qte77

Verify an external or AI-generated security report against the actual codebase before acting on it. Use when handed a scanner PDF, automated teardown, audit report, or bug-bounty submission — classifies every finding CONFIRMED / OVERSTATED / FALSE-POSITIVE / FABRICATED and salvages the real work items.

Creates GitHub Actions for the Marketplace. Use when scaffolding a new action, implementing composite steps, writing BATS tests, or preparing a Marketplace release.

Audit documentation against its declared hierarchy — broken links, duplicates, misplaced content, stale references, single-source-of-truth enforcement. Use for doc health reviews.

Audit README.md files against best practices for repos, accounts, or orgs. Detects missing sections, stale links, inconsistent formatting, and convention violations. Use when reviewing README quality across one or many repos.

Generate or update README.md files across three scopes — repo (with project-type detection), account (GitHub user profile), and org (organization profile). Use when creating, updating, or aligning a README to org conventions.

Audits website accessibility for WCAG 2.2 AA compliance, generating findings and code fixes. Use when reviewing accessibility, keyboard navigation, screen reader compatibility, or inclusive design.

Audits a site's SEO and AI-search (GEO) readiness — meta tags, Open Graph/Twitter, JSON-LD, robots/llms conventions — and generates fixes. Use when reviewing search visibility, social previews, structured data, or LLM/AI-crawler discoverability.

Audit code against OWASP Top 10 vulnerabilities with structured findings. Use when reviewing code for security issues or conducting security audits.

Compacts verbose context into structured summary. Use after pollution sources (searches, logs, JSON) or at phase milestones.

Create a pull request from the current branch. Analyzes commits, generates title+body from PR template, pauses for approval, then pushes and creates PR. Use after committing changes.

Designs concise, streamlined backend systems matching exact task requirements. Use when planning APIs, data models, system architecture, or when the user requests backend design work.

Audits and aligns project documentation against authority chains (project docs and Claude Code infrastructure). Detects broken references, duplicates, scope creep, and chain breaks. Use when reviewing documentation health, fixing stale references, or enforcing single-source-of-truth.

Interactive Q&A to build UserStory.md from user input. Use when the user wants to create a user story document or start the assisted workflow.

Generates prd.json task tracking file from PRD.md requirements document. Use when initializing Ralph loop or when the user asks to convert PRD to JSON format for autonomous execution.

Generates academic/technical writeups with IEEE citations and pandoc PDF output. Use when creating research papers, technical reports, or documentation with references.

Maintains AGENTS.md, AGENT_LEARNINGS.md, AGENT_REQUESTS.md, and CONTRIBUTING.md governance files in sync with codebase changes. Use when updating governance files, during sprint reviews, or after structural changes.

Generate commit message for staged changes, pause for approval, then commit. Stage files first with `git add`, then run this skill.

Interactive Q&A to build UserStory.md from user input. Use when the user wants to create a user story document or start the assisted workflow.

Generates prd.json task tracking file from PRD.md requirements document. Use when initializing Ralph loop or when the user asks to convert PRD to JSON format for autonomous execution.

Transforms UserStory.md into PRD.md by extracting features and converting user stories into functional requirements.

Investigates codebase before planning. Use before any non-trivial implementation task to gather context in isolation.

Provides concise, focused code reviews matching exact task complexity requirements. Use when reviewing code quality, security, or when the user asks for code review.

Writes tests following TDD (using pytest and Hypothesis) and BDD best practices. Use when writing unit tests, integration tests, or BDD scenarios.

Compacts verbose context into structured summary. Use after pollution sources (searches, logs, JSON) or at phase milestones.

Audit and tighten codebase quality gates — lint, types, tests, code review. Use when onboarding a project, before a release, or when validation is too permissive.

Compacts verbose context into structured summary. Use after pollution sources (searches, logs, JSON) or at phase milestones.

Audits and aligns project documentation against its own declared hierarchy. Discovers authority chains from CONTRIBUTING.md (or equivalent), then detects broken links, duplicates, and misplaced content. Use when reviewing doc health, fixing stale references, or enforcing single-source-of-truth.

Implements concise, streamlined Python code matching exact architect specifications. Use when writing Python code, creating modules, or when the user asks to implement features in Python.

Investigates codebase before planning. Use before any non-trivial implementation task to gather context in isolation.

Provides concise, focused code reviews matching exact task complexity requirements. Use when reviewing code quality, security, or when the user asks for code review.

Writes tests following TDD (using pytest and Hypothesis) and BDD best practices. Use when writing unit tests, integration tests, or BDD scenarios.

Compacts verbose context into structured summary. Use after pollution sources (searches, logs, JSON) or at phase milestones.

Designs concise, streamlined backend systems matching exact task requirements. Use when planning APIs, data models, system architecture, or when the user requests backend design work.

Interactive Q&A to build UserStory.md from user input. Use when the user wants to create a user story document or start the assisted workflow.

Generates prd.json task tracking file from PRD.md requirements document. Use when initializing Ralph loop or when the user asks to convert PRD to JSON format for autonomous execution.

Implements concise, streamlined Python code matching exact architect specifications. Use when writing Python code, creating modules, or when the user asks to implement features in Python.

Generate commit message for staged changes, pause for approval, then commit. Stage files first with `git add`, then run this skill.

Context compression for verbose outputs. Use when conversation context exceeds 70% capacity or when summarizing large outputs.

Academic/technical writeups with Pandoc-compatible markdown. Use for documentation, reports, or technical explanations.

Evidence-based codebase investigation. Use when exploring unfamiliar code, understanding architecture, or gathering context for implementation.

Capture the screen and inject a short text summary into Claude's context via an in-process VLM (llama-cpp-python). No daemon. Use to feed terminal/editor/browser state to Claude for debug, fix suggestions, or summarization with minimal token cost.

Transcribe speech using local STT. Use when the user wants voice input or offline audio transcription.

Speak text aloud using local TTS. Use when the user wants Claude's output read aloud or to toggle auto-read mode.

Read document content → classify by type → apply YYYY-MM-DD taxonomy naming → move to organized subdirs → generate manifest. Use when organizing chaotic document folders.

Read email threads → categorize by urgency → draft responses for review → flag priorities → identify newsletters for unsubscribe. Use when processing an email backlog.

OCR and extract invoice/receipt data → validate → output organized spreadsheet. Use when processing invoices, receipts, or expense documents.

Research a new source (tool / paper / protocol / agent) first-party and add it to the ai-agents-research corpus as an analysis doc — placement, conventions, lint, one-PR-per-topic. Use when the user drops a URL/tool/paper to "add as a source" or asks to extend coverage. For >~4 sources at once, use the batch workflow.