antoniocascais/claude-code-toolkit
Agent
Deep specialist seat pinned to Sonnet 5 (full model ID, bypasses the haiku alias remap) for the harder reasoning / verification role. Role and charge are supplied in the spawn prompt — a hard council seat, a recon verifier that cross-checks scout findings, or any task needing stronger reasoning. Full tool access to…
antoniocascais/claude-code-toolkit
Agent
Fast specialist seat pinned to real Haiku 4.5 (full model ID, bypasses the haiku alias remap). Cheap parallel specialist whose role and charge are supplied in the spawn prompt — a council seat, a codebase recon scout, or any other low-cost specialist task. Full tool access to ground work in the actual repo.
antoniocascais/claude-code-toolkit
Agent
Implements a fully-specified coding task from a written spec. Executes; does not design. Only use when explicitly dispatched with a spec file — do NOT auto-delegate for design, brainstorming, or open-ended work.
antoniocascais/claude-code-toolkit
Agent
Claude Fable 5 agent, pre-tuned per Anthropic's Fable 5 prompting guide. Use for the hardest, longest-horizon, most ambiguous work — multi-hour/multi-day implementations, deep debugging, whole-repo review, dense-image/vision analysis, or anything where first-shot correctness on a complex spec matters. Not for routine…
antoniocascais/claude-code-toolkit
Agent
Enhance knowledge base entries following Obsidian standards by implementing approved improvement plans from knowledge base reviews.
antoniocascais/claude-code-toolkit
Agent
Architecture design and review specialist. Discusses system-design questions in an architecture context, and on request scores existing architecture against a rubric (Scalability, Coupling/Cohesion, Reliability, Security, Cost, Operability — 1-5 each), flags concrete issues, and recommends a direction with explicit…
antoniocascais/claude-code-toolkit
Agent
Optimize task notes for Claude's session performance by cleaning outdated context and maintaining accurate project status.
antoniocascais/claude-code-toolkit
Command
Security review between two versions of a FOSS Android app.
antoniocascais/claude-code-toolkit
Command
Warm up skill discovery then execute task.
antoniocascais/claude-code-toolkit
Command
Responds to PR review comments from screenshots. Use when assessing reviewer feedback, triaging PR suggestions, or deciding whether to accept/reject proposed changes.
antoniocascais/claude-code-toolkit
Skill Claude CodeCodex
User-invoked codebase recon via an ant-colony pattern. The moderator carves a large or unfamiliar codebase into disjoint territories, fans out cheap Haiku scout subagents that explore in parallel and dump full findings to /tmp scratchpads (returning only terse pointers), then one Sonnet verifier cross-checks every…
antoniocascais/claude-code-toolkit
Skill Claude CodeCodex
Dispatches a task to a Claude Fable 5 subagent with a prompt written the way Fable 5 wants to be prompted, and holds a back-and-forth with it across turns. Use when the user says /ask-fable, ask fable, fable, fable 5, send this to fable, hand this off to fable, get a Fable second opinion, or when a task sits at the…
antoniocascais/claude-code-toolkit
Skill Claude CodeCodex
Conducts realistic mock interviews with detailed feedback and scoring. Use for interview prep, behavioral questions, technical interviews, STAR practice, system design interviews, or interview coaching.
antoniocascais/claude-code-toolkit
Skill Claude CodeCodex
User-invoked breadth check — convenes 3 specialist subagent personas to pressure-test a plan/decision/diff from angles you might have missed, surfacing framed positions + a dissent log. Intended to run AFTER the user has already reasoned through the problem, as a final "did we miss anything" sweep.
antoniocascais/claude-code-toolkit
Skill Claude CodeCodex
Manages tasks using the ctask CLI wrapper over a local SQLite database. Use when tracking work items, creating tasks, managing dependencies, adding comments, labeling, or reviewing task status. Triggers on task tracking, ticket management, work planning, backlog management.
antoniocascais/claude-code-toolkit
Skill Claude CodeCodex
Serialize the current brainstorm/design discussion into a structured implementation spec and delegate the build to the cheaper "executor" subagent (Sonnet). Use when the user says to dispatch, delegate, hand off, or offload implementation to the executor after designing an approach together.
antoniocascais/claude-code-toolkit
Skill Claude CodeCodex
Plans and executes git commits with optional TICKETID prefix. Analyzes staged changes, proposes optimal commit structure (single or multiple), generates descriptive messages with technical context, and executes after user approval. Use when committing code changes, creating atomic commits, or splitting large…
antoniocascais/claude-code-toolkit
Skill Claude CodeCodex
Creates impressive LaTeX Beamer presentations with modern design. Generates .tex files with theme selection, font pairing, TikZ diagrams, overlays, and best practices. Use for LaTeX slides, Beamer presentations, scaffolding decks, slide design advice, or TikZ diagram generation.
antoniocascais/claude-code-toolkit
Skill Claude CodeCodex
Reviews code changes before merging, through a correctness/security lens and an SRE operational-risk lens. Use when reviewing PRs, checking staged changes, reviewing diffs, code review, merge readiness check, assessing deploy or rollback risk, or validating changes before commit/push.
antoniocascais/claude-code-toolkit
Skill Claude CodeCodex
Drafts a copy-pasteable prompt for Claude Fable 5 without dispatching anything. Use when the user says /prompt-fable, write me a fable prompt, draft a prompt for fable, help me prompt fable 5, or wants to hand a prompt to Fable somewhere else (the web app, another session, a colleague). For actually running the task…
antoniocascais/claude-code-toolkit
Skill Claude CodeCodex
Generates multiple choice quiz questions based on current conversation context. Use when testing understanding, reviewing what was discussed, or wanting a knowledge check on the session.
antoniocascais/claude-code-toolkit
Skill Claude CodeCodex
Creates new Claude Code skills with proper structure and best practices. Use when user wants to create a skill, update an existing skill, add a new command, scaffold a workflow, define skill hooks, or asks "how do I make a skill".
antoniocascais/claude-code-toolkit
Skill Claude CodeCodex
Remove AI writing patterns from prose. Use when drafting, editing, or reviewing text to eliminate predictable AI tells.
antoniocascais/claude-code-toolkit
Skill Claude CodeCodex
Guides strong, effective unit test generation using proven testing techniques. Use when writing unit tests, reviewing test quality, improving existing tests, generating test cases, checking test coverage strength, or when tests exist but may be weak. Triggers on: unit test, test quality, test coverage, write tests…