blunotech-dev

60 mods across 1 repository, 2 stars between them.

context-injection

01

blunotech-dev/agents

Skill Claude CodeCodex

Injects retrieved context into prompts correctly — covers context formatting, source attribution, context window budget management, and relevance filtering. Use when building RAG pipelines, document Q&A, search-augmented generation, or any artifact where retrieved chunks must be fed into a Claude prompt reliably.

2 3mo ago A 60 tokens

document-chunking

02

blunotech-dev/agents

Skill Claude CodeCodex

Implements chunking strategies for documents before embedding or retrieval — covers fixed-size, semantic, recursive, and sliding window approaches with overlap and metadata preservation. Use when building RAG pipelines, document ingestion, vector store population, or any artifact where documents must be split before…

2 3mo ago A 60 tokens

prompt-compression

03

blunotech-dev/agents

Skill Claude CodeCodex

Compress prompts to reduce token count without degrading output quality. Use this skill when the user wants to shorten a system prompt, user prompt, or instruction block; when they say a prompt is "too long", "hitting token limits", or "too expensive to run"; when they want to audit a prompt for bloat; or when they…

2 3mo ago A 115 tokens

rag-evaluation

04

blunotech-dev/agents

Skill Claude CodeCodex

Evaluates RAG pipeline quality end-to-end. Use when measuring retrieval precision/recall, answer faithfulness, hallucination rate, or comparing RAG configurations. Trigger for any task involving RAG quality assessment, LLM-as-judge evaluation, RAGAS metrics, groundedness checks, or A/B comparison of retrieval or…

2 3mo ago A 73 tokens

response-parser

05

blunotech-dev/agents

Skill Claude CodeCodex

Parses structured output from LLM responses. Use when extracting JSON from markdown-fenced LLM output, handling partial or streamed JSON, recovering from malformed model responses, or building robust pipelines that consume Claude/OpenAI structured outputs. Trigger for any task involving LLM output parsing, JSON…

2 3mo ago A 73 tokens

retrieval-strategy

06

blunotech-dev/agents

Skill Claude CodeCodex

Implements optimized retrieval strategies for RAG and search pipelines. Use when building or improving document retrieval, choosing between similarity search, hybrid search, reranking, or MMR, diagnosing retrieval quality issues, or tuning recall/precision tradeoffs in LLM-powered search. Trigger for any task…

2 3mo ago A 84 tokens

tool-execution-loop

07

blunotech-dev/agents

Skill Claude CodeCodex

Implements the agentic tool execution loop for Anthropic API artifacts — covers tool call detection, dispatch to handler, result injection, and multi-turn continuation until the model signals completion. Use this skill when building any AI-powered artifact that needs Claude to call tools (web search, MCP, custom…

2 3mo ago A 75 tokens

blunotech-dev/agents

Skill Claude CodeCodex

Keep API docs in sync with implementation by generating or validating OpenAPI/Swagger specs, detecting undocumented routes, and fixing spec drift. Use when the user asks to generate docs, validate a spec, find undocumented endpoints, or update stale API documentation.

2 3mo ago A 54 tokens

api-versioning

09

blunotech-dev/agents

Skill Claude CodeCodex

Implement API versioning with URL or header strategies, deprecation handling, and backward compatibility. Use when the user asks about versioning, managing breaking changes, evolving APIs, supporting multiple versions, or handling v1/v2 migrations.

2 3mo ago A 50 tokens

cache-invalidation

10

blunotech-dev/agents

Skill Claude CodeCodex

Implement cache invalidation strategies for data consistency. Use when handling stale data, invalidating on updates, designing cache flows, or working with SWR, cache tags, or event-driven invalidation across Redis, CDNs, or client caches.

2 3mo ago A 52 tokens

blunotech-dev/agents

Skill Claude CodeCodex

Implement correct transaction handling with proper isolation levels, retries, and rollback on failure. Use when dealing with concurrency issues, deadlocks, inconsistent data, or transaction design (e.g., SELECT FOR UPDATE, locking strategies).

2 3mo ago A 49 tokens

jwt-backend

12

blunotech-dev/agents

Skill Claude CodeCodex

Implement JWT auth on the backend, including token generation, validation, refresh rotation, revocation, and secure storage. Use when building token-based auth, securing endpoints, or handling expiry and access/refresh flows.

2 3mo ago A 46 tokens

migration-strategy

13

blunotech-dev/agents

Skill Claude CodeCodex

Implement safe database migrations with zero-downtime patterns, rollbacks, and strategies for large schema changes without data loss. Use when the user asks about migrations, schema updates, backfills, column/table changes, or tools like Flyway, Liquibase, Alembic, or ActiveRecord.

2 3mo ago A 63 tokens

n-plus-one-fix

14

blunotech-dev/agents

Skill Claude CodeCodex

Detect and fix N+1 query patterns using eager loading, batching, or dataloader approaches. Use when queries run in loops, ORM lazy loading causes repeated DB calls, or the user reports slow endpoints or N+1 issues. Also trigger when the user shares code with loops that call .find(), .load(), .fetch(), or any ORM…

2 3mo ago A 95 tokens

blunotech-dev/agents

Skill Claude CodeCodex

Implement efficient pagination using offset, cursor, or keyset strategies. Use when fixing slow or deep pagination, high offsets, infinite scroll, or designing list endpoints.

2 3mo ago A 36 tokens

query-optimization

16

blunotech-dev/agents

Skill Claude CodeCodex

Optimize slow SQL queries using plan analysis, indexing, join tuning, subquery/CTE simplification, and pagination improvements. Use when the user shares slow queries, EXPLAIN output, or reports high execution time, sequential scans, or inefficient joins.

2 3mo ago A 55 tokens

webhook-system

17

blunotech-dev/agents

Skill Claude CodeCodex

Build a production-grade outbound webhook system with retries, signing, failure tracking, and re-delivery. Use when implementing webhook delivery, event subscriptions, or handling webhook failures and reliability.

2 3mo ago A 40 tokens

blunotech-dev/agents

Skill Claude CodeCodex

Evaluate how logic handles edge cases and extreme inputs. Use when checking robustness, debugging failures, or testing boundaries like empty input, zero values, or limits.

2 3mo ago A 36 tokens

blunotech-dev/agents

Skill Claude CodeCodex

State the likely root cause before writing code. Use when debugging bugs, errors, or failing tests to enforce hypothesis-driven fixes.

2 3mo ago A 32 tokens

blunotech-dev/agents

Skill Claude CodeCodex

Validate that function inputs match the expected shape. Use when debugging unexpected behavior, null errors, type issues, or incorrect arguments.

2 3mo ago A 30 tokens

anti-purple-ui

23

blunotech-dev/agents

Skill Claude CodeCodex

Enforce a strict monochrome UI with a single high-contrast accent color, removing generic tech gradients and “AI-style” palettes. Use when the user wants minimal, anti-AI, or non-generic aesthetics, or says the UI looks too techy or generic.

2 3mo ago A 59 tokens

banner-design

24

blunotech-dev/agents

Skill Claude CodeCodex

Design banners for social media, ads, website heroes, creative assets, and print. Multiple art direction options with AI-generated visuals. Actions: design, create, generate banner. Platforms: Facebook, Twitter/X, LinkedIn, YouTube, Instagram, Google Display, website hero, print. Styles: minimalist, gradient, bold…

2 3mo ago A 118 tokens