skillkit-essentials

Makes agent explain concepts with extreme clarity for beginners learning new topics or projects. Uses analogies-first approach, visual mental models, and ELI5 style to transform complex technical explanations into accessible learning experiences. Trigger when user is new to a technology, starting a project, or explicitly requests simple explanations.

Guides an agent to document developer progress objectively after completing a sprint, project phase, or milestone. Reads a global markdown file, detects git work sessions via 3-day gap analysis, writes factual entries (no sycophancy, no praise), and performs cross-entry progression analysis for portfolio and gig use. USE WHEN: User says "document my progress", "log what I did", "I just finished [sprint/project/phase]", "update btdt", or provides a repo path after completing work. WORKFLOW: Pre-flight → Session Detection → Collection → Analysis → Write → Confirm OUTPUT: Extends the user's global progress log (been-there-done-that.md) with a dated, factual entry placed at the correct position in a Year/Month/Date/Project tree. Default output language: English (ask user on first run if file is new). CRITICAL: Agent MUST stop and wait at every STOP gate. Do not proceed without explicit user confirmation. No assumptions. No skipping.

Transform AI-to-AI documentation into human-readable prose with personality. USE WHEN: Converting rigid AI-generated docs (checklists, templates, CAPS LOCK emphasis, perfect structures) into flowing, conversational documentation that feels like a colleague wrote it, not a robot. PRIMARY TRIGGERS: "humanize this doc" → Full transformation workflow "make this readable" → Quick readability pass "remove AI patterns" → Surgical pattern removal "add human touch" → Inject personality without losing precision INPUT: Markdown files with AI-agent patterns (checklist spam, rigid headers, template overload) OUTPUT: Flowing prose with burstiness, analogies, and occasional absurd touches CORE PRINCIPLE: Total war on AI rigidity. Destroy robotic tone while preserving technical accuracy.

Intelligent pre-deployment QA checklist generator. Explores the codebase, confirms project understanding with user, spawns parallel domain subagents to deeply analyze each layer (frontend, backend, database, security, etc.), then produces a complete human-executable checklist in docs/. USE WHEN: User says "pre-deploy check", "deploy checklist", "ready to deploy?", "generate QA checklist", or any request to verify project readiness before deployment.

Use when you need to design effective LLM prompts. Intelligently selects optimal prompting methods (Chain of Thought, Few-Shot, Zero-Shot, ReAct, Tree of Thoughts, Self-Consistency) and output formats (XML, JSON, YAML, Natural Language) based on task complexity, target LLM, accuracy requirements, and available context. Trigger on prompt design, prompt optimization, or when choosing between prompting techniques.

Create implementation-ready technical specifications through conversational discovery, code investigation, and structured documentation. USE WHEN user needs to plan a feature, create tech-spec, or prepare implementation-ready documentation. Triggers on "buat spec", "create tech spec", "plan feature", "specification", or when user describes a feature to build without clear implementation plan.

Create comprehensive, accurate README.md files with anti-hallucination validation. USE WHEN: Creating new README, updating existing README, validating README accuracy, or ensuring documentation matches actual codebase. PRIMARY TRIGGERS: "create README" → Full creation workflow (scan → generate → validate → test) "update README" → Partial update with validation "validate README" → Validation-only workflow "check README accuracy" → Anti-hallucination audit KEY FEATURES: - Codebase scanning for accurate facts - 5-layer anti-hallucination validation - Script execution testing - Citation tracking for all claims - Template-based structure selection DIFFERENTIATOR: Every claim verified against actual codebase. No assumptions, no hallucinations. Script execution testing ensures examples work.

Automate the full release workflow: version bumping (major/minor/patch), changelog generation, git tagging, pushing, and GitHub release creation. Handles semver across Node.js, Python, Rust, Go, and generic projects. Enforces mandatory confirmations before irreversible actions (push, release). USE WHEN: user says "release", "bump version", "cut a release", "tag and release", "/releasing", or asks to prepare a new version of their project.

Enforce agent to complete all 7 production safety gates with evidence before any deployment. Use when about to deploy, push to production, merge a release branch, or ship any change to a live environment. Blocks rationalized shortcuts under time, authority, sunk-cost, or exhaustion pressure.