agent reliability skills

FailproofAI/failproofai

Skill Claude CodeCodex

Build and maintain documentation sites with Mintlify. Use when creating docs pages, configuring navigation, adding components, or setting up API references.

FailproofAI/failproofai

Skill Claude CodeCodex

The way to answer "how are my production AI agents doing?" and to run the team's agent-observability deployment — reach for it even on casual phrasing that names no tool. Trigger when the user wants to: • inspect agent telemetry — did agents error/fail/go flaky; sessions, events, latency, token usage, slowest models…

qualixar/superlocalmemory

Skill Claude CodeCodex

Index and query a codebase as a structural graph — build the code graph, trace blast radius of a change, find callers/callees/inheritors, semantic code search by meaning, assemble PR review context, and detect what changed since last index. Use when the user asks how code connects, what breaks if X changes, what calls…

qualixar/superlocalmemory

Skill Claude CodeCodex

Cross-session peer coordination via the SLM mesh network. Lets multiple AI agent sessions on the same machine discover each other, send messages, share lightweight state, and lock files to avoid conflicts. Requires full, power, or mesh MCP profile. All 8 tools are MCP-only — there is no CLI fallback.

qualixar/superlocalmemory

Skill Claude CodeCodex

Search and retrieve facts, decisions, and past context from SuperLocalMemory. Use when the user asks to recall, find, search, or "what did we decide/say about X". Triggers multi-channel semantic retrieval with reranking; always call before storing anything new.

qualixar/qualixar-os

Skill Claude CodeCodex

Use when the user needs to run GitNexus CLI commands like analyze/index a repo, check status, clean the index, generate a wiki, or list indexed repos. Examples: "Index this repo", "Reanalyze the codebase", "Generate a wiki".

qualixar/qualixar-os

Skill Claude CodeCodex

Use when the user is debugging a bug, tracing an error, or asking why something fails. Examples: "Why is X failing?", "Where does this error come from?", "Trace this bug".

qualixar/qualixar-os

Skill Claude CodeCodex

Use when the user wants to rename, extract, split, move, or restructure code safely. Examples: "Rename this function", "Extract this into a module", "Refactor this class", "Move this to a separate file".

IgorGanapolsky/ThumbGate

Skill Claude CodeCodex

Fetch live ThumbGate revenue, paid orders, and funnel telemetry from production billing endpoints. Use BEFORE answering any question about money, conversion, traffic, or "why we didn't make X." Never quote planning documents as actuals.

IgorGanapolsky/ThumbGate

Skill Claude CodeCodex

Status: shipped 2026-04-21. Test-backed. CLI-automatable. Safe to recommend publicly.

IgorGanapolsky/ThumbGate

Skill Claude CodeCodex

Automated Bluesky reply monitoring and draft queueing for ThumbGate's acquisition engagement loop. Polls the AT Protocol notifications endpoint every 15 minutes, writes human-reviewable draft replies into a queue file, and never auto-posts without sign-off. Trigger when the user asks about Bluesky replies, engagement…

ByteStack-Labs/claude-plugins

Skill Claude CodeCodex

Detects and quantifies confidently-wrong behavior: where a model, classifier, agent, or LLM judge is highly confident and incorrect, and where the coupling between confidence and correctness breaks down under distribution shift. Measures calibration on the in-distribution set and again on the production distribution…

ByteStack-Labs/claude-plugins

Skill Claude CodeCodex

Start here. Audits a deployed ML or LLM or agent system that scores well on evaluation but fails, regresses, or behaves unexpectedly in production. Runs a reproducible root-cause "autopsy": frames the eval-to-deployment gap, reproduces the production failure, quantifies it by slice, tests confidence calibration under…

ByteStack-Labs/claude-plugins

Skill Claude CodeCodex

Verifies the tools an agent or orchestrator depends on, by re-deriving a tool evaluation's real accuracy instead of trusting a single pass/fail score. Separates a formatting miss (a correct value scored wrong) from a real failure (a wrong value scored right), recomputes the expected answer from the raw inputs rather…

fainir/flipback

Skill Claude CodeCodex

Decide well whether to end your turn, finish big tasks instead of delivering a piece of one, and never hand the user a list of remaining steps. Use this when you are about to stop and the work is not verifiably done - you have completed part of a multi-part request, announced work you have not done, hit an error you…