engram-architecture-guardrails

Architecture guardrails for Engram across local store, cloud sync, dashboard, and plugins. Trigger: Any change that affects system boundaries, ownership, state flow, or cross-package responsibilities.

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/architecture-guardrails/SKILL.md

Quality

Content

86%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 content is concise, well-structured, and actionable, with concrete package-routing rules and explicit validation guidance. It is a strong instruction-only skill whose only weak spot is the absence of copy-paste-ready commands or a fully sequenced workflow.

Suggestions

Add a short worked example mapping a sample change (e.g., 'adding cloud-shared tags') through the Decision Rules to a concrete package choice to nudge actionability toward fully executable.

Optionally sequence the Validation steps as an explicit checklist (test boundary -> verify product story -> test push & pull) to strengthen workflow clarity.

If detailed package-responsibility tables grow, split them into a references file to preserve the lean overview.

Dimension	Reasoning	Score
Conciseness	The body is lean and efficient — e.g., 'Local SQLite is the source of truth; cloud is replication and shared access' — with no padding and no explanation of concepts Claude already knows; every line earns its place.	5 / 5
Actionability	Decision Rules provide concrete, executable routing to specific package paths ('Local-only concern -> `internal/store`', 'Cloud materialization ... -> `internal/cloud/cloudstore`'), but as an instruction-only skill it stops short of copy-paste-ready commands, leaving minor gaps.	4 / 5
Workflow Clarity	The skill is clearly organized into When-to-Use, Decision Rules, and Validation, with explicit verification checkpoints (regression tests, push/pull testing); it is not a sequenced multi-step workflow, so it sits just below the 'clear sequence with explicit feedback loops' anchor.	4 / 5
Progressive Disclosure	Well-organized into clear sections with no bundle files and well under 50 lines, so per the under-50-lines guideline the structure alone earns a top score with no need for external references.	5 / 5
	Total	18 / 20 Passed

Description

66%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 concise and clearly scoped to a distinct niche, with an explicit trigger clause covering both what and when. It could improve by naming concrete guardrail actions and adding more natural-language trigger synonyms.

Suggestions

Add 1-2 concrete guardrail actions (e.g., 'routes concerns to the correct package and flags boundary violations') to lift specificity above domain-naming.

Soften the trigger with natural user phrasing or synonyms (e.g., 'Use when refactoring across store, cloud, dashboard, or plugin layers') alongside the technical condition.

Consider mentioning the validation expectation in the description so users know the skill enforces regression tests.

Dimension	Reasoning	Score
Specificity	Names the Engram domain and several concrete concerns (boundaries, ownership, state flow, cross-package responsibilities), but describes the domain rather than listing concrete executable actions, placing it at the 'names domain and 1-2 concrete actions' anchor rather than the 'several specific actions' anchor.	3 / 5
Completeness	Clearly states both what it does ('Architecture guardrails for Engram across local store, cloud sync, dashboard, and plugins') and when to use it (explicit Trigger clause), with the 'when' concrete and specific; falls just short of 5 because the trigger is framed as a developer-facing condition rather than natural user-request phrases.	4 / 5
Trigger Term Quality	The explicit 'Trigger: Any change that affects system boundaries, ownership, state flow, or cross-package responsibilities' provides relevant keywords, but they are technical-jargon-heavy and lack natural synonyms or variations a user would casually say.	3 / 5
Distinctiveness Conflict Risk	Highly specific to the Engram system with named subsystems (local store, cloud sync, dashboard, plugins), giving it a clear niche with minimal conflict risk against unrelated skills.	5 / 5
	Total	15 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: Gentleman-Programming/engram
Path: skills/architecture-guardrails/SKILL.md
Commit: 47f281c

Reviewed: 6 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.