Repository
ash1794/vibe-engineering agent skills
- skills
- 33
- GitHub stars
- 163
GitHub description: “33 engineering discipline skills for Claude Code, OpenAI Codex & Gemini CLI + a CLI for CI/CD enforcement. Extracted from real-world multi-agent system development. Born from real pain, not theory.”
- Stars
- 163 (42 forks)
- Licence
- MIT
- Last push
- Oct 2026
- Created
- Feb 2026
- claude-code
- claude-code-plugin
- developer-tools
- skills
- testing
- vibe-coding
- ai-agents
- ai-coding
- anthropic
- claude
- code-quality
- developer-experience
- multi-agent
- software-engineering
- agents-md
- codex-skills
Install all skills
npx skills add ash1794/vibe-engineeringAdd --skill <name> for a single skill and -a <agent> to choose the agent (see the agent guides).
Skills in ash1794/vibe-engineering, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Audits tests for concurrency safety — race conditions, shared mock state, cleanup ordering. | ash1794/ | 163 | — | ~665 | Automated safety check: Pass | MIT | today |
| 2 | Generates fuzz test scaffolding for parsers handling external input (YAML, JSON, config files, user input). | ash1794/ | 163 | — | ~722 | Automated safety check: Pass | MIT | today |
| 3 | Implements snapshot/golden file tests with temporal normalization so tests don't break daily. | ash1794/ | 163 | — | ~669 | Automated safety check: Pass | MIT | today |
| 4 | Analyzes large tasks for independent subtasks that can be safely parallelized. | ash1794/ | 163 | — | ~717 | Automated safety check: Pass | MIT | today |
| 5 | Strips AI-generation "smell" from prose before it ships (READMEs, docs, release notes, PR descriptions, posts, emails). | ash1794/ | 163 | — | ~2.3k | Automated safety check: Pass | MIT | today |
| 6 | Keeps specification documents and code in agreement. An agent skill from ash1794/vibe-engineering. | ash1794/ | 163 | — | ~2.2k | Automated safety check: Pass | MIT | today |
| 7 | Generates edge case, failure mode, and spec-driven test cases. | ash1794/ | 163 | — | ~1.4k | Automated safety check: Pass | MIT | today |
| 8 | Safely integrates commits from parallel agent branches using sequential cherry-pick. | ash1794/ | 163 | — | ~573 | Automated safety check: Pass | MIT | today |
| 9 | Enforces tiered test coverage standards with three dimensions — line coverage by tier, spec-to-test traceability, and spec-to-code implementation mapping. | ash1794/ | 163 | — | ~1.2k | Automated safety check: Pass | MIT | today |
| 10 | Extracts and records architectural decisions from diffs, conversation context, and explicit choices. | ash1794/ | 163 | — | ~1.4k | Automated safety check: Pass | MIT | today |
| 11 | Refuses "flaky" as a diagnosis. An agent skill from ash1794/vibe-engineering. | ash1794/ | 163 | — | ~783 | Automated safety check: Pass | MIT | today |
| 12 | Assesses production readiness or audits a codebase against its specs. | ash1794/ | 163 | — | ~1.5k | Automated safety check: Pass | MIT | today |
| 13 | Closes a large backlog of findings (a gap analysis, an audit, or 10+ bugs) in prioritized waves. | ash1794/ | 163 | — | ~1.3k | Automated safety check: Pass | MIT | today |
| 14 | Writes a handover document so another person, another agent, or a different tool can pick up multi-session work cold. | ash1794/ | 163 | — | ~893 | Automated safety check: Pass | MIT | today |
| 15 | 15.Vibe Help Routes to the right vibe-engineering skill for the current task and lists the full catalog. | ash1794/ | 163 | — | ~1.2k | Automated safety check: Pass | MIT | today |
| 16 | Keeps private and unapproved material out of a public build. | ash1794/ | 163 | — | ~1.1k | Automated safety check: Pass | MIT | today |
| 17 | Runs the Implement→Review→Test→Fix cycle until the work is actually clean, with evidence. | ash1794/ | 163 | — | ~681 | Automated safety check: Pass | MIT | today |
| 18 | Captures reusable knowledge after work is done — learnings from feedback or failures, resolved bugs (symptom, root cause, prevention), and recurring code patterns — into the project's persistent… | ash1794/ | 163 | — | ~864 | Automated safety check: Pass | MIT | today |
