1.3K skills · sorted by relevance
Builds and improves C/C++ and Rust fuzzing harnesses, the entry points that feed generated test data into code. Helps structure inputs, reach more code paths, and address crashes caused by inconsistent test behavior.
Delegate code review, development, and research from OpenCode to DeepSeek Harness. The skill checks service readiness, tracks each task, and returns reports or proposed code changes for the main agent to review.
Deliver TeamHarness messages to the correct room, channel, or session using recorded reply routes. It covers task handoffs and requester reports, while defining when to reply directly or suppress acknowledgements that could cause message loops.
Scaffold your own focused AI agent harness — pick host (Claude Code, Codex, pi.dev, Hermes), template, agents, skills, and ship a npm-publishable harness with its own npx CLI. Use when a user asks to "create my own agent harness", "scaffold a harness", "make a custom Claude Code plugin like ruflo", or "build a vertical AI assistant for X".
The English summary is being prepared. Showing the original description.
Initialize a Harness Engineering framework in the current project. Use when user says 'harness', 'init harness', 'initialize framework', 'setup harness engineering', '/harness', or wants to set up a Plan-Build-Verify development workflow with specialized agents (planner, generator, evaluator). Creates CLAUDE.md, agent definitions, command templates, hooks, and documentation structure for autonomous AI-driven development.
The English summary is being prepared. Showing the original description.
Run one iteration of VL-Harness evolution — evolve video-memory-harness code for long-video MCQ. Called by meta_harness.py or interactively via /vl-harness.
The English summary is being prepared. Showing the original description.
LAM ハーネスの規範層をプロジェクトへ敷く初期化スキル。 plugin コンポーネントとして配れない層（.claude/rules/ と docs/internal/ と .claude/scripts/ = managed、 および CLAUDE.md 等の starter）をファイルとして配置し、.claude/harness.json に記録する。 ランタイム（Python）が無い環境では完了を拒む。 Layer 1（.claude/settings.json の permissions）は敷かず、手作業の手順として提示する。 Use when the user installs lam-harness into a project, or runs /lam-harness:init.
The English summary is being prepared. Showing the original description.
Seed minimal agent harness v0 — manifest, eval checks stub, governance. AUTO-INVOKED after project-setup or retroactive-project-setup when docs/harness/manifest.json is missing. Also triggers on: generate harness, scaffold agents, agent bootstrap, first time agents in this repo, new project agent setup, set up agent harness, agent onboarding files, missing agent configuration, agent instructions setup, make agents read project rules, agent reliability setup, agents not configured. Pairs with project-setup. Evolution is harness-evolution.
The English summary is being prepared. Showing the original description.
Improve agent reliability over time — diagnose why agents fail and fix the setup. Triggers on: agent keeps failing, same mistake again, agent not improving, make agent smarter, agent quality plateau, agents ignore skills, agent skips tests, fix agent behavior, agent unreliable, improve agent setup, self-improving harness, agents worse over time, tune agent instructions, agent going in circles, agent ignores AGENTS.md, repeated agent errors. Requires harness v0 and eval harness. AUTO-ROUTED from harness-engineering on symptoms. Not first setup — harness-generation first.
The English summary is being prepared. Showing the original description.
Produce or apply an approved report-first proposal for workflow, ROSE, skill, command, subagent, memory, install, or harness-doc changes; use after harness-issue-triage localizes a harness problem or when the user explicitly requests harness maintenance, and do not edit core harness files without explicit human approval.
The English summary is being prepared. Showing the original description.
Improve an AI agent's harness, the software that organizes its work, while keeping the model fixed. Test changes in a sandbox, measure their results, and retain variants that pass tests and demonstrate improvement.
Run three static audits covering architecture alignment, threats, and MCP server policies, permissions, and dependencies. Store timestamped results, track changes across runs, and fail scheduled CI jobs when findings reach a chosen severity.
Compare a saved repository audit with a fresh audit in one command. Receive a structured report showing structural similarity, with an alert and exit code when similarity falls below your chosen threshold.
Design the operating layer around a coding agent so it can read and edit code, run checks, and correct errors. Define completion criteria, permission boundaries, feedback, and recovery methods, and assess which tasks suit autonomous execution.
Review agent work histories to identify recurring failures, repeated discoveries, and stalled tasks. Improve the prompts, specialist agents, skills, tools, and memory that guide future work, then submit those changes separately for review.
Measure which code fuzzing reaches as it tries many generated inputs. Use coverage reports to find unreachable areas, compare progress, and guide improvements to test harnesses, starting inputs, or dictionaries of useful input values.
Removes hosted demo restrictions from an Open Harness fork, including session and message caps and deletion blocks. Cleans up related helpers and tests while preserving unrelated authentication, session ownership checks, and sandbox behavior.
Manage an AI team's project plans and recorded progress, including task dependencies and repeated improvement cycles. Track accepted results, identify work ready to start, pause or resume projects, and prepare status reports for requesters.
Research one agent harness's release (docs, source, runtime) and fill its capability cells in scripts/harness_capabilities.py with cited evidence. Use after a harness version bump, when just harness-probe reports re-research, or when capability cells read unknown.
The English summary is being prepared. Showing the original description.
Audit one or all supported agent harnesses (claude, codex, opencode, pi, omp, antigravity, cursor, grok) for config efficiency, hook overhead, permission friction, plugin and MCP cost, skill metadata portability, dead config, and measured session friction. Use when invoked as `$optimize-harness [harness ...] [focus]`, or when the user asks to optimize or compare agent harness configuration.
The English summary is being prepared. Showing the original description.
Change the agent harness itself (AOS, AO or CBS hooks, gates, memory, permissions, delegation, plugins, bootstrap) the safe way: look up the matching harness pattern, design against its gotchas, build with /startcycle and a live trail, check every harness, open a PR after GO. Use for "change a hook", "fix the go-gate", "harness work", "plugin change".
The English summary is being prepared. Showing the original description.
Evaluate large language models on shared tests of knowledge, reasoning, and code generation with lm-evaluation-harness. Save scores and individual predictions, compare models in tables, and track performance across saved stages of model training.
Compare two JSON records describing agent setups and their scores. Receive an overall similarity score with component details to help assess reuse, compare template candidates, identify overlapping work, or check how much a setup has changed.
Coordinate project delivery by routing requests to eight specialist skills or running a verified delivery workflow. Use live Jira data for progress analysis and completion forecasts, with recorded evidence and checks before tasks are closed.