GitHub
error-handling
Error-handling conventions (error mapping/presentation, what to throw vs return, user-facing output). Use when adding errors or changing failure behavior.
Anveio AI Skills
GitHub ↗Explorez les skills IA publiés de Anveio et consultez leurs instructions source.
Statistiques de l’auteur
Skills indexés
24Étoiles des dépôts des skills indexés
24Forks du dépôt
0Moyenne des étoiles par skill indexé
1Les étoiles d’un dépôt peuvent se répéter entre ses skills.
Catégories populaires
Indexation récente
Explorer
GitHub
task-coding-loop
Earn trust through verification. Invoke at session start to establish verifiable checkpoints (environment, baseline, completion). Trust comes from gates, not claims.
GitHub
app-architecture
Create apps following contract-port architecture with composition roots. Use when creating new apps in apps/, scaffolding CLI tools, setting up dependency injection, or when the user asks about app structure, e...
GitHub
kpi-code-quality
KPI for measuring and improving code quality. Covers lint errors, type safety, test coverage, and verification pass rates. Use to ensure code meets quality standards.
GitHub
task-lint-fixer
Fix lint errors and update typescript-coding skill with lessons learned. Use when fixing Biome lint errors, resolving linting issues, or when lint check fails. Automatically extracts patterns from fixes and add...
GitHub
task-verification-pipeline
Run and debug a repo verification pipeline (`./verify.sh --ui=false` or equivalent), including stage selection and opt-in E2E tiers.
GitHub
task-effective-git
Git workflow patterns for agents. Invoke at session start when working in a git repository, before any git operations (status, add, commit, push, rebase), when making code changes, or when the user asks to comm...
GitHub
task-rsid
Recursive Self-Improvement Development. Continually improve the codebase.
GitHub
writing-claude-skills
Create properly formatted Claude Code skills with YAML frontmatter, directory structure, and best practices. Use when creating new skills, converting documentation to skills, or learning how to write skills.
GitHub
kpi-verification-pass-rate
KPI for measuring first-pass verification success. Tracks how often verification passes on the first attempt. Use to reduce wasted cycles from verification failures.
GitHub
role-software-engineer
Role definition for software engineer agents. Defines responsibilities, principles, required skills, and success criteria. Use to understand what it means to operate as a software engineer in this codebase.
GitHub
env-patterns
Environment/config conventions (env vars, defaults, validation, CI/local differences). Use when adding config or diagnosing env-related failures.
GitHub
coding-patterns
TypeScript monorepo patterns including contract-port architecture, dependency injection, hermetic primitive ports, and composition root. Use when creating packages, designing contracts/interfaces, implementing...
GitHub
task-plan-writing
Write rigorous implementation plans as if presenting to distinguished engineers. Use when entering plan mode, designing architecture, or when the user asks to plan a feature. Raises plan quality through expert...
GitHub
devcontainer-sandboxing
Create or harden a devcontainer-based development sandbox so coding agents run inside an isolated container with least privilege and strong guardrails (no destructive host access, controlled network/secrets, re...
GitHub
typescript-coding
TypeScript coding patterns and type system best practices. Use when writing TypeScript code, designing types, working with generics, discriminated unions, conditional types, or when the user mentions TypeScript...
GitHub
claude-typescript-sdk
Build AI applications with the Anthropic TypeScript SDK. Use when creating Claude integrations, building agents, implementing tool use, streaming responses, or working with the @anthropic-ai/sdk package.
GitHub
kpi-pr-throughput
KPI for measuring and improving PR throughput. Defines metrics, measurement methods, and improvement strategies. Use to optimize how many quality PRs get merged.
GitHub
claude-agent-sdk
Build coding agents with the Claude Agent SDK. Use when creating agentic workflows, implementing todo tracking, monitoring agent progress, building multi-turn conversations, streaming responses, or integrating...
GitHub
role-code-reviewer
Role definition for code reviewer agents. Defines review criteria, feedback patterns, and approval workflows. Use to understand how to review PRs and provide constructive feedback.
GitHub
task-handoff-writing
Write high-signal handoffs (`HANDOFF.md` or `docs/handoffs/.md`) with concrete validation evidence and actionable next steps.
GitHub
task-memory-consolidation
Parse memory.yaml and consolidate recurring patterns into skills. Use when memory.yaml grows large, when patterns recur 3+ times, or during RSID Ideate stage. Automates the memory-to-skill pipeline.
GitHub
task-pull-request
Author pull requests and respond to review feedback. Use when creating PRs, requesting reviews, reading comments, addressing feedback, or merging changes.
GitHub
aat
Agent Acceptance Testing - hypothesis-driven PR verification protocol
Le classement utilise les étoiles du dépôt GitHub indexé. Plusieurs skills peuvent partager ce nombre : ce n’est ni un nombre d’installations ni une note de qualité.