional review-dashboard Artifact; per-file review state persists to a caller-supplied location or stays ephemeral for a single pass.

by dobachi

Expert code reviewer providing constructive feedback on quality, security, performance, and maintainability.

by chock-core

trigger: secrets, eval/exec, unsanitized SQL, hallucinated dependencies. avoid: committing credentials, adding unverified packages, executing dynamic code. Install scan-secrets for the enforced counterpart of the secret slice (a commit-time gate), and verify-dependency-exists for the dependency slice (opt-in: disabled by default, needs a curated allowlist); the eval/exec and unsanitized-SQL guidance stays advisory (a gate can decide only the non-literal slice: agentic-code-security's code pack). [Advisory skill only; enforcement needs chock installed in the repo.]

by chock-core

trigger: secrets, eval/exec, unsanitized SQL, hallucinated dependencies. avoid: committing credentials, adding unverified packages, executing dynamic code. Install scan-secrets for the enforced counterpart of the secret slice (a commit-time gate), and verify-dependency-exists for the dependency slice (opt-in: disabled by default, needs a curated allowlist); the eval/exec and unsanitized-SQL guidance stays advisory (a gate can decide only the non-literal slice: agentic-code-security's code pack).

by chock-core

trigger: secrets, eval/exec, unsanitized SQL, hallucinated dependencies. avoid: committing credentials, adding unverified packages, executing dynamic code. Install scan-secrets for the enforced counterpart of the secret slice (a commit-time gate), and verify-dependency-exists for the dependency slice (opt-in: disabled by default, needs a curated allowlist); the eval/exec and unsanitized-SQL guidance stays advisory (a gate can decide only the non-literal slice: agentic-code-security's code pack). [Advisory skill only; enforcement needs chock installed in the repo.]

by David Allada

Simplify recently changed code for clarity, consistency and maintainability without changing what it does, following the project's own guideline files.

by insomnius

Evidence-based code-smell reviews and focused refactoring, informed by Refactoring.Guru

Cross-repo issue swarm: agent-ready GitHub issues become verified PRs (human merges). Opt in per repo with .swarm.json.

by Fars Saadeldin

Translate between generative code and the geometry it produces, keeping output assets lean instead of bloated.

by Seth Hobson

Technical debt reduction, dependency updates, and code refactoring automation