AI & ML

officebeats Bundle

Diagnose and redesign bloated AI context using bounded retrieval, explicit context ownership, and phase-aware compaction.

sentientsprite Bundle

OpenProse VM skill pack. Activate on any `prose` command, .prose files, or OpenProse mentions; orchestrates multi-agent workflows.

hatayama Skill

Sample uloop hello-world tool. Use to verify custom tool wiring or inspect a minimal tool implementation example.

digital-stoic-org Skill

Convert Word (.docx) files to clean markdown for LLM context (uses markitdown). Use when converting Word documents to markdown for analysis or summarization. Triggers include "convert docx", "word to markdown", "docx file".

digital-stoic-org Skill

Convert EPUB files to clean markdown for LLM context (uses epub-to-markdown). Use when converting ebooks or EPUB documents to markdown for analysis or summarization. Triggers include "convert epub", "epub to markdown", "epub file".

digital-stoic-org Skill

Convert PowerPoint (.pptx) files to clean markdown for LLM context (uses markitdown). Use when converting presentations to markdown for analysis or summarization. Triggers include "convert pptx", "powerpoint to markdown", "pptx file", "slides to markdown".

digital-stoic-org Bundle

Decide HOW work should EXECUTE — linear vs parallel fan-out, sub-agents vs teams vs dynamic Workflow, and the per-step seam — instead of defaulting to linear+single-model. Produces an execution design, does NOT run the task. Delegates the per-step model+effort call to a model-picker skill when the environment has one. Use when authoring/challenging a skill or agent, AND mid-task when deciding how to run real work — 'should I fan this out', 'should this fan out', 'parallel or linear', 'sub-agents or workflow', 'per-step seam', 'execution topology', 'execution architecture'. For a trivial few-item call, early-exit to linear cheaply rather than a full analysis.

digital-stoic-org Bundle

Autonomous multi-philosopher dialogue using Agent Teams. Use when: /encounter, autonomous dialogue, philosopher encounter, run philosophers, let philosophers talk.

digital-stoic-org Bundle

Automates agent-skills plugin version bumps and release metadata. Use when: adding/removing/updating skills or commands, bumping plugin version, preparing a release. Triggers: bump version, edit plugin, update plugin, release, version bump, new skill added, new command added.

abagames Bundle

Routes a user's request to a separate task, subagent, automation, or current agent with an appropriate model role, reasoning effort, and workspace isolation. Use when the user or an authoritative instruction asks to dispatch, delegate, orchestrate, enter dispatch mode, run work in another session, select an execution backend, or schedule work. While dispatch mode is active, proactively send substantive execution to the host's preferred worker boundary: a new user-visible task in Codex Desktop App and a subagent on hosts without durable tasks. Do not invoke merely because ordinary work is complex, long-running, or parallelizable, or when this skill is only being mentioned, reviewed, or edited.

abagames Skill

Reviews the agent's own immediately preceding response as an advisory pass, surfacing assumptions, reasoning gaps, alternatives, and unverified claims. Use ONLY when the user explicitly asks for self-critique, critical thinking, or challenges to the agent's prior answer. Do not use for normal follow-ups, someone else's work, automatic checking, or independent quality assurance.

abagames Bundle

Distills reusable agent procedures, validation loops, debugging methods, tool-use patterns, and decision rules from completed, paused, abandoned, or failed projects. Use when closing or archiving a project, reducing side-project sprawl, or when asked to harvest project knowledge into reusable agent capabilities. Gates candidates for trigger clarity, validation, and transferability to avoid weak skills.

abagames Bundle

Measures whether a player who was never told the rules can read a game's intent off the screen, by sampling scenes from a recorded run and having an isolated agent that has not seen the design or source name the goal, the options, and the risk. Use when a game runs and its mechanics are verified but it is unknown whether the screen communicates what to aim for without a tutorial or HUD text, or as a cheap early gate that can fail a design for decision collapse before a telemetry sweep. Not for judging fun or difficulty, not for verifying that a mechanic matches its spec, and not for confirming that varied decisions survive continued optimal play.

abagames Bundle

Validates that one abstraction layer (a spec, design doc, schema, contract, or generated artifact) is self-sufficient by spawning an ISOLATED sub-agent that sees only that layer and must reconstruct the adjacent layer, returning pass / weak-pass / fail. Use when checking whether an extracted or generated artifact preserves enough structure to be rebuilt or used without the original source, and to prevent an author from grading their own output.

abagames Bundle

Splits a batch of expensive per-item agent work into a cheap reversible pass over every item and an expensive irreversible pass, separated by a method-freeze checkpoint. Use when running one costly procedure over many items (evaluations, migrations, audits, labeling, benchmark or fixture construction) and the method — rubric, transform rules, criteria, instrument — could still turn out to be wrong, or when part of the work spends something that cannot be spent twice: fresh seeds, held-out data, one-shot quota, published output, or a reviewer's first impression. Not for single items, cheap items, or a method already validated on the same class of item.

atournayre Skill

Orchestre une équipe d'agents spécialisés pour les tâches complexes. Auto-détecte le type, compose l'équipe, coordonne les phases analyse → challenge → implémentation → QA.

