engram-business-rules

Product and business-rule guardrails for Engram. Trigger: Any change that affects sync behavior, project controls, permissions, or memory semantics.

Quality

73%

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/business-rules/SKILL.md

Quality

Content

72%

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

The body is an efficiently organized guardrail reference with strong conciseness and clean section structure. Its weaker spots are actionability (principles over concrete specifics) and workflow_clarity (no sequenced process with validation checkpoints).

Suggestions

Add one concrete example or checklist per rule group so the guardrails translate into verifiable, executable checks rather than abstract principles.

Provide a short ordered workflow (e.g., identify affected area -> check matching rule -> verify deterministic/testable behavior -> preserve audit trail) with an explicit validation checkpoint for sync-affecting changes.

Turn 'fail loudly' and 'Preserve auditability' into explicit validation steps with expected outcomes so destructive/batch sync changes have a feedback loop.

Dimension	Reasoning	Score
Conciseness	The body is lean and rule-driven with no concept padding or unnecessary explanation; every line states a constraint and assumes Claude's competence, matching 'Lean and efficient; every token earns its place.'	3 / 3
Actionability	Rules are directive ('must map to real business rules, never fake toggles', 'fail loudly rather than dropping data silently') but mostly function as principles/guardrails without concrete implementation specifics or examples, sitting between abstract and fully concrete.	2 / 3
Workflow Clarity	There is no sequenced multi-step workflow; rules like 'fail loudly' and 'Preserve auditability' imply validation but lack explicit checkpoints or an ordered process, so it is organized but missing a real workflow with feedback loops.	2 / 3
Progressive Disclosure	The skill is well under 50 lines, needs no external bundle files (none exist), and is organized into clear one-level sections ('When to Use', 'Product Rules', 'Sync Rules'), meeting the simple-skill allowance for a 3.	3 / 3
	Total	10 / 12 Passed

Description

75%

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 explicitly answers both what and when via a clear Trigger clause, with a distinct Engram-specific niche. Its main weakness is that the wording favors domain jargon over natural user phrasings and describes scope rather than concrete actions.

Suggestions

Add a few concrete verbs/actions (e.g., 'enforce', 'review', 'validate') to the what-clause so capabilities read as actions rather than scope.

Soften jargon in the trigger with natural phrasings a user might actually say (e.g., 'sync settings', 'who can see what data') alongside the domain terms.

Consider including a short 'Use when...' variant in addition to 'Trigger:' to broaden natural-keyword coverage.

Dimension	Reasoning	Score
Specificity	It names the domain (Engram) and several areas ('sync behavior, project controls, permissions, or memory semantics') but describes scope rather than listing multiple concrete actions, matching the 'Names domain and some actions, but not comprehensive' anchor.	2 / 3
Completeness	It states what the skill provides ('Product and business-rule guardrails for Engram') and gives an explicit when via the 'Trigger:' clause, satisfying both halves; the explicit trigger guidance means completeness is not capped at 2.	3 / 3
Trigger Term Quality	The explicit 'Trigger:' clause surfaces relevant keywords ('sync', 'permissions', 'project controls'), but terms like 'memory semantics' and 'project controls' lean toward domain jargon rather than the natural phrasings a user would commonly say, so it is not full coverage.	2 / 3
Distinctiveness Conflict Risk	Tied to a specific product (Engram) with narrow, domain-specific triggers, it occupies a clear niche and is unlikely to fire for unrelated skills.	3 / 3
	Total	10 / 12 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/business-rules/SKILL.md
Commit: 763a6ba

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.