Kior Labs

    0followers

    Independent studio building tools and reviews for teams running AI agents: trace diagnosis, security review, eval sets, cost and context. Each skill ships as a small runnable tool with a reproducible sample, stated limits, and support for Claude Code, Cursor and any agent that reads SKILL.md. Makers of Tracegrade.

    55 skills
    1 use
    Joined Nov 2026

    Skills by Kior Labs (55)

    MCP Config Audit — What Your MCP Config Gives Away

    by Kior Labs

    Free

    Reads your mcp.json and reports the unpinned package that fetches new code at every start, the token sitting in the file, the endpoint that is plain HTTP, and what runs without asking you.

    1
    1

    Lockfile Diff Review — What Your npm Update Added

    by Kior Labs

    Free

    Compares two package-lock.json files and shows the new direct dependencies, install scripts, non-registry sources, integrity changes and name lookalikes.

    1
    0

    CI Failure Triage — Find the First Real Failure

    by Kior Labs

    Free

    Reads a failed CI log, separates the first real failure from the cascade after it, and gives a fix order for each failing job.

    1
    0

    Test Gap Map — Find Changed Code With No Test

    by Kior Labs

    Free

    Reads a diff and maps every source file to the test file that should move with it, naming the changed code that no test in the repository covers by name.

    1
    0

    Commit Message Doctor — Make Your Git History Reviewable

    by Kior Labs

    Free

    Reads a real git log, scores the commits that will confuse reviewers, and drafts the changelog grouped into features, fixes and breaking changes.

    1
    0

    Diff Risk Brief — Review the Risky Files First

    by Kior Labs

    Free

    Reads a unified diff and ranks the files that deserve careful review first: auth, money, migrations, lockfiles, large edits and changes with no test moving with them.

    1
    0

    Agent Timeout Budget — Where Your Latency Goes

    by Kior Labs

    Free

    Reads run traces and computes per-tool p50/p95/p99 latency, timeout rate, retry amplification and a suggested timeout from the observed tail.

    1
    0

    MCP Token Budget — What Your Tool Schemas Cost

    by Kior Labs

    Free

    Reads a captured tools/list and estimates the context your MCP servers consume, which tools are expensive, and how much is schema rather than useful description.

    1
    0

    Eval Leakage Check — Is Your Test Set Contaminated?

    by Kior Labs

    Free

    Reads your eval JSONL and reports duplicate cases, answers sitting in the prompt, test inputs that also appear in train, and label imbalance before you quote a score.

    1
    0

    Judge Sanity Check — Is Your LLM Judge Stable?

    by Kior Labs

    Free

    Reads your paired verdicts and reports chance-corrected agreement, position flips, verbosity bias, self-preference and sample size — before a judge score gates a release.

    1
    0

    Tool Description Lint — Why Your Agent Picks the Wrong Tool

    by Kior Labs

    Free

    Reads your tool definitions and reports the missing boundaries, undocumented parameters, overlapping tools and unguarded destructive actions that make an agent choose wrong.

    1
    0

    Agent Eval From Traffic — Turn Real Runs Into a Test Set

    by Kior Labs

    $12

    Turns production traces into a deduped, redacted eval set with tool assertions and a coverage manifest, so you can test the requests your agent actually receives.

    1
    0

    Agent Security Review Pack — Score Your Agent Build

    by Kior Labs

    $14.99

    Reads your agent repo and scores the surfaces an injected instruction can reach: prompt assembly, tool permissions, secrets, output handling, run bounds and egress, mapped to the OWASP Agentic Top 10.

    1
    0

    Agent Reliability Pack — Find Where Your Agent Fails

    by Kior Labs

    $19

    Reads your run traces and reports task success, recovery, retry amplification, loops and the top failure classes, each with the fix that actually applies to it.

    1
    0

    Context Lint — Find What's Bloating Your Instructions

    by Kior Labs

    Free

    Reads your CLAUDE.md and AGENTS.md and reports the rules that contradict each other across layers, the duplicates, the dead file paths, the vague directives, and what every session pays for them.

    1
    0

    Tool Safety Scan — Audit Your Agent's Tool Contract

    by Kior Labs

    Free

    Reads your tool definitions and reports hidden instructions, cross-tool steering, ungated actions and any change since approval.

    1
    0

    Agent Cost Scan — What Every Run Really Costs

    by Kior Labs

    Free

    Reads your agent logs and reports cost per run, the model eating the budget, and three ranked fixes with the money each one recovers.

    1
    0

    Incident Runbook Starter

    by Kior Labs

    Free

    Write a runbook that works at 3am, from an incident you already survived: symptoms, blast radius, triage tree, safe actions, escalation, verification.

    1
    0

    Flaky Test Triage Card

    by Kior Labs

    Free

    Sort flaky failures into timing, state, order, network and nondeterminism, with the diagnostic command and the fix for each.

    1
    0

    Agent Cost Quick Audit

    by Kior Labs

    Free

    Turn your agent logs into a cost table, then separate necessary spend from waste you can delete this week.

    1
    0

    RAG Failure Triage

    by Kior Labs

    Free

    Find out whether a bad RAG answer came from the query, retrieval, ranking, generation or the corpus, before you rewrite a single prompt.

    1
    0

    Prompt Injection Test Pack

    by Kior Labs

    Free

    24 ready-made injection attacks, a scoring sheet, and the control that blocks each class, so you can measure an agent before you ship it.

