claude-code-skill agents

netresearch/typo3-testing-skill

Agent

Generate unit and functional tests for TYPO3 extensions.

Yakoub-ai/agent-mmm

Agent

Use this agent for any Marketing Mix Model (MMM) work — scoping and planning an MMM engagement, auditing and preparing data, designing model architecture and priors, building and fitting models, diagnosing convergence or attribution problems, interpreting contributions and ROAS, optimising budget, designing…

Yakoub-ai/agent-mmm

Agent

Specialist sub-agent for MMM diagnostics. Assesses convergence, fit, generalisation, baseline health, prior-to-posterior learning and attribution plausibility for a fitted run, and reports whether the results are safe to act on. Invoked by agent-mmm for review and debugging work.

Yakoub-ai/agent-mmm

Agent

Specialist sub-agent for the MMM iterative improvement loop. Runs the tournament of model variants, scores each run, and applies posterior-informed prior tightening to refine the best model. Invoked by agent-mmm when the task is improving or optimizing an existing MMM.

Kaos599/Deep-Ass-Research

Agent

You are a Deep Diver. You go deep on ONE committed thread and produce atomic, primary-sourced claim notes. You are the embodiment of read the primary source, not the summary thread.

Kaos599/Deep-Ass-Research

Agent

DAR — Relevance Monitor (Drift Guard, step 4.5).

Kaos599/Deep-Ass-Research

Agent

DAR — Synthesizer (Synthesize phase — the deliverable).

NYTC69/review-loop

Agent

Review frontend code for common web security vulnerabilities. Use before committing or creating PRs for frontend code.

NYTC69/review-loop

Agent

The Reviewer agent in a review-loop workflow. Use this agent when the Orchestrator needs an independent critical review of a solution plan or a set of code changes produced by the Executor. This agent reads and analyzes but never modifies files. Returns a structured verdict.

NYTC69/review-loop

Agent

Use this agent when you need expert analysis of type design in your codebase. Specifically use it when introducing a new type to ensure it follows best practices for encapsulation and invariant expression, during code review to check all types being added, or when refactoring existing types to improve their design…

nestharus/agent-implementation-skill

Agent

Decomposes work into sections around confirmed problems, producing section specs, a refined global proposal, and a global alignment document.

nestharus/agent-implementation-skill

Agent

Discovers factors introduced by proposal choices — new problems, constraints, and operational concerns that technical and design decisions create — and assesses whether each factor needs user input or can be absorbed.

nestharus/agent-implementation-skill

Agent

Deepens understanding of extracted problems by discovering sub-problems, implied problems, ambiguities, contradictions, and factors — producing enriched problem definitions that support reliable decomposition.

JSchOBL/agentic-ai-learning-journey

Agent

Audit a project's declared dependencies for unpinned versions, duplicates, and packages that are declared but never imported. Use when the user asks to check, audit, or review dependencies, or to find unused or unpinned packages.

TimboGP/timbogp-marketplace

Agent

Use this agent for a one-shot, scored Lean review of a venture's whole model. It reads the .lean/ workspace (canvas, risks, progress, and any interview/experiment/metrics artifacts) and returns a prioritized "Lean review": the current stage with evidence, the riskiest untested assumptions, the weakest canvas blocks…

TimboGP/timbogp-marketplace

Agent

Use this agent to get a focused, scored UX review of a single UI artifact — a component, a screen, a screenshot, or a live page. It evaluates across four lenses (usability heuristics, accessibility, visual hierarchy, and interaction feedback) and returns prioritized findings with concrete fixes. Trigger it when the…

Njengah/claude-code-tracker

Agent Claude Code

Read-only reviewer for JWT login, password hashing, and /auth routes in this tracker. Use when the user asks to review auth.py, registration, login tokens, or getcurrentuser. Use after changes to auth helpers or auth routes. Do not use for session/cost exploration or for implementing features.

Njengah/claude-code-tracker

Agent Claude Code

Read-only scout for session, token, and cost code in this FastAPI tracker. Use when the user asks where usage is recorded, how costusd is calculated, or which routes touch sessions and analytics. Use proactively for "where does X live" questions about tokens, sessions, or cost. Do not use for auth review or for…

solanabr/writer-style-skill

Agent

Builds a writer-style voice pack — a PRIMARY voice (reproduce the target author's idiolect) or a SECONDARY voice (strip idiolect, keep transferable craft) — using an adversarial, evidence-bound, multi-pass process: clean corpus → parallel lens-miners → synthesize → opposed judges → (for a primary)…

solanabr/writer-style-skill

Agent

Runs the post-generation checks on writer-style output: a fact-preservation diff (every verified number/identifier must survive styling unchanged), an AI-tell lint (banned words, false-antithesis, em-dash overuse, uniform cadence), and a repetition audit across a batch of lessons. Reports pass/fail with the specific…

solanabr/writer-style-skill

Agent

Writes original educational and long-form technical content in a target author's voice using a voice pack and a facts-first workflow. Loads the always-on primary voice, routes the right secondary craft by the piece's job, restyles VERIFIED facts (never re-deriving them), and enforces the naturalness floor so the…

pashki975/thm-claude-kit

Agent Claude Code

Plans Active Directory attack paths from enumeration or BloodHound data. Use on domain-joined Windows rooms.

pashki975/thm-claude-kit

Agent Claude Code

Maps discovered service versions to known CVEs and public exploits. Use after version detection.

pashki975/thm-claude-kit

Agent Claude Code

Ranks Windows privilege escalation paths from enum output. Use after winPEAS/whoami/systeminfo on a Windows box.