gateguard

Fact-forcing gate that blocks Edit/Write/Bash (including MultiEdit) and demands concrete investigation (importers, data schemas, user instruction) before allowing the action. Measurably improves output quality by +2.25 points vs ungated agents.

Quality

57%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/gateguard/SKILL.md

Quality

Content

63%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is actionable and the three-stage gate workflow is clear and well-structured, with the gate prompts serving as built-in validation checklists. It is held back by marketing-style padding and a referenced hook script that is not actually present in the bundle.

Suggestions

Remove or relocate the 'Evidence' A/B-test table and promotional claims; they consume context without aiding execution.

Ship the referenced scripts/hooks/gateguard-fact-force.js in a scripts/ bundle, or remove the path reference if the pip package is the primary install path.

Add an explicit error-recovery loop for the destructive-bash gate (e.g. rollback -> verify -> proceed).

Dimension	Reasoning	Score
Conciseness	Gate prompts and commands are efficient, but the 'Evidence' A/B-test table and marketing lines ('No competitor does all three', 'verified experimentally') are padding that does not help Claude execute.	3 / 5
Actionability	Provides concrete numbered gate-prompt templates and executable commands (ECC_GATEGUARD=off, pip install gateguard-ai, gateguard init) with only minor gaps.	4 / 5
Workflow Clarity	The DENY/FORCE/ALLOW three-stage gate is a clearly sequenced workflow with the gate itself acting as a validation checkpoint and feedback loop; minor gaps in explicit error-recovery documentation.	4 / 5
Progressive Disclosure	Section structure is well-organized, but the body references scripts/hooks/gateguard-fact-force.js and no scripts/ bundle directory exists, so the one-level reference is a dead link.	3 / 5
	Total	14 / 20 Passed

Description

51%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific and distinct about what the gate does, but it reads as marketing-heavy technical prose and omits any explicit 'when to use' trigger guidance. Adding a natural-language 'Use when...' clause would lift completeness and trigger quality.

Suggestions

Add an explicit 'Use when...' clause naming natural trigger phrases (e.g. 'Use when Claude is about to edit files in a multi-module codebase or modify data with specific schemas').

Replace jargon like 'Fact-forcing gate' and 'ungated agents' with terms a user would naturally say.

Drop the '+2.25 points' marketing claim from the description; it is evidence, not a capability.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'blocks Edit/Write/Bash (including MultiEdit)' and 'demands concrete investigation (importers, data schemas, user instruction)' — with only minor gaps (no mention of destructive-bash handling).	4 / 5
Completeness	Has a clear 'what' (blocks edits and forces investigation) but no 'Use when...' or equivalent explicit trigger guidance, which caps completeness at 3 per the rubric.	3 / 5
Trigger Term Quality	Dominated by technical jargon ('Fact-forcing gate', 'MultiEdit', 'ungated agents') rather than natural phrases a user would say; lacks common trigger variations.	2 / 5
Distinctiveness Conflict Risk	The fact-forcing pre-action gate is a fairly distinct niche with specific triggers; only minor overlap risk with closely related skills like safety-guard.	4 / 5
	Total	13 / 20 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
referenced_paths_exist	Referenced path issues: 1 missing, 1 deeper-than-1-level	Warning

	Total	14 / 16 Passed

Repository: affaan-m/ECC
Path: skills/gateguard/SKILL.md
Commit: 06c5e11

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.