# Agent Skills

Copyable AgentClash skills for coding agents, exposed as docs pages and markdown exports.

Source: https://agentclash.dev/docs/agent-skills
Markdown export: https://agentclash.dev/docs-md/agent-skills

AgentClash ships portable Agent Skills for coding agents that understand the `SKILL.md` folder format. The canonical source lives in `web/content/agent-skills/.../SKILL.md`; docs pages and markdown exports are generated from that source.

## Install Targets

- Codex: copy a skill folder into `.agents/skills/<skill>/SKILL.md` or point Codex at the markdown export.
- Claude Code: copy a skill folder into `.claude/skills/<skill>/SKILL.md`; if the repo already uses `AGENTS.md`, add a `CLAUDE.md` import for `@AGENTS.md`.
- Cursor: use these pages as agent-requested rule references, or add thin `.cursor/rules/*.mdc` stubs that link to the matching markdown export.
- Generic agents: fetch `/llms.txt`, `/llms-full.txt`, or the individual `/docs-md/agent-skills/<skill>` pages.

## Core Operating Skills

- [agentclash-ci-release-gate](https://agentclash.dev/docs-md/agent-skills/agentclash-ci-release-gate) - ci: Use when comparing AgentClash candidate runs against baselines, evaluating release gates, or adding CI/CD checks that fail on regressions.
- [agentclash-cli-setup](https://agentclash.dev/docs-md/agent-skills/agentclash-cli-setup) - setup: Use when configuring the AgentClash CLI, authenticating, selecting a workspace, linking a project, or diagnosing CLI access against production or local backends.
- [agentclash-eval-runner](https://agentclash.dev/docs-md/agent-skills/agentclash-eval-runner) - running: Use when starting, following, or reporting AgentClash runs and evals with the CLI, especially run create, eval start, live events, rankings, and suite-only scopes.
- [agentclash-regression-flywheel](https://agentclash.dev/docs-md/agent-skills/agentclash-regression-flywheel) - regression: Use when inspecting AgentClash run failures, promoting useful failures into regression suites, editing regression cases, and verifying suite-only reruns.
- [agentclash-scorecard-reader](https://agentclash.dev/docs-md/agent-skills/agentclash-scorecard-reader) - reviewing: Use when interpreting AgentClash rankings, scorecards, replay timelines, artifacts, and evidence into engineering findings and next actions.

## Challenge Pack Skills

Focused skills for planning, authoring, scoring, judging, tooling, artifacts, validation, and publishing challenge packs.

- [agentclash-challenge-pack-artifacts](https://agentclash.dev/docs-md/agent-skills/challenge-pack-skills/agentclash-challenge-pack-artifacts) - challenge-pack-artifacts: Use when specifying AgentClash challenge pack artifacts, file outputs, evidence capture, upload/download expectations, and scorecard artifact references.
- [agentclash-challenge-pack-input-sets](https://agentclash.dev/docs-md/agent-skills/challenge-pack-skills/agentclash-challenge-pack-input-sets) - challenge-pack-inputs: Use when designing AgentClash challenge pack cases and input sets for smoke, full benchmark, regression, edge-case, or CI suite-only coverage.
- [agentclash-challenge-pack-llm-judges](https://agentclash.dev/docs-md/agent-skills/challenge-pack-skills/agentclash-challenge-pack-llm-judges) - challenge-pack-judging: Use when configuring AgentClash LLM-as-judge scoring, judge prompts, rubrics, dimensions, evidence inputs, abstention behavior, and judge result interpretation.
- [agentclash-challenge-pack-planner](https://agentclash.dev/docs-md/agent-skills/challenge-pack-skills/agentclash-challenge-pack-planner) - challenge-pack-planning: Use when turning a vague AgentClash evaluation idea into a challenge pack plan with task boundaries, target agents, input coverage, scoring strategy, tools, artifacts, and publish criteria.
- [agentclash-challenge-pack-scoring-validators](https://agentclash.dev/docs-md/agent-skills/challenge-pack-skills/agentclash-challenge-pack-scoring-validators) - challenge-pack-scoring: Use when defining deterministic AgentClash scoring validators, score dimensions, evidence sources, pass/fail rules, numeric metrics, and validator failure messages.
- [agentclash-challenge-pack-tools-sandbox](https://agentclash.dev/docs-md/agent-skills/challenge-pack-skills/agentclash-challenge-pack-tools-sandbox) - challenge-pack-tools: Use when defining AgentClash challenge pack tool access, sandbox runtime needs, filesystem expectations, network policy, command execution, and secret references.
- [agentclash-challenge-pack-validation-publish](https://agentclash.dev/docs-md/agent-skills/challenge-pack-skills/agentclash-challenge-pack-validation-publish) - challenge-pack-publication: Use when validating AgentClash challenge packs, fixing schema errors, publishing packs, recording returned IDs, and preparing follow-up run commands.
- [agentclash-challenge-pack-yaml-author](https://agentclash.dev/docs-md/agent-skills/challenge-pack-skills/agentclash-challenge-pack-yaml-author) - challenge-pack-authoring: Use when writing or editing AgentClash challenge pack YAML, including tasks, cases, input sets, scoring blocks, tools, sandbox settings, assets, and metadata.

## Agent Build Skills

Focused skills for agent build specs, deployments, runtime resources, provider accounts, model aliases, and secrets.

- [agentclash-agent-build-author](https://agentclash.dev/docs-md/agent-skills/agent-build-skills/agentclash-agent-build-author) - agent-builds: Use when creating or editing AgentClash agent build specifications, including agent identity, runnable configuration, prompts, model choices, runtime expectations, and version notes.
- [agentclash-agent-deployment-setup](https://agentclash.dev/docs-md/agent-skills/agent-build-skills/agentclash-agent-deployment-setup) - agent-deployments: Use when creating, selecting, or diagnosing AgentClash agent deployments for runs, including build selection, deployment IDs, workspace context, and run compatibility.
- [agentclash-runtime-resources-setup](https://agentclash.dev/docs-md/agent-skills/agent-build-skills/agentclash-runtime-resources-setup) - runtime-resources: Use when configuring AgentClash provider accounts, model aliases, runtime profiles, workspace secrets, tools, and other resources required before agent deployments or runs.

## Canonical Layout

```text
web/content/agent-skills/<category-or-skill>/.../SKILL.md
```

Each skill keeps the main instructions focused and uses trigger-oriented frontmatter so agents can discover the right workflow before loading the full body.