agentsclimarketplace

Zero context validation

Skill whykusanagi/zero-context-validation/skills/zero-context-validation

Use when you need to validate documentation completeness and cannot objectively test it yourself because you have implementation contextFrom its SKILL.md

Install
npx -y skills add whykusanagi/zero-context-validation --skill zero-context-validation

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

3.4 KB, 711 tokens by cl100k_base, as published. Nobody here has run it

Zero-Context Validation

Overview

Test documentation completeness by spawning blind sub-agents to attempt implementation. They expose blindspots you can't see because you have context.

You orchestrate, judge results, iterate. Blind agents test docs, report gaps.

When to Use

Use: Validating docs before publishing, testing API/setup guides, verifying docs after refactors.

Don't use: Code review, testing code functionality, proof-reading.

Quick Reference

SituationAction
Just wrote docsSpawn blind agent with implementation task
Agent reports gapsJudge if real → fix docs → re-test
Agent invents detailsStrengthen "no assumptions" → re-test
Agent succeeds cleanDocumentation ready ✅
Multiple iterationsNormal - iterate until clean success

The Iron Law

NO ASSUMPTIONS ALLOWED. Test agent uses ONLY documentation. Missing info = report gap, not guess.

Violating: Fills gaps → incomplete docs → wasted time.

Process

1. Prepare: Define implementation task for blind agent.

2. Spawn: Launch blind sub-agent using Task tool - ZERO context, ONLY docs, NO assumptions, REPORT gaps.

3. Judge: Succeeds clean → docs ready ✅ | Reports gaps → fix, re-test | Invents → strengthen rules, re-test

4. Iterate: Repeat until success. Multiple iterations normal.

Common Rationalizations (FORBIDDEN)

RationalizationWhy It Fails
"Docs approved by experts"Approval ≠ tested
"Use your best judgment"Assumptions hide gaps
"Common patterns apply"Document patterns
"Implementation successful" (but invented 80%)Invention ≠ validation
"Just a quick sanity check"Review misses gaps

Re-run with no-assumptions enforced.

Red Flags - STOP Validation

  • "Using common patterns" for undocumented details
  • Creating base classes not in docs
  • Inventing file structures/imports
  • "Assuming X based on Y"
  • Success but invented components
  • Instructions include "use best judgment"

Validation invalid. Restart with stricter rules.

Success Metrics

Good: Agent succeeds with zero assumptions OR reports gaps. Bad: Agent invents details. Goal: Find gaps before wasting developer time.

Common Mistakes

MistakeFix
"Just review, don't implement"Require implementation attempt
Including context in instructionsFresh agent, docs only
Allowing "reasonable assumptions"Forbid assumptions, require reports
Authority pressure ("approved by experts")Neutral instructions
Treating blocked agents as failureBlocked = found gaps

Impact

Without: Docs look complete → publish → blocked developers. With: Test docs → find gaps → fix → ship complete.

1 hour validation saves 2-4 hours confusion.

Example

Typical workflow: 3 iterations to find and fix gaps. See examples.md for detailed multi-iteration workflow.

Related Skills

  • superpowers:test-driven-development - Same principles, applied to docs
  • superpowers:writing-skills - Testing skills uses same validation

Technical Implementation

Uses the built-in Task tool to spawn blind sub-agents. No external dependencies required.

What ships with it: 2 files

12.2 KB alongside SKILL.md

Gives 0 of the 12 instructions most quality gates skills give in 711 tokens

Counted across 1,195 of the 2,094 authors here whose files we hold, read 2026-08-07

  • Read the output and check the exit codein 54 of 1195, across 14 files
  • Verify requirements using a line-by-line checklistin 53 of 1195, across 12 files
  • Identify the verification command proving the claimin 51 of 1195, across 12 files
  • Run the full verification commandin 50 of 1195, across 11 files
  • Verify output confirms the claimin 49 of 1195, across 12 files
  • Check version control diff after agent delegationin 46 of 1195, across 6 files
  • State claim with evidencein 44 of 1195, across 4 files
  • Run the test suitein 33 of 1195, across 26 files
  • Keep state in memory by defaultin 27 of 1195, across 6 files
  • Make prototype runnable with one commandin 26 of 1195, across 5 files
  • Produce a verification reportin 25 of 1195, across 14 files
  • Detect the package manager from lockfilesin 24 of 1195, across 5 files

Said here and by no other author read

  • Spawn blind sub-agents to attempt implementation
  • Give the test agent zero context
  • Allow the test agent to use only documentation
  • Define an implementation task for the blind agent
  • Report gaps instead of guessing missing info
  • Fix documentation if the agent reports gaps

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 326,512. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.