Bridge between the inference-perf-bench / ai-bench output bundle and the profile-and-optimize perf-baseline registry.
Canonical inference perf-bench skill (formal name. The colloquial alias is `ai-bench` - identical behaviour).
Build a multi-page benchmark report PDF (scatter panels + per-concurrency heatmap tables) from `vllm bench sweep serve_workload` and/or AIPerf outputs, in the GLM-5.1 reference…
Closed-loop speculative-decoding-as-a-service orchestrator -- a self-hosted analog of Fireworks FireOptimizer's adaptive speculative execution.
Tune a speculative-decoding DRAFT head's TRAINING hyperparameters (global batch, learning rate, accumulation, warmup) for a target LLM, optimizing the TRUE serving in-engine…
Search a vLLM serving model's config space for its best inference performance: a `perftunereport campaign_run` matrix sweep over concurrency x max_num_batched_tokens x…
Process audiobooks from the inbox: transcribe to text and organize audio for voice training. Part of Horus's learning pipeline. — from grahama1970/agent-skills
Manage book library via Readarr, search for books, and monitor downloads. Handles service health checks and API interactions. Part of Horus's learning pipeline.
Scan one or more external-content items for prompt injection attempts and return a structured verdict.
Insert urgent work as decimal phase (e.g., 72.1) between existing phases — from NafisRayan/100x-Agent-Toolkit
Use when the user asks about patterns, insights, or behavioral analysis — e.g. 'what patterns do you see', 'insights', 'how am I doing', 'behavioral analysis
Analyze websites for design inspiration, extracting colors, typography, layouts, and patterns. Use when you have specific URLs to analyze for a design project.
Install skills, agents, and teams from agent-almanac into any supported agentic framework using the CLI.
GLAW Insurance Coverage & Bad-Faith seat — first-party policyholder coverage disputes (property/CGL/auto/D&O), the claim → proof-of-loss → appraisal → litigation path,…
Expert-level insurance systems, underwriting, claims processing, actuarial analysis, risk assessment, and insurtech solutions
Query, inspect, or refresh codebase intelligence files in .planning/intel/ — from rikitrader/glaw
Query, inspect, or refresh codebase intelligence files in .planning/intel/ — from majiayu000/claude-skill-registry
GLAW Strategic Intelligence Cell — Geopolitical / Country-Risk Intelligence. Assesses jurisdiction and country risk for cross-border matters: political analysis, economic…
Automated intercompany transaction identification and elimination skill for consolidated reporting
Master Symfony Dependency Injection with autowiring, #[Target] interface binding, decoration, and tagged services
GLAW International Tax computation & information-return seat — the COMPUTE counterpart to the flag-only /glaw-international.
Automatically routes tasks to external AI CLIs (Codex or Gemini) when more efficient. No manual commands needed - routing decisions are made automatically based on task type.
Conduct semi-structured interviews and moderate focus groups with rapport building, probing techniques, and group dynamics management
Generate competency-based and behavioral interview questions with legal compliance validation
Inventory management optimization skill with safety stock calculation, reorder point determination, and ABC analysis
View and manage calendar invitations - check pending invites, accept/decline meeting requests, create events
Visual design audit for iOS apps on real hardware. Connects to a real iPhone via the same StateServer as /ios-qa, screenshots every screen, evaluates against Apple HIG, DESIGN.md,…
Autonomous iOS bug fixer. Takes a bug found by /ios-qa, reads the source, writes the fix, rebuilds, redeploys, and verifies the fix on the real device.
Live-device iOS QA for SwiftUI apps. Connects to a real iPhone via USB CoreDevice IPv6 tunnel, reads Swift source to understand every screen, then runs a vision-driven agent loop:…
Regenerate the iOS debug bridge against the latest upstream gstack templates. Updates StateServer.swift, DebugOverlay.swift, Package.swift, and the typed @Observable state…
GLAW IP Counsel — intellectual-property seat covering trademark (clearance, Nice classes, USPTO TEAS, ITU vs use-based, office actions), patent (provisional vs utility, §101…
GLAW IRS Whistleblower seat (IRC §7623) — the tax analog to /glaw-sec-whistleblower. For a WHISTLEBLOWER: screens eligibility (specific & credible information, the §7623(b) $2M /…
Specialized skill for NVIDIA Isaac Sim photorealistic simulation and synthetic data generation
ISO 9001:2015 Quality Management System implementation skill with gap assessment and documentation templates
Regulatory compliance skill for ISO nanotechnology standards verification and documentation
Medical device standards compliance verification skill for ISO 13485, ISO 14971, IEC 62304, IEC 60601, and related standards
Comprehensive risk management skill implementing ISO 14971:2019 methodology for medical device risk analysis
Orchestrates issue creation with automatic review. Use when asked to "create and review issues", "create verified issues", or when you want issues automatically validated against…
Verifies Trellis issues against original requirements for completeness, correctness, and appropriate scope.
Use when an issue is too large for a single task - breaks into linked sub-issues with full documentation, ensuring manageable work units
Use for any development work - the master 13-step coding process that orchestrates all other skills, ensuring GitHub issue tracking, proper branching, TDD, code review, a — from…
Orchestrates issue implementation with automatic review and commits. Use when asked to "implement feature", "implement epic", "implement project", "execute feature", "execute…
Reviews code changes from a completed task implementation for correctness, completeness, and simplicity.
Use throughout all work - ensures GitHub issues are updated continuously as work happens, not batched at the end
Use before starting ANY work - hard gate ensuring a GitHub issue exists, creating one if needed through user questioning — from general/ai-tooling
Use when asked to evaluate issue size, decompose large issues, or audit backlog complexity.
Split complex issues into smaller, implementable sub-issues. Called automatically when ComplexityGate determines an issue needs splitting.
Analisa e classifica issues com detecção de duplicados. Use quando precisar gerenciar issues do GitHub/GitLab, classificar bugs, ou organizar backlog de tarefas.
Use when building Android UIs with Jetpack Compose, managing state with remember/mutableStateOf, or implementing declarative UI patterns.
Harness Engineering release manager — generates CHANGELOG from pm:OK tasks, bumps version, creates git tag, and writes release notes
Harness Engineering review orchestrator — manages pm:REVIEW → pm:OK flow with 4-perspective code review and user approval gate
Harness Engineering project initializer — validates environment, registers hooks, and prepares Plans.md workspace for the full Plan→Work→Review→Ship workflow
Dashboard lifecycle management — setup, start, stop, status. Invoked by /jira dashboard command.
Interactive setup wizard for Jira MCP server registration. Guides through prerequisites check, credential collection, MCP server registration, and connection validation.
Expert skill for just-in-time compilation including profiling, tiered compilation, and deoptimization
Help users identify, understand, and resolve conflicts in jj repositories. Use when user mentions 'conflict', 'resolve conflicts', 'merge conflict', 'conflicted commits', '2-sided…
Write a description for the current `jj` commit.
Resolve conflicts in the current `jj` commit.
Daily routines for a corporate software engineering job. Start mode triages the inbound review queue, your own open PRs, and the issue tracker's plan for today.
Analyze and evaluate jobs for internal equity and leveling using point-factor methods