policy

Define and enforce decision policies, compliance rules, and exceptions over Semantica graphs. Uses ContextGraph.check_decision_rules/enforce_decision_policy and context.PolicyEngine.

Quality

63%

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 ./plugins/skills/policy/SKILL.md

Quality

Content

76%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 and largely actionable with executable examples for both the simple and managed-policy paths, but the consequential enforcement workflow lacks validation/feedback checkpoints and a couple of constructs (Policy(...), decision_data) are left abstract.

Suggestions

Add a validation/feedback step for enforcement — e.g. branch on `result['compliant']` to handle violations before recording exceptions, and show how to react to `enforce_decision_policy` failures.

Resolve the abstract `Policy(...)` by showing the minimal fields a Policy object requires, or point to a model reference, so the full-path example is copy-paste runnable.

Clarify what `decision_data` / `graph_store` should be in the enforce and PolicyEngine snippets to close the actionability gap.

Dimension	Reasoning	Score
Conciseness	The body is lean and efficient with no concept-explanation padding; every section (simple path, full path, notes) earns its place and assumes Claude's competence.	5 / 5
Actionability	Both paths provide executable Python with real method calls, args, and return shapes (e.g. `{'compliant': bool, 'violations': [...], ...}`); minor gaps like abstract `Policy(...)` and undefined `decision_data` keep it just below fully copy-paste ready.	4 / 5
Workflow Clarity	It organizes a simple-path vs full-path structure but, for a consequential policy-enforcement/exception workflow, offers no validation checkpoints or error-recovery feedback loops; the rubric caps such workflows at 3.	3 / 5
Progressive Disclosure	The ~50-line body is cleanly split into labeled sections ("the simple path", "the full path") with inline notes; with no bundle files this nears the simple-skill ceiling, though `Policy(...)` is referenced inline with no model pointer, leaving a minor organization gap.	4 / 5
	Total	16 / 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 well-scoped to its niche but lacks an explicit trigger ("Use when...") clause, which caps completeness, and its keywords read as API references rather than natural user phrasing.

Suggestions

Add an explicit 'Use when...' trigger clause naming natural phrases users say, e.g. 'Use when the user asks to set up or enforce decision policies, compliance rules, or exceptions over Semantica decisions'.

Soften API jargon in favor of user-facing keywords (e.g. 'decision policies', 'compliance checks', 'policy exceptions') alongside the method references.

Consider listing the full set of concrete actions (check, enforce, version policies, record exceptions, analyze impact) to push specificity toward comprehensive.

Dimension	Reasoning	Score
Specificity	"Define and enforce decision policies, compliance rules, and exceptions" lists several concrete actions over the specific Semantica-graphs domain, falling just short of fully comprehensive coverage.	4 / 5
Completeness	It clearly states what the skill does (define/enforce policies, compliance rules, exceptions) but has no "Use when..." trigger clause, so per the rubric guideline completeness is capped at 3.	3 / 5
Trigger Term Quality	Triggers are framed as API jargon ("Semantica graphs", "ContextGraph.check_decision_rules/enforce_decision_policy", "context.PolicyEngine") rather than natural phrases a user would say; the common terms "policy", "compliance", "decision rules" appear but lack user-voice phrasing.	2 / 5
Distinctiveness Conflict Risk	Scoped specifically to policy governance over Semantica graphs, giving it a clear niche with only minor overlap risk against other Semantica skills.	4 / 5
	Total	13 / 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: semantica-agi/semantica
Path: plugins/skills/policy/SKILL.md
Commit: 05aec19

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.