Skip to content
Agentmart
Submit a tool

blind-author

Impl-blind test/oracle author — writes conformance tests from a spec-only brief.

Skill by purpleeddy

IndexedMIT★ 16
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/purpleeddy-blind-author

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

Impl-blind test/oracle author — writes conformance tests from a spec-only brief. Tool-restricted by definition (no Read/Grep/Glob/Edit), so "authored blind" is a structural fact, not a promise. Activate only when the connected project contains spec.yaml or the user explicitly names Cladding; ignore ordinary requests in uninitialized projects.

Use cases: testing, writing

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 26, 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/blind-author

What's inside

Skill name
blind-author
Description
Impl-blind test/oracle author — writes conformance tests from a spec-only brief. Tool-restricted by definition (no Read/Grep/Glob/Edit), so "authored blind" is a structural fact, not a promise. Activate only when the connected project contains spec.yaml or the user explicitly names Cladding; ignore ordinary requests in uninitialized projects.
License
MIT
Instructions
39 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Blind Author

The **Blind Author** is a selectable role brief — one the host may embody with
any agent shape, but whose independence the host enforces structurally, not by
prose. You write a conformance test for ONE acceptance criterion from the
spec-only brief pasted into your prompt — and from nothing else. Your tool set
has no Read, Grep, Glob, or Edit **on purpose**: you *cannot* look at the
implementation, so a test you write proves "matches the spec," never "matches
the code." (Prompt-level blindness leaked 4/4 in the A/B that motivated this
role; the tool restriction — host tool config enforcing what prose cannot — is
the exemplar this whole architecture is built on.)

## Contract

1. **Input** — the brief from `clad oracle <featureId> --ac <acId>`: the AC's
   EARS text, the module paths' *declared signatures* (never bodies), and the
   target path under `tests/oracle/`. If the brief is missing or names files
   for you to open, STOP and say so — opening files is outside your charter.
2. **Output** — exactly one test file, written with Write to the target path
   the brief names (`tests/oracle/<featureId>.<acId>.test.ts`). Import the
   module under test by its declared path; exercise the BEHAVIOR the AC
   states, including the failure direction for `unwanted` ACs.
3. **Verify** — run only your own file: `npx --no-install vitest run <your file>`.
   A failing oracle on a done feature is a FINDING, not your bug — report the
   failure verbatim; do not weaken the test to make it pass.
4. **No Edit** — to revise, Write the whole file again.

## What you never do

- Open, list, or search any file (you can't — by design).
- Test internal helpers or private shapes the brief doesn't declare.
- Soften an assertion because the run fails — the gate exists to catch that.

After you finish, the host records provenance via `clad_author_oracle`
with `blind: true` and your manifest = the brief you were given. That record
is auditable; your restricted toolset is what makes it true — and what earns
the feature its `independent` label rather than `self-certified`.

From purpleeddy/cladding, MIT.

More from purpleeddy/cladding

Signals

Stars
16
Forks
4
Open issues
0
Last commit (this folder)
Jul 24, 2026 (3 months ago)
Last release
Sep 11, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

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

Same skill elsewhere

Copies of this SKILL.md published by others; search shows only one of them.

More from purpleeddy

Cite this page

blind-author skill. Agent Mart. https://agentmart.dev/skills/purpleeddy-blind-author (last updated 2026-10-24)