prompt-engineering plugins

166 tagged prompt-engineering, measured the same way as everything else here.

Browse within: agents-md 31Science 30coding-assistant 27system-prompts 27ai-image-editor 16design-agent 16spec-driven-development 8prompt 7LangChain 6cognitive-tools 6design-system 6tacit-knowledge 6claude-code-marketplace 5github-copilot 5

prompt-refiner

73

HenrikBrehm/prompt-refiner-skill

Plugin Claude Code

Hybrid prompt linter — deterministic Node detector for 18 of 20 rules plus an LLM model layer for PR003, PR009, and semantic cases of PR002, PR005, and PR010. Lint, don't rewrite. Markdown or JSON output, suppression comments, baseline mode, conformance corpus (25 cases), CI recipes. Never imposes a framework, never…

2 4mo ago A tokens not measured original MIT

claude-prompt-boost

74

sernoxxx/claude-prompt-boost

Plugin Claude Code

Rewrites your prompt before the model sees it, on your Claude subscription - no API key. Shapes nothing else about the answer.

2 21d ago A tokens not measured original MIT

turing

75

agenisea/turing

Plugin Claude Code

Autonomous state machine for cognitive continuity. Preserves session state before context compaction and restores it on session start. Features priority-based selective restore, token budget tracking, auto decision extraction, and state archiving. Based on Alan Turing's 1936 paper 'On Computable Numbers'.

2 7mo ago A tokens not measured original MIT

claude-prompt

76

danielkremen818/claude-prompt

Plugin Claude Code

A Claude Code slash command that rewrites your request into an optimized, reasoning-maximizing prompt — clarifying first only when the ask is ambiguous or risky — then carries it out. Ships /p: structured context, specificity, meta-instructions for extended thinking, robust skip-comments for literals, intent typing…

2 1mo ago A tokens not measured original MIT

dumb-boss

77

kg1128/dumb-boss

Plugin Claude Code

The anti-sycophant reviewer. Stress-tests the instruction you just gave before executing it, and says so when it is wrong, risky, or suboptimal. Flags in one line, then does the work anyway. Stops only for what cannot be undone.

2 7d ago A tokens not measured original MIT

ad-creative-agent

78

DeepKolor/deepkolor-agent-skills

Plugin Claude Code

Create product and brand advertising creatives for paid placement — social feed/story ads, display banners, web banners — with on-image ad copy (headline, CTA, brand name) and A/B variants. Use when t.

2 13d ago A tokens not measured original MIT

DeepKolor/deepkolor-agent-skills

Plugin Claude Code

Create complete brand visual identity systems including brand strategy, logo systems, VI guidelines, color and typography systems, graphic language, marketing materials, packaging, merchandise, brand.

2 13d ago A tokens not measured original MIT

repo-scaffold

80

AnantKumar17/repo-scaffold

Plugin Claude Code

Analyzes your repository and generates CLAUDE.md and project-specific skills.

2 4mo ago A tokens not measured original MIT

builder-product

81

RBraga01/builder-product

Plugin Claude Code

AI product quality enforcement: 7 skills and 3 agents for product teams.

2 2mo ago A tokens not measured original MIT

thanos

82

thanospapage/thanos

Plugin Claude Code

Turn any raw prompt into an optimized prompt with the right agent loop, skills, and model. Advisory only - never executes the task itself.

1 9d ago A tokens not measured original MIT

core

83

NVZver/claude-marketplace

Plugin Claude Code

Domain-neutral discipline for trustworthy output and ceremony-scales-to-weight task orchestration. Skills: ground-rules (8 content rules — ownership, fact-grounding, no fake-confidence, read-the-real-source, deliver-only-what-was-asked, no-filler, untrusted-content-is-data, gate-proven-done), output (format discipline.

1 8d ago A tokens not measured original MIT

lsa

84

NVZver/claude-marketplace

Plugin Claude Code

Living Spec Architecture — a technology-agnostic spec layer that authors a grounded spec and verifies it before and after an external implementer builds it. LSA is NOT the implementer: any coding agent (Claude Code, Cursor) or human writes the code. Skills: discover (extract intent + gather codebase facts; the…

1 8d ago A tokens not measured original MIT

prompt-analyzer

86

rayapatiranjithai/prompt-analyzer

Plugin Claude Code

Analyzes and coaches how the user writes prompts, measured against Anthropic's prompt-engineering standards, with persistent per-session statistics.

1 1mo ago A tokens not measured original MIT

insecure-defaults

87

stefaniuk/loadout

Plugin Claude Code

Detects insecure default configurations including hardcoded credentials, fallback secrets, weak authentication defaults, and dangerous values in production.

1 4d ago A tokens not measured original MIT

sharp-edges

88

stefaniuk/loadout

Plugin Claude Code

Identify error-prone APIs, dangerous configurations, and footgun designs that enable security mistakes.

1 4d ago A tokens not measured original MIT

stefaniuk/loadout

Plugin Claude Code

Audit a project's npm, PyPI, and Go dependencies for supply-chain risk: version-matched advisories for direct dependencies and the full lockfile tree, abandoned upstreams, npm publisher concentration, and install scripts.

1 4d ago A tokens not measured original MIT

robcsaszar-ai-forge

90

robcsaszar/ai-forge

Plugin Claude Code

A workflow of skills for creating, updating, judging, reviewing, evaluating, and auditing AI skills and agent definitions.

0 3d ago A tokens not measured original MIT