OpenAgentSkill Registry Manifest
Skill: weak-agent-test
Slug: kklimuk-weak-agent-test
Category: coding-agents
Description: Run the weak-agent adversarial test harness against docx-cli. Spawns weak exercise agents (Haiku by default, Sonnet to probe, or a local agent harness's pre-produced runs) to perform real document tasks over six scenarios — five editing (MNDA form-fill + font fidelity, invoice table-edit/restructure + logo replace, résumé styling, contract redlining + commenting, contract finalize via accept/reject + comment reply/resolve) and one authoring (T. S. Eliot poetry journal: multi-column, verse, footnotes, links, figure) — renders every result with Word, has opus judge them against ground-truth rubrics, measures each exercise's tool economy, token cost, wall-clock, and correctness (from transcripts for Claude, the exercise.json ledger for the local harness), and synthesizes a prioritized ergonomics report. Use when the user says 'adversarial review', 'test docx-cli with weak agents', 'run the haiku harness', 'weak agent test', or wants to re-run yesterday's adversarial process.

Agent fit:
- Decision: 69/100 Prototype first
- Primary fit: Document processing
- Role: Fallback candidate

Supply profile:
- Track: Coding and developer agents
- Scenario: GitHub automation
- Applicable agents: Claude Code, CLI, Codex, Cursor
- Maintenance: 3d since push
- Risk: Needs review

Trust:
- Trust score: 66/100 Manual review
- Audit: 75/100 Needs review

Attribution:
- Status: Registry indexed
- Source: github candidate review
- Creator: kklimuk
- Claim URL: https://www.openagentskill.com/skills/kklimuk-weak-agent-test#claim-this-skill

Install:
npx skills add kklimuk/docx-cli --skill weak-agent-test

URLs:
- Web: https://www.openagentskill.com/skills/kklimuk-weak-agent-test
- API: https://www.openagentskill.com/api/agent/skills/kklimuk-weak-agent-test
- Install API: https://www.openagentskill.com/api/skills/kklimuk-weak-agent-test/install
- Repository: https://github.com/kklimuk/docx-cli/tree/main/.claude/skills/weak-agent-test