timurgaleev

159 mods across 2 repositories, 18 stars between them.

unfreeze

97

timurgaleev/vibestack

Skill Claude Code

Clear the freeze boundary set by /freeze, allowing edits to all directories again.

not rated 7 changed 8d ago A 19 tokens original MIT

vibe-upgrade

98

timurgaleev/vibestack

Skill Claude CodeCodex

Upgrade the installed vibestack pack to the latest release, run version migrations, and show what changed.

not rated 7 changed 3d ago D 26 tokens original MIT

address-pr-review

99

timurgaleev/vibestack

Skill Claude Code

Work a PR's open review threads and failing CI checks to a close: fix or explain, push, reply, resolve.

not rated 7 changed 5d ago A SkillSpector: pass 29 tokens original MIT

agent-eval

100

timurgaleev/vibestack

Skill Claude Code

Build and run an eval harness for an LLM agent or prompt, with scoring and a regression gate.

not rated 7 changed 4d ago A SkillSpector: warn 25 tokens original MIT

ai-cost-guard

101

timurgaleev/vibestack

Skill Claude Code

Find code paths that can run up an unbounded LLM or inference bill and require a dollar cap before shipping.

not rated 7 changed 5d ago A SkillSpector: warn 28 tokens original MIT

aws-cost

102

timurgaleev/vibestack

Skill Claude Code

Read-only AWS cost review: where last month's money went, what changed, and the top actions to cut the bill.

not rated 7 changed 7d ago C 27 tokens original MIT

bedrock-guardrails

103

timurgaleev/vibestack

Skill Claude Code

Read-only audit of Amazon Bedrock guardrails, IAM, logging and data residency before shipping an LLM feature.

not rated 7 changed 7d ago A SkillSpector: warn 29 tokens original MIT

connect-review

104

timurgaleev/vibestack

Skill Claude Code

Review an Amazon Connect contact center, IVR or voice bot for latency, reliability, cost and flow design.

not rated 7 changed 5d ago A SkillSpector: warn 25 tokens original MIT

kb-review

105

timurgaleev/vibestack

Skill Claude Code

Review a Bedrock Knowledge Base or RAG pipeline: chunking, retrieval quality, recall@5 and cost per query.

not rated 7 changed 7d ago A SkillSpector: warn 28 tokens original MIT

mcp-review

106

timurgaleev/vibestack

Skill Claude Code

Review an MCP server for tool design, auth, input validation and prompt-injection risk before publishing it.

not rated 7 changed 5d ago A SkillSpector: warn 25 tokens original MIT

unslop

107

timurgaleev/vibestack

Skill Claude Code

Rewrite machine-sounding English prose (README, PR bodies, posts) in a human voice, keeping every fact.

not rated 7 changed 7d ago D 26 tokens original MIT

vibe

108

timurgaleev/vibestack

Skill Claude Code

Router for the vibestack skills: name the task and it picks the right skill, also where there is no / picker.

not rated 7 changed 3d ago A 29 tokens original MIT

timurgaleev/vibestack

Agent Claude Code

AI citation strategist who optimizes content for inclusion in LLM answers and AI search. Use PROACTIVELY when structuring content for AI discoverability, planning citation-friendly assets, or auditing AI visibility.

not rated 7 yesterday A 48 tokens copy · 95% MIT

ai-engineer

110

timurgaleev/vibestack

Agent Claude Code

AI/ML engineer for RAG, LLM integration, and MLOps. Use PROACTIVELY when building AI features. Evals go to /agent-eval, spend caps to /ai-cost-guard, RAG review to /kb-review.

not rated 7 changed 5d ago A 57 tokens original MIT

backend-architect

111

timurgaleev/vibestack

Agent Claude Code

Senior backend specialist for scalable APIs, database schemas, caching, and cloud infrastructure. Use PROACTIVELY when designing backend services, choosing database patterns, or planning for scale, security, and reliability.

not rated 7 yesterday A 44 tokens copy · 86% MIT

bug-hunter

112

timurgaleev/vibestack

Agent Claude Code needs its repo

Debugging specialist for errors and test failures. /investigate owns root-cause debugging; use this for a scoped diagnosis inside another skill or where the pack is not installed.

not rated 7 changed 7d ago C 39 tokens original MIT

build-doctor

113

timurgaleev/vibestack

Agent Claude Code needs its repo

Lint, typecheck, and build specialist. Runs checks, finds root causes, and fixes all issues automatically.

not rated 7 yesterday C 26 tokens original MIT

code-reviewer

114

timurgaleev/vibestack

Agent Claude Code

Diff reviewer for correctness, security, and fit. /review owns the pre-merge review (/codex review for a second model); use this for a scoped read-only pass inside another skill or where the pack is not installed.

not rated 7 changed 5d ago A 50 tokens copy · 86% MIT

code-shaper

115

timurgaleev/vibestack

Agent Claude Code

Code refactoring without changing behavior.

not rated 7 yesterday A 11 tokens original MIT

timurgaleev/vibestack

Agent Claude Code

Codebase orientation specialist who maps unfamiliar repos for new engineers. Use PROACTIVELY when onboarding to a new codebase, producing architecture tours, or generating onboarding docs.

not rated 7 yesterday A 41 tokens copy · 97% MIT

content-creator

117

timurgaleev/vibestack

Agent Claude Code

General content creator for blog posts, newsletters, and long-form technical writing. Use PROACTIVELY when drafting articles, newsletters, or repurposing content across channels.

not rated 7 yesterday A 38 tokens copy · 83% MIT

database-optimizer

118

timurgaleev/vibestack

Agent Claude Code

Database performance specialist for query plans, indexing, schema design, and tuning. Use PROACTIVELY when investigating slow queries, designing indexes, or refactoring schemas for scale.

not rated 7 yesterday A 39 tokens copy · 86% MIT

developer-advocate

119

timurgaleev/vibestack

Agent Claude Code

Developer advocate for community content, conference talks, and developer experience advocacy. Use PROACTIVELY when planning DevRel content, evaluating developer experience, or designing community programs.

not rated 7 yesterday A 39 tokens copy · 94% MIT

devops-automator

120

timurgaleev/vibestack

Agent Claude Code

DevOps engineer for Terraform/CDK, CI/CD, containers, and observability. Use PROACTIVELY when writing infrastructure code; /setup-deploy and /land-and-deploy own this repo's deploy pipeline.

not rated 7 changed 7d ago A 50 tokens copy · 89% MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: