AI & ML

austek Skill

Compact the current conversation into a handoff document for a fresh agent to pick up.

max-786 Bundle

Turn multiview fit reports into a sequential or parallel repair queue for aligning Blender products to source-of-truth templates. Use after validation shows disalignment, when the agent must iteratively fix wireframe, texture, lighting, or projection mismatches, and when a recurring failure should stop the rebuild loop for a diagnosis.

max-786 Skill

Build complete product scenes using PolyHaven assets — HDRI environment, textured ground/pedestal, and optional props from the 3D model library. Trigger when asked to build a product scene, create a showcase setup, add a pedestal, or compose a product shot.

austek Bundle

Build and sharpen project's domain model (glossary/ADRs). Use when modifying CONTEXT.md or ADRs.

austek Skill

Tool-selection rules for when the IntelliJ IDEA MCP server (`mcp__idea__*` tools) is connected. Consult this whenever exploring code (finding a symbol, its usages, or callers), checking whether a file compiles or lints, doing a multi-site rename or refactor, or debugging a runtime issue — the IDE's index and debugger are cheaper and faster than Bash/grep/Read for these. Always check this before reaching for grep, cat, a full Gradle/Maven/npm build, or a print-statement debugging loop when `mcp__idea__*` tools are present in the session's tool list, even if the user's request doesn't mention the IDE.

yannick-bottino Bundle

Moteur de mémoire structurée à 3 couches (Cold / Warm / Hot) pour une mission de conseil. À utiliser dès qu'un agent ou un skill doit lire ou persister de la mémoire projet avant de modifier un livrable. Se déclenche pour : initialiser le substrat de mémoire d'un projet (init_memory, appelé par project-init), lire les décisions actives AVANT de réécrire un livrable, acter une décision structurante (cadrage, méthodo, hypothèse, arbitrage client), écrire une synthèse de jalon, logguer un run IA, ou lancer une passe de maintenance ("lint", "health-check de la mémoire", "operator run", "heartbeat", "dreams", "vérifie la mémoire du projet", "synthèse de jalon"). Lire les décisions actives EN PREMIER avant d'écraser toute saisie humaine. Utilise ce skill chaque fois que la mémoire d'un projet doit être lue, écrite ou maintenue, même si l'utilisateur ne nomme pas explicitement le "substrat" ou la "mémoire".

yannick-bottino Skill

Start a clean Claude session with only the context the next task needs, instead of /compact. Captures the goal of your next session, points to the right files (never copies them), and outputs a self-contained prompt to paste into a fresh chat. Use when: "re-fresh", "refresh context", "fresh start", "session handoff", "my chat got sloppy", "start a new chat with context", "hand off this session", outputs degrading, drifting off task. Three levels: lite (quick reset), full (default handoff), ultra (full briefing). NOT for: summarizing in place (that's /compact), or saving permanent notes.

yannick-bottino Skill

Analyzes and improves prompts submitted by consultants for Claude Opus 4.7 in the chat app (claude.ai, Mac, iOS). Applies an updated framework (5 core components + 3 advanced modes) combined with Opus 4.7-specific principles. Use this skill whenever a user asks to improve a prompt, restructure an instruction for Claude, or shares a prompt saying "comment je peux ameliorer ca", "optimise ce prompt", "improve this prompt", "aide-moi a mieux prompter", "refine my prompt", "prompt review", "is this prompt good enough?", "c'est un bon prompt ?", "comment prompter Claude". Also trigger when the user pastes a block of text that looks like a prompt and asks for feedback or improvement. Even "review my prompt" or "critique this prompt" should trigger this skill.

ccronca Skill

Consult official Claude Code documentation from docs.claude.com using selective fetching. Use this skill when working on Claude Code hooks, skills, subagents, MCP servers, or any Claude Code feature that requires referencing official documentation for accurate implementation. Fetches only the specific documentation needed rather than loading all docs upfront.

ccronca Skill

Create an agent team to analyze data engineering architectural changes from multiple perspectives (performance, architecture/design patterns, data quality). Teammates work in parallel to review changes, then synthesize findings into a design document with recommendations.

jboguanzon Skill

Compact the current conversation into a handoff document for another agent to pick up.

austek Skill

Socratic tutor for learning Rust and Python — progressive exercises, compiler/traceback-driven debugging, ownership vs. runtime-model contrasts. Use when the user asks to learn, practice, or debug exercises in Rust or Python, or wants a language concept explained from first principles.

navinspire-ia Bundle

Inspect and optionally adjust the agent's runtime state. Use to check the current model or preset, context window, iteration progress and limits, token usage, workspace and tool configuration, subagent status, and request routing metadata such as channel, chat ID, and sender ID; diagnose unavailable capabilities; change allowed runtime settings; or store temporary session scratchpad values.

tticom Bundle

Write a durable, repository-owned handoff tied to exact revisions and evidence without duplicating specs, diffs, or reports. Use when work must survive conversation loss, cross agent or identity boundaries, accompany a PR, or record the state of a governed development task.

tticom Bundle

Verify operating-system, home, Git-host, commit, workspace, and branch identity before repository mutations, then enforce branch-safe Git and PR operations. Use with multiple agent accounts, isolated clones, protected branches, automation identities, or policies that allow feature pushes but prohibit direct main pushes, force pushes, self-approval, or merges.

tticom Bundle

Safely remove stale review worktrees and prune dead worktree metadata across the Git checkouts in an agent workspace, preserving any dirty, locked, unclassified, or unverified work, and record a receipt and checkout index. Use when asked to clean up the workspace, remove stale review worktrees, or produce a map of the workspace checkouts.

tticom Bundle

Execute a versioned, review-gated development task without conflating project policy with reusable workflow mechanics. Use when a repository has an active-task pointer or approved prompt, fixed scope, validation contract, separate author/reviewer identities, or a one-PR-at-a-time development loop.

navinspire-ia Skill

Search and install agent skills from ClawHub, the public skill registry.

navinspire-ia Skill

Work with GitHub Actions, GitLab CI, and deployment pipelines - inspect runs, fix workflows, and gate releases. Use gh when available for Actions.

navinspire-ia Skill

Run the Navin Career desk for freelance missions and permanent jobs. Search authorized sources, score matches, tailor a CV from the Master CV, import pasted LinkedIn offers, track inbox and follow-ups. Use for /career, Freelance, Jobs, TJM, candidatures.

navinspire-ia Skill

BTC / ETH / SOL swing skill for the Trading Agent OS. Technical + sentiment + vol cap; no fake token fundamentals.

navinspire-ia Skill

Recommend which model or provider preset to use based on cost, latency, context size, and task difficulty. Use when the user asks which model to pick or when work is mismatched to the current model.

navinspire-ia Skill

Run the Navin Trading Agent OS. Use when the user wants a programmable investment agent, paper portfolio, market scan, debate, risk limits, backtest, or /trading.

navinspire-ia Skill

Detect duplicates, missing values, schema drift, and inconsistencies across datasets. Use before migrations, reporting, or model training.

navinspire-ia Skill

Recover from tool failures and flaky commands with intelligent retries, alternate tools, and clear fallbacks. Use when exec, network, or MCP calls fail mid-task.

rlaope Skill

[omh] Policy overlay for terminal commands - add cwd, environment, safety, and result-evidence gates after preferring native shell tools for ordinary CLI, package-manager, and test runs. Use when the user says: command-operator, command operator, terminal command, terminal task, shell command, shell task, cli command, command execution.

rlaope Skill

[omh] Business research brief - turns a market, competitor, pricing, or customer question into a structured evidence-vs-inference brief; for raw link gathering use ulw-research, and for ongoing multi-role research use research-department. Use when the user says: research-brief, business-research, business research, research brief, decision brief, pricing decision brief, decision-ready brief, source-backed business research.

rlaope Skill

[omh] Policy overlay for live lookups - add provider, freshness, units, and source-quality gates after preferring native live-data tools for ordinary weather, finance, sports, maps, and time-zone requests. Use when the user says: live-info-operator, live info operator, live information, real time information, real-time information, weather today, current weather, weather forecast.

rlaope Skill

[omh] Hermes Deep Interview workflow: one-question-at-a-time clarification. Use when the user says: deep-interview, interview, clarify, feature shaping, ambiguous product request, one question, 要件を詰めて, 曖昧な要求.

rlaope Skill

[omh] Agent Debug workflow: capture a stuck, looping, drifting, or repeatedly failing agent run, diagnose the likely failure pattern, and prepare the smallest safe recovery action. Use when the user says: agent-debug, agent debug, agent debugging, agent introspection, agent self-debug, self-debug, self debugging, looping agent.

rlaope Bundle

[omh] Hermes Code Review workflow: bug-first review with evidence. Use when the user says: code-review, review, audit, find bugs, release gate, claim audit, evidence audit, README claim.

navinspire-ia Skill

Turn websites into clean Markdown or structured JSON for RAG, migrations, or analysis. Use when the user needs scraped content, tables, or documentation corpora - not full browser testing.

navinspire-ia Skill

Macro overlay for the Trading Agent OS. Tape, vol, and benchmark first; single-name stories second.

navinspire-ia Skill

Query metrics, logs, and traces (Prometheus, Grafana, Loki, Sentry, OpenTelemetry) to diagnose incidents. Use during outages or performance investigations.

navinspire-ia Skill

Plan and execute source→target data migrations with mapping, transforms, reconciliation, and cutover checks. Use for CRM/ERP/DB moves.

navinspire-ia Skill

Map the attack surface and build a STRIDE threat model - trust boundaries, data flows, entry points, assets, and prioritized threats with mitigations. Use for /threatmap, architecture security reviews, or "what could go wrong?" planning.