Best agent skills for developers, page 789

A skill your agent uses when choosing an open-weight LLM and clearing it for use — which family and size fit the task, the hardware and the budget, and above all whether the license permits shipping.

ericrisco/rsc-harness

A skill your agent uses when an approved, clarified spec must become a technical blueprint before any code — the SDD phase between clarify and tasks: architecture, contracts, data flow, testing…

ericrisco/rsc-harness

A skill your agent uses when operating Microsoft Power Automate cloud flows from code — create, enable, update, list or delete via the Dataverse Web API (workflow table, category 5) with Entra ID…

ericrisco/rsc-harness

A skill your agent uses when you want a disciplined, spec-driven path from a feature idea to shipped, verified software — the SDD dispatcher and front door, in any language.

ericrisco/rsc-harness

A skill your agent uses when writing, reviewing or structuring Unity game code in C for Unity 6 LTS — GameObjects and the Transform hierarchy, the MonoBehaviour lifecycle, prefabs and variants…

ericrisco/rsc-harness

A skill your agent uses when building, scripting or debugging a game in Unreal Engine 5 with Blueprint or C++ — the gameplay framework (Actor, Pawn, Character, GameMode, PlayerController), Actor…

ericrisco/rsc-harness

A skill your agent uses when fine-tuning an open-weight LLM fast on ONE GPU with low VRAM — Unsloth's fast model loaders with 4-bit QLoRA and the trl trainer, response-only loss masking so the…

ericrisco/rsc-harness

A skill your agent uses when operating Zapier from an agent through the official hosted Zapier MCP server — connecting with a bearer key, discovering an app's actions, enabling one, and invoking a…

ericrisco/rsc-harness

React specialist perspective for the weekly review. An agent skill from mizchi/skills.

mizchi/skills

Run the full test suite with coverage reporting. An agent skill from enuno/unifi-mcp-server.

enuno/unifi-mcp-server

Evaluates API surface design, consistency, and exemplar alignment.

athola/claude-night-market

Selects architecture paradigm via research before scaffolding.

athola/claude-night-market

Generates a Mermaid architecture diagram showing high-level component relationships.

athola/claude-night-market

Applies layered n-tier architecture with enforced boundaries.

athola/claude-night-market

Applies microservices for independent deployment and per-service scaling.

athola/claude-night-market

Selects and routes to the right architecture paradigm. An agent skill from athola/claude-night-market.

athola/claude-night-market

Assesses architecture decisions, ADR compliance, and coupling.

athola/claude-night-market

Provides auth patterns for API keys, OAuth, and token management.

athola/claude-night-market

Detects codebase bloat via dead code, duplication, complexity, and doc bloat scans.

athola/claude-night-market

Records browser sessions via Playwright and converts video to GIF.

athola/claude-night-market

Hunts bugs with evidence trails. An agent skill from athola/claude-night-market.

athola/claude-night-market

Generates a Mermaid class diagram showing types, inheritance, and composition.

athola/claude-night-market

Applies KISS, YAGNI, and SOLID principles for clean code with reduced complexity.

athola/claude-night-market

Improves code quality across duplication, efficiency, and architectural fit.

athola/claude-night-market

Delegates tasks to the OpenAI Codex CLI (codex exec) via delegation-core.

athola/claude-night-market

Generates conventional commit messages from staged changes. An agent skill from athola/claude-night-market.

athola/claude-night-market

Provides sanitization guidelines for external content in skills and hooks.

athola/claude-night-market

Optimizes context window via MECW principles and memory tiering.

athola/claude-night-market

Guides when to ask clarifying questions versus proceed autonomously.

athola/claude-night-market

Implements GitHub or GitLab issues via parallel subagents with review gates between task batches.

athola/claude-night-market

Merges ephemeral report and analysis artifacts into permanent documentation.

athola/claude-night-market

Generates or remediates documentation with human-quality writing.

athola/claude-night-market

Updates documentation after code changes with quality gates, slop detection, and accuracy checks.

athola/claude-night-market

Converts documents and URLs to markdown via tiered fallback (MCP markitdown, native tools, user notice).

athola/claude-night-market

Computes DORA delivery-performance metrics from git and GitHub API.

athola/claude-night-market

Provides error classification, recovery, and graceful-degradation patterns.

athola/claude-night-market

Provides weighted scoring, rubrics, and decision-threshold patterns.

athola/claude-night-market

Delegates tasks to Gemini CLI implementing delegation-core for Google's models.

athola/claude-night-market

Detects git forge (GitHub/GitLab/Bitbucket) and maps CLI commands cross-platform.

athola/claude-night-market

Delegates tasks to a locally served Muse Glimmer via ollama.

athola/claude-night-market

Applies NIST/CWE security hardening to Python and Rust code.

athola/claude-night-market

Select hook scope (plugin, project, global) by audience. An agent skill from athola/claude-night-market.

athola/claude-night-market

Installs egregore watchdog daemon via launchd or systemd for autonomous relaunching.

athola/claude-night-market

Audits changes for additive bias and Iron Law compliance. An agent skill from athola/claude-night-market.

athola/claude-night-market

Searches and navigates stored knowledge in memory palaces. An agent skill from athola/claude-night-market.

athola/claude-night-market

Generates Makefiles with testing, linting, formatting, and automation targets.

athola/claude-night-market

Audits Makefiles for build correctness, portability, and recipe duplication.

athola/claude-night-market

Verifies math-heavy code for algorithmic correctness and numerical stability.

athola/claude-night-market