Skip to content
Agentmart
Submit a tool

agentclash-challenge-pack-artifacts

Use when specifying AgentClash challenge pack assets, artifact references, produced file captures, evidence references, artifact upload/download expectations…

Skill by agentclash

IndexedMIT★ 36
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/agentclash-agentclash-challenge-pack-artifacts

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Use when specifying AgentClash challenge pack assets, artifact references, produced file captures, evidence references, artifact upload/download expectations, and review-only evidence.

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/agentclash-challenge-pack-artifacts

What's inside

Skill name
agentclash-challenge-pack-artifacts
Description
Use when specifying AgentClash challenge pack assets, artifact references, produced file captures, evidence references, artifact upload/download expectations, and review-only evidence.
License
MIT
Metadata
agentclash.role: challenge-pack-artifacts · agentclash.version: 1 · agentclash.requires_cli: true
Instructions
320 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# AgentClash Challenge Pack Artifacts

## Purpose
Make challenge pack files and evidence explicit without confusing three different surfaces:

- source assets declared in challenge-pack YAML
- case artifact references exposed to scoring evidence
- files produced by the agent and captured after execution

Use this skill when a coding agent needs exact artifact fields and evidence references without reading the AgentClash source repo.

## Use When
- A pack includes fixture files, expected reports, images, logs, datasets, or other stored assets.
- Cases need `inputs[].artifact_key`, `expectations[].artifact_key`, `artifact_refs`, or case `artifacts`.
- Scoring needs `artifact...` or `file:...` evidence references.
- Native execution should capture files from the sandbox through `post_execution_checks`.
- A reviewer needs to inspect artifacts after a run.

## Do Not Use When
- The pack only needs plain text final-output scoring; use `agentclash-challenge-pack-scoring-validators`.
- The task is selecting input sets or regression suites; use `agentclash-challenge-pack-input-sets` or `agentclash-regression-flywheel`.
- The task is configuring tools, sandbox network, or package access; use `agentclash-challenge-pack-tools-sandbox`.

## Environment
Use hosted production for CLI examples unless the user intentionally targets a local or self-hosted backend.

```bash
export AGENTCLASH_API_URL="https://api.agentclash.dev"
```

`agentclash challenge-pack validate` is a hosted API call: authenticate first and select a workspace with `agentclash link`, `--workspace`, `AGENTCLASH_WORKSPACE`, or local `.agentclash.yaml`. Use `agentclash-cli-setup` if the machine is not already logged in.

## Validation Commands
Validate after changing any asset, artifact reference, input artifact key, expectation artifact key, or file evidence target.

```bash
agentclash challenge-pack validate path/to/pack.yaml
agentclash challenge-pack validate path/to/pack.yaml --json
```

Human output prints `Challenge pack is valid` or `Challenge pack has errors`. Use `--json` for structured `valid` and `errors` fields.

## Asset Declaration Shape
Challenge-pack assets use the same field shape at `version.assets`, `challenges[].assets`, and `input_sets[].cases[].assets`.

```yaml
version:
  assets:
    - key: policy_pdf
      kind: document
      path: assets/policy.pdf
      media_type: application/pdf
      artifact_id: 00000000-0000-0000-0000-000000000000

challenges:
  - key: summarize-policy
    title: Summarize Policy
    category: document
    difficulty: medium
    assets:
      - key: challenge_notes
        path: assets/challenge-notes.md

input_sets:
  - key: policy-smoke
    name: Policy Smoke
    cases:
      - challenge_key: summarize-policy
        case_key: summary-basic
        assets:
          - key: case_notes
            path: assets/cases/summary-basic-notes.md
```

Source-backed fields:

- `key`: required and unique inside that one `assets` list.
- `path`: required, even when `artifact_id` is present.
- `kind`: optional string.
- `media_type`: optional string.
- `artifact_id`: optional UUID for an already stored artifact.

The current validator does not enforce enums for `kind` or `media_type`; use clear, conventional values and validate the pack.

## Version Assets Versus Local Assets
Only `version.assets` form the reference pool for artifact references.

These fields must reference a declared `version.assets[].key`:

- `challenges[].artifact_refs[].key`
- `input_sets[].cases[].artifacts[].key`
- `input_sets[].cases[].inputs[].artifact_key`
- `input_sets[].cases[].expectations[].artifact_key`
- `input_sets[].cases[].expectations[].source: artifact:<key>`

Challenge-level and case-level `assets` are validated for `key` and `path`, but they are not accepted as targets for `artifact_refs`, `artifacts`, `artifact_key`, or `source: artifact:...`. If a file needs to be referenced by scoring or case evidence, declare it in `version.assets`.

## Artifact References
Use `artifact_refs` on a challenge to say which version assets matter to that challenge. Use case `artifacts` to expose version assets as artifact evidence for a case.

```yaml
version:
  assets:
    - key: policy_pdf
      path: assets/policy.pdf
      media_type: application/pdf
    - key: expected_summary
      path: assets/expected-summary.json
      media_type: application/json

challenges:
  - key: summarize-policy
    title: Summarize Policy
    category: document
    difficulty: medium
    artifact_refs:
      - key: policy_pdf

input_sets:

From agentclash/agentclash, MIT.

More from agentclash/agentclash

Signals

Stars
36
Forks
3
Open issues
61
Last commit (this folder)
Jun 24, 2026 (4 months ago)
Last release
Aug 15, 2026 (2 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from agentclash

Cite this page

agentclash-challenge-pack-artifacts skill. Agent Mart. https://agentmart.dev/skills/agentclash-agentclash-challenge-pack-artifacts (last updated 2026-10-24)