atournayre Skill

Démarre un développement avec un starter léger puis active le mode plan

atournayre Bundle

Expert guidance for creating, building, and using Claude Code subagents and the Task tool. Use when working with subagents, setting up agent configurations, understanding how agents work, or using the Task tool to launch specialized agents.

hatayama Bundle

Migrate only uloop V2 CLI option syntax in agent skills, Markdown, POSIX shell scripts, and PowerShell scripts to V3 syntax. Use when updating first-party or third-party uloop command examples that contain V2-style boolean arguments or renamed options.

kynetic-ai Skill

Pencil MCP reference and canvas conventions for designing kynetic-spec web UI

abagames Bundle

Reverse-engineers existing source code into a two-layer artifact ladder — a concrete reproduction spec (preserves behavior-affecting constants, same-tick ordering, input edges, collision/threshold semantics; drops cosmetics) and an abstract design doc (intentionally omits reproduction detail and records what is unspecified vs. safe-to-assume). Use to document or recover a program's intent and reproducible behavior without leaking implementation-only detail into the design layer.

abagames Bundle

Injects controlled, game-specific semantic defects — timing/order, identity and lifecycle, scoring and economy, persistence/save, RNG/determinism, input buffering, animation-gameplay sync, content/configuration — into a game or its trace reducer, and records a withheld manifest of intended defect mechanism, precondition, expected symptom, violated invariant, hidden oracle, equivalent-mutant risk, and a clean-control counterpart, so the detection power of a test suite or of an agent repair workflow can be measured against known-planted defects. Use when measuring whether tests or an agent workflow actually catch gameplay defects, when building known-bad fixtures for a with-skill / without-skill comparison, or when checking that a workflow does not "fix" a healthy build. Not for finding unknown defects in a real build, not for repairing defects, and not for balance tuning.

abagames Bundle

Refines a reusable agent workflow based on an actual execution result, review, failure, or simulation output. Classifies problem causes (task/execution/workflow/evaluation/capability-boundary/output-format/overconstraint) before proposing the smallest workflow diff. Use when the user wants to improve a workflow, prompt, rubric, or agent skill after applying it to a real task.

atournayre Skill

Vérifie la checklist avant exécution et liste les oublis

atournayre Skill

Transforme un prompt en prompt exécutable compatible avec le Task Management System (TaskCreate/TaskUpdate/TaskList)

atournayre Bundle

Expert prompt engineering for creating effective prompts for Claude, GPT, and other LLMs. Use when writing system prompts, user prompts, few-shot examples, or optimizing existing prompts for better performance.

digital-stoic-org Bundle

Create or audit RISEN prompts with structure validation. Use when creating structured prompts from notes, auditing existing RISEN prompts, or improving prompt quality. Triggers include "risen prompt", "edit risen", "create risen", "audit risen", "structure prompt".

ils15 Skill

Pin session objectives to prevent scope creep. Use for alignment across long multi-agent sessions.

hoangsonww Bundle

Operate and maintain the local MCP server for this project. Use when creating MCP host config, troubleshooting tool connectivity, modifying tool domains, or adjusting safety policy flags.

hoangsonww Bundle

Audit the configured MCP servers (user + project scope) via the Agent Monitor Config Explorer API: transport (stdio vs http), command/args and env variable names, headers, and the source file each definition came from. Reads /api/cc-config/mcp. Use when reviewing MCP integrations for hygiene, duplication, or unexpected transports.

hoangsonww Bundle

Define and check simple service-level objectives for Claude Code from Agent Monitor data — session completion rate, tool success rate (PostToolUse/PreToolUse), and error rate (APIError/total) — then compare each to its target and report the error budget remaining. Use when reporting reliability or when someone asks "are we meeting our SLOs?".

hoangsonww Bundle

Render the multi-agent orchestration DAG for a session — parent→child subagent edges, tree depth, and fan-out — from the Agent Monitor workflow intelligence API. Cross-checks the orchestration dataset against the raw agent records and session detail. Use when visualizing how a session's agent structure was organized.

hoangsonww Bundle

Benchmark one session (or a small recent set) against the rolling average using Agent Monitor data — cost, total tokens, tool count, and workflow complexity score — and report where each metric lands as a percentile of the population. Tells you whether a session was normal, cheap, or an outlier. Use when judging whether a session was typical or out of band.

hoangsonww Bundle

Scan recent Claude Code activity for errors and failure signals across all sessions using Agent Monitor data — APIError events and PreToolUse→PostToolUse gaps (tools that started but never completed) — then group failures by tool and model and rank them by frequency. Use when checking for errors or asking "what's failing right now".

hoangsonww Bundle

Run a full audit of the user's Claude Code configuration via the Agent Monitor Config Explorer API: counts per surface (user vs project), duplicate or overlapping skills and subagents, hooks that run shell commands, and which surfaces are read-only vs mutable. Reads /api/cc-config/overview, /skills, /agents, /commands, /hooks, and /settings. Use when reviewing your Claude Code setup for sprawl, duplication, or risk.

hoangsonww Bundle

Roll up Claude Code sessions by working directory (project) from Agent Monitor data — session count, total cost, total tokens, and last-active timestamp per cwd — so per-project activity can be compared at a glance. Use when summarizing where effort and spend went across projects.