vladkesler/initrunner

prompt-craft

Translate natural language image descriptions into detailed, structured DALL-E prompts with subject, style, composition, lighting, and mood specifications.

step-by-step

Decompose mathematical problems into sub-expressions, evaluate each one with the calculator tool, and present the full working chain. Handles arithmetic, trigonometry, logarithms, and financial formulas.

document-comparison

Compare two or more PDF documents by extracting targeted sections, building a structured comparison matrix, and highlighting differences with page references.

structured-extraction

Extract structured data from web pages using browser snapshot and text tools, then process it into tables, comparisons, or summaries using Python.

latency-analysis

Analyze endpoint latency trends using historical check data from memory. Detects slow degradation, spikes vs sustained issues, and calculates baseline deviations.

response-validation

Validate API response structure and content. Detects schema drift, unexpected null values, and abnormal response sizes.

ssl-certificate

Check SSL/TLS certificate expiry and chain validity using openssl. Alerts on certificates expiring within 30 days.

email-triage

Classify incoming emails into triage categories using content analysis, sender profile memory, and thread detection. Produces a category (URGENT, REPLY_NEEDED, FYI, NEWSLETTER, NOTIFICATION, SPAM) with confidence and reasoning.

reply-composer

Draft context-aware email replies that match sender tone, reference thread history, and follow the user's style preferences. Presents drafts for review before sending.

api-contract-testing

Curl-based HTTP endpoint probing and response validation. Tests status codes, response bodies, headers, and schema conformance against expected contracts.

database-verification

Shell-based database connectivity and integrity checks. Verifies that databases are reachable, schemas match expectations, and data integrity constraints hold.

environment-diagnostics

Environment variable validation and configuration verification. Checks that required variables are set, config files parse correctly, ports are available, and system dependencies meet version requirements.

service-health-check

Health endpoint verification and dependency status checks. Probes standard health paths, validates dependency connectivity, and reports overall service readiness.

container-scan

Dockerfile security review. Checks for running as root, leaked secrets in build layers, insecure base images, and missing best practices.

javascript-sast

JavaScript and Node.js security scanning. Checks dependency vulnerabilities via npm audit and source patterns for XSS, eval, and prototype pollution.

python-sast

Python static analysis using bandit. Identifies injection, deserialization, unsafe exec/eval, weak crypto, and hardcoded credentials in Python code.

secret-detection

Detect hardcoded secrets, API keys, tokens, and credentials in source code using pattern matching. Covers AWS, GitHub, Slack, Stripe, and generic high-entropy strings.

coverage-analysis

Running coverage tools, interpreting coverage reports, identifying high-risk gaps, and prioritizing which uncovered code to test first.

edge-case-generation

Systematic edge-case identification including boundary values, null inputs, type mismatches, and error path testing.

jest-patterns

Jest and Vitest testing patterns including describe/it blocks, expect matchers, mocking, and async test strategies for JavaScript and TypeScript.

mocking-strategies

Mock, patch, fake, and stub patterns for isolating dependencies in Python and JavaScript test suites.

pytest-patterns

Pytest best practices including fixtures, parametrize, markers, and assertion patterns for Python test suites.

kubernetes

Diagnose and fix Kubernetes pods, services, networking, storage, and rollout failures with kubectl. Safety-first, read-only by default.

summarizer

Summarize long text, articles, or documents into concise bullet points.

web-researcher

Web research tools for fetching and reading web pages. Use when the agent needs to browse the web or make HTTP API calls.