weak-agent-test SKILL.md skillA
weak-agent-test from kklimuk/docx-cli is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add kklimuk/docx-cli/weak-agent-test@git:20261009.47f0f3fPins git:20261009.47f0f3f in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- kklimuk/docx-cli
- Path
.claude/skills/weak-agent-test/SKILL.md- Versions recorded
- 5
- Latest version
- git:20261009.47f0f3f, committed Oct 9, 2026
- First version recorded
- Jul 14, 2026
- Size
- 26,913 bytes
- Repository stars
- 227
- License
- MIT
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…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Adversarial review — weak-agent harness for docx-cli This harness answers one question: **can weak agents actually use docx-cli to get real work done, and what should we fix first?** It runs the `weak-agent-test` workflow (`.claude/workflows/weak-agent-test.js`), which fans out one weak exercise agent per scenario (Haiku by default — swappable to Sonnet via `args.model`), renders every output with Microsoft Word, grades each against ground-truth criteria with an **opus** judge, and has **opus** synthesize a prioritized improvement report. Exercise agents do NOT self-report tool counts — every tool-economy and token number is **measured** after the run (agents under-count their own calls ~2×, so self-reports were dropped): from the agent transcripts for the Claude arms, from each scenario's `exercise.json` ledger for the local arm. Both roll up into the same Run-metrics table (tokens, wall-clock, tool split, correctness) via `exercise-metrics.ts`. The test corpus is **bundled with this skill** under `scenarios/`, one folder per scenario, named after its key (`scenarios/mnda/`, `scenarios/invoice/`, …). Each …
Read the whole file at its exact version.
How to install
mdr add kklimuk/docx-cli/weak-agent-test@sha256:7136e184c44f5561The line at the top of this page pins the label git:20261009.47f0f3f, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_igndzaencaidfado)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Jul 14, 2026 and Oct 9, 2026, about one every 22 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261009.47f0f3f latest | 2026-10-09 | 47f0f3f | 26,913 B | A | view · diff |
| git:20260718.ecfa684 | 2026-07-18 | ecfa684 | 24,473 B | A | view · diff |
| git:20260714.16fa2a2 | 2026-07-14 | 16fa2a2 | 22,650 B | A | view · diff |
| git:20260714.24c3139 | 2026-07-14 | 24c3139 | 22,117 B | A | view · diff |
| git:20260714.16409a1 | 2026-07-14 | 16409a1 | 21,467 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (26913 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
kklimuk/docx-cli · 227 stars · license MIT · pushed 2026-10-17 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_igndzaencaidfado GET https://markdownregistry.com/api/v1/resolve?ref=kklimuk/docx-cli/weak-agent-test GET https://markdownregistry.com/api/v1/blob/7136e184c44f5561aa3cf835d5f4f7029663dad00efd27104487ab52f26ae6ea
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.