| 19 | Validates PRD, user stories, or feature requirements against SMART criteria. | ash1794/ | 163 | — | ~558 | Automated safety check: Pass | MIT | today |
| 20 | Researches real projects, papers, and documented failures before proposing a new feature, architecture, or technology choice. | ash1794/ | 163 | — | ~905 | Automated safety check: Pass | MIT | today |
| 21 | Documents rollback procedures before making risky changes. An agent skill from ash1794/vibe-engineering. | ash1794/ | 163 | — | ~525 | Automated safety check: Pass | MIT | today |
| 22 | Performs deployment with pre-flight checks, atomic replacement, post-deploy verification, provenance (proving the environment serves the exact commit you pushed), and automatic rollback. | ash1794/ | 163 | — | ~730 | Automated safety check: Pass | MIT | today |
| 23 | Queries all configured services for health status — uptime, restarts, errors, resources. | ash1794/ | 163 | — | ~486 | Automated safety check: Pass | MIT | today |
| 24 | Runs a multi-phase project from an orchestrating main thread that plans, routes and verifies but does not build. | ash1794/ | 163 | — | ~1.1k | Automated safety check: Pass | MIT | today |
| 25 | Generates a behavioral scenario acceptance matrix for comprehensive test coverage planning. | ash1794/ | 163 | — | ~695 | Automated safety check: Pass | MIT | today |
| 26 | Validates completed work against defined acceptance criteria. | ash1794/ | 163 | — | ~462 | Automated safety check: Pass | MIT | today |
| 27 | Catches shortcuts and reward hacking — weakening or deleting tests to make them pass, hard-coding expected outputs, silently dropping requirements, or claiming work is done without running it. | ash1794/ | 163 | — | ~999 | Automated safety check: Pass | MIT | today |
| 28 | Challenges a recommendation, design, large change, or any artifact submitted for hard review (spec, proposal, policy, plan) across 5 dimensions (consistency, completeness, actionability, alignment… | ash1794/ | 163 | — | ~2.3k | Automated safety check: Pass | MIT | today |
| 29 | Performs a fast 6-point quality check for technical documents (specs, design docs, READMEs). | ash1794/ | 163 | — | ~653 | Automated safety check: Pass | MIT | today |
| 30 | Performs end-of-iteration review with quality grading, metrics, and trend analysis. | ash1794/ | 163 | — | ~497 | Automated safety check: Pass | MIT | today |
| 31 | Scans staged changes for secrets, debug statements, TODOs without references, and other common commit mistakes. | ash1794/ | 163 | — | ~753 | Automated safety check: Notes | MIT | today |
| 32 | Checks production-bound code for observability, error handling at system boundaries, input validation, graceful degradation, and resource management, scaled to the project's real stakes. | ash1794/ | 163 | — | ~1.1k | Automated safety check: Pass | MIT | today |
| 33 | Detects and redirects scope creep during implementation — unrequested features, drive-by refactors, premature abstraction, and over-engineering. | ash1794/ | 163 | — | ~702 | Automated safety check: Pass | MIT | today |
Questions, answered from the data.
What is the best skill in ash1794/vibe-engineering?
Vibe Concurrent Test Safety from ash1794/vibe-engineering ranks first of the 33 skills in ash1794/vibe-engineering listed here, with the highest score: its repository has 163 GitHub stars, its SKILL.md loads about 665 tokens and it passes the automated safety check with no findings. Next come Vibe Fuzz Parser Inputs and Vibe Golden File Testing.
Are the skills in ash1794/vibe-engineering official?
None yet. All 33 skills in ash1794/vibe-engineering listed here come from community repositories; a skill counts as official when the product's own GitHub organization publishes it.
How do I install all skills from ash1794/vibe-engineering?
Run npx skills add ash1794/vibe-engineering in your project: the open-source skills CLI installs the repository's skills into your coding agent's skills folder. To install a single skill, open its page here for the exact command.
How are these skills ranked?
By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.