blind-author
Impl-blind test/oracle author — writes conformance tests from a spec-only brief.
Skill by purpleeddy
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.
About
Use cases: testing, writing
Reviews
Write a reviewNo 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
- 0.600score
reviewer
purpleeddy
Philosophical guardrails enforcer — independently audits code, tests, and spec for layered-integrity, Why>What, error-as-data, and the related Ironclad…
SkillBFreshness: B★ 16Claude Code +9 - 0.600score
orchestrator
purpleeddy
Cycle-contract coordinator for a cladding-managed project — declares the outcome conditions each feature must satisfy (spec-first, independent verification…
SkillBFreshness: B★ 16Claude Code +9 - 0.597score
planner
purpleeddy
SSoT custodian — keeps spec.yaml structurally clean.
SkillBFreshness: B★ 16Claude Code +9 - 0.597score
developer
purpleeddy
Implementer — writes production code, tests, and migrations.
SkillBFreshness: B★ 16Claude Code +9 - 0.597score
observability
purpleeddy
Log and metrics analyst — reads .cladding/audit.log.jsonl, perf/baseline.json, and drift reports; surfaces patterns the human can act on.
SkillBFreshness: B★ 16Claude Code +9 - 0.596score
check
purpleeddy
Run every Iron Law stage and the drift detector suite.
SkillBFreshness: B★ 16Claude Code +9 - 0.596score
sync
purpleeddy
Validate the active spec.yaml against the Ironclad schema and refresh the inventory.
SkillBFreshness: B★ 16Claude Code +9 - 0.596score
checkpoint
purpleeddy
Record a feature checkpoint event pinning the current git HEAD plus a spec digest, so a later rollback can restore the exact pre-change state.
SkillBFreshness: B★ 16Claude Code +9 - 0.596score
changelog
purpleeddy
Render release notes / a changelog from the cladding spec.
SkillBFreshness: B★ 16Claude Code +9 - 0.596score
oracle
purpleeddy
Author an IMPL-BLIND spec-conformance oracle for an acceptance criterion the policy worklist (`clad oracle --required`) demands — an empty worklist means…
SkillBFreshness: B★ 16Claude Code +9 - 0.596score
rollback
purpleeddy
Record a rollback event and print the maintainer-runnable git command for the most recent checkpoint of a feature.
SkillBFreshness: B★ 16Claude Code +9 - 0.596score
doctor
purpleeddy
Diagnose Cladding runtime health — Claude Code hook liveness and version, CI package pinning, lifecycle governance, and sentinel-miss frequency by phase ×…
SkillBFreshness: B★ 16Claude Code +9
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
- Repository
- github.com/purpleeddy/cladding
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Same skill elsewhere
Copies of this SKILL.md published by others; search shows only one of them.
More from purpleeddy
- 0.600score
orchestrator
purpleeddy
Cycle-contract coordinator for a cladding-managed project — declares the outcome conditions each feature must satisfy (spec-first, independent verification…
SkillBFreshness: B★ 16Claude Code +9 - 0.600score
reviewer
purpleeddy
Philosophical guardrails enforcer — independently audits code, tests, and spec for layered-integrity, Why>What, error-as-data, and the related Ironclad…
SkillBFreshness: B★ 16Claude Code +9 - 0.597score
observability
purpleeddy
Log and metrics analyst — reads .cladding/audit.log.jsonl, perf/baseline.json, and drift reports; surfaces patterns the human can act on.
SkillBFreshness: B★ 16Claude Code +9 - 0.597score
developer
purpleeddy
Implementer — writes production code, tests, and migrations.
SkillBFreshness: B★ 16Claude Code +9 - 0.597score
planner
purpleeddy
SSoT custodian — keeps spec.yaml structurally clean.
SkillBFreshness: B★ 16Claude Code +9 - 0.596score
checkpoint
purpleeddy
Record a feature checkpoint event pinning the current git HEAD plus a spec digest, so a later rollback can restore the exact pre-change state.
SkillBFreshness: B★ 16Claude Code +9
Cite this page
blind-author skill. Agent Mart. https://agentmart.dev/skills/purpleeddy-blind-author (last updated 2026-10-24)