    1
    0

    MCP Security Checklist

    by Kior Labs

    Free

    A 12-point, evidence-based security pass over any MCP server before you install it, approve it for a team, or publish your own.

    1
    0

    Dependency Upgrade Strategist

    by Kior Labs

    $15

    Plan a risky dependency or runtime upgrade: blast radius, ordering, verification and rollback.

    1
    0

    API Deprecation Planner

    by Kior Labs

    $15

    Plan a breaking API change: real usage inventory, segmented consumers, gates instead of dates.

    1
    0

    Flaky Test Triage

    by Kior Labs

    $12

    Group flaky failures by cause, rank by real cost, and fix the suite with a quarantine that expires.

    1
    0

    Log to SLO Compiler

    by Kior Labs

    $15

    Turn real logs into SLIs, SLOs, error budgets and burn-rate alerts that fire on user pain.

    1
    0

    Cloud Cost Anomaly Explainer

    by Kior Labs

    $15

    Explain a cloud bill spike from usage data, separating cause from correlation, with a ranked fix list.

    1
    0

    Data Contract Enforcer

    by Kior Labs

    $15

    Detect schema and semantic drift, write the contract, add the CI check that keeps it true.

    1
    0

    Incident Runbook Builder

    by Kior Labs

    $12

    Turn past incidents into runbooks that work at 3am: signals, triage trees, decisions, verification.

    1
    0

    Postgres Query Surgeon

    by Kior Labs

    $15

    Diagnose a slow Postgres query from its plan, then prescribe the fix with risk notes.

    1
    0

    EU AI Act Readiness Pack

    by Kior Labs

    $19

    Classify an AI system under the EU AI Act, map obligations and build the documentation pack.

    1
    0

    AI Supply Chain Attestation

    by Kior Labs

    $19

    Attest what runs in your AI stack: SBOM, provenance, signing and verification at install.

    1
    0

    Secrets Exposure Audit

    by Kior Labs

    $12

    Find leaked credentials across history, logs and bundles, triage real exposure, then rotate and prevent.

    1
    0

    AI Threat Model

    by Kior Labs

    $15

    Threat-model an AI feature before launch: injection, agency, exfiltration, controls and residual risk.

    1
    0

    MCP OAuth Implementer

    by Kior Labs

    $19

    Move a remote MCP server from a shared API key to OAuth 2.1: discovery, audience, scopes and tests.

    1
    0

    Human in the Loop Gate Designer

    by Kior Labs

    $15

    Decide which agent actions need a human, place the gate where it holds, and measure whether it works.

    1
    0

    Multi Agent Topology Designer

    by Kior Labs

    $19

    Decide whether you need more than one agent, then design the topology, handoffs and state.

    1
    0

    Agent Observability Setup

    by Kior Labs

    $15

    Instrument an agent so failures are visible before users report them: spans, attributes, dashboards and alerts.

    1
    0

    Structured Output Repair

    by Kior Labs

    $12

    Fix unreliable JSON from an LLM: classify the failures, repair the schema and add validation that fails loudly.

    1
    0

    Eval Dataset Curator

    by Kior Labs

    $15

    Build a gold eval set from production data: stratified, deduplicated, labelled and versioned.

    1
    0

    Context Budget Engineer

    by Kior Labs

    $15

    Cut agent context without losing quality: per-section budgets, techniques and a measured before/after.

    1
    0

    Agent Failure Postmortem

    by Kior Labs

    $12

    Turn one bad agent run into a blameless postmortem with a root cause and a regression test.

    1
    0

    Model Migration Planner

    by Kior Labs

    $15

    Move a workload to another model with a parity matrix, cost and latency projections, and a staged rollout you can abort.

    1
    0

    Tool Schema Designer

    by Kior Labs

    $15

    Repair tool schemas so models pick the right tool and fill it correctly, proven with a before/after routing test.

    1
    0

    RAG Diagnostics

    by Kior Labs

    $15

    Separate query, retrieval and generation failures with evidence, then fix the layer that is actually broken.

    1
    0

    Prompt Injection Red Team

    by Kior Labs

    $19

    Build an adversarial suite for an agent, measure attack success by class, and map the controls that actually stop it.

    1
    0

    Agent Cost Profiler

    by Kior Labs

    $19

    Find where an agent's token spend actually goes, separate waste from necessary cost, and cut it without breaking quality.

    1
    0

    Tracegrade

    by Kior Labs

    $19

    Turn production agent traces into a calibrated eval suite: failure clusters, ready assertions, and a judge checked against humans.

    1
    0

    MCP Server Auditor

    by Kior Labs

    $19

    A severity-ranked security review for any MCP server, before you ship it or connect it.

    1
    0

    Onboarding Pack Builder

    by Kior Labs

    $12

    Build the first-week pack for a new client: welcome email, kickoff agenda, intake form, access checklist, ways of working and a 30-day plan.

    1
    0

    Proposal & Scope Builder

    by Kior Labs

    $12

    Turn discovery notes into a client-ready proposal with scope, timeline, three pricing options and objection handling.

    1
    0

    Reply First Cold Outreach

    by Kior Labs

    $9

    Write a four-email plus LinkedIn cold sequence that gets replies, with subject lines and answers to common objections.

    1
    0

    SEO Brief Builder

    by Kior Labs

    $9.99

    Turn a keyword into a writer-ready brief with search intent, outline, meta copy and a quality checklist.

    1
    0

    Instagram Content Manager

    by Kior Labs

    $9

    Run an Instagram professional account from chat: performance reports, comment replies, competitor research, publishing and DM replies.

    1
    0