Validation engine

Skill Razaib-khan/ForgeWeave/src/forgeweave/templates/gemini/.gemini/skills/validation-engine

Checks outputs from other skills for consistency, correctness, and adherence to AGENTS.md rulesFrom its SKILL.md

Install

npx -y skills add Razaib-khan/ForgeWeave --skill validation-engine

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

1 stars1 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

2.5 KB, 495 tokens by cl100k_base, as published. Nobody here has run it

Validation Engine

Purpose

Systematically inspect outputs from any skill or agent for correctness, consistency, completeness, and compliance with project rules defined in AGENTS.md. Acts as a quality gate before outputs are presented to the user or used by downstream skills.

When to Use

After any skill produces output that needs quality assurance
Before presenting research results to the user
When cross-checking claims across multiple sources
After code generation, before presenting the code

When Not to Use

The output is trivial and doesn't need validation
The user is iterating quickly and doesn't want validation overhead
The output is an intermediate step that will be further processed

Inputs

Input	Type	Required	Description
`output`	string	Yes	The content to validate
`type`	enum	Yes	research, code, documentation, plan
`rules`	array	No	Specific rules to enforce (defaults from AGENTS.md)

Expected Outputs

Output	Description
Validation report	Pass/fail per rule, with details
Issues found	List of problems with severity and location
Suggestions	How to fix each issue

Exact Workflow Steps

Load validation rules from AGENTS.md and the specific skill's requirements
For research: check every claim has a source URL, flag contradictions, check no blog sources
For code: check syntax, check against project conventions, verify tests pass
For documentation: check completeness, accuracy, clarity
For plans: check steps are ordered, dependencies identified, risks documented
Compile validation report with pass/fail per rule

Required Checks

All required fields are present in the output
No contradictions across the output
Output follows applicable rules from AGENTS.md
All claims are traceable to sources

Failure Modes

Failure Condition	Response
Validation rules are ambiguous	Ask for clarification
Output fails critical rules	Reject and report specific failures
Output fails minor rules	Accept with warnings

References

Reference	Path
AGENTS.md	`./AGENTS.md`
Internal validator component	Used by the deep-research skill pipeline

What ships with it: 2 files

3.2 KB alongside SKILL.md, 1 of them executable

references/

validation-rules.md889 B

scripts/

check_claims.pyruns2.3 KB

Gives 0 of the 12 instructions most quality gates skills give in 495 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

Load validation rules from AGENTS.md
Check all required fields are present
Reject output failing critical rules
Accept output failing minor rules with warnings
Ask for clarification on ambiguous validation rules
Check no contradictions across the output

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.