endor-policy
Create and manage Endor Labs security policies for automated enforcement. Use when the user says "create a policy", "block critical vulns", "endor policy", "security gate", "enforcement rules", "exception policy", or wants to define rules for blocking PRs, requiring reviews, or enforcing security standards. Do NOT use for one-time PR review (/endor-review) or viewing findings (/endor-findings).
73
89%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that hits all the marks. It provides specific capabilities, rich natural trigger terms, explicit 'Use when' and 'Do NOT use' clauses, and clear differentiation from related skills. The negative boundary ('Do NOT use for...') is a particularly strong feature that reduces conflict risk with sibling skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions: 'Create and manage security policies', 'blocking PRs', 'requiring reviews', 'enforcing security standards', 'exception policy'. Also specifies the platform (Endor Labs) and the domain (automated enforcement). | 3 / 3 |
Completeness | Clearly answers both 'what' (create and manage Endor Labs security policies for automated enforcement) and 'when' (explicit 'Use when...' clause with multiple trigger phrases). Also includes a 'Do NOT use' clause to reduce false matches, which is excellent. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'create a policy', 'block critical vulns', 'endor policy', 'security gate', 'enforcement rules', 'exception policy'. These are realistic phrases a user would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with clear niche (Endor Labs security policies). The explicit 'Do NOT use' clause for /endor-review and /endor-findings actively prevents conflicts with related skills, making it very unlikely to trigger incorrectly. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
79%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-crafted skill with excellent actionability — the executable commands with complete JSON payloads are immediately usable. The confirmation gate before policy changes is a good safety measure. The main weaknesses are the lack of a post-creation validation step (important given the high-impact nature of policies that can block all PRs) and a reference to a bundle file that doesn't exist.
Suggestions
Add an explicit validation step after policy creation, e.g., list policies to confirm creation, then suggest testing against a specific project with /endor-validate-policy before relying on enforcement.
Either include the referenced 'references/data-sources.md' file in the bundle or remove the reference to avoid a dead link.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and well-structured. It uses tables for quick reference, provides only the necessary commands and JSON payloads, and doesn't explain concepts Claude already knows. Every section earns its place. | 3 / 3 |
Actionability | Provides fully executable, copy-paste ready bash commands with complete JSON payloads for each policy template. The list, create, and exception workflows all have concrete commands with real filter syntax. | 3 / 3 |
Workflow Clarity | The workflow covers list, create, and exception steps clearly, and includes a confirmation gate before creating policies. However, there's no explicit validation/verification step after policy creation (e.g., verify the policy was created correctly, test it against existing findings before it blocks real PRs). For a destructive/high-impact operation like blocking all PRs org-wide, a feedback loop is missing. | 2 / 3 |
Progressive Disclosure | References 'references/data-sources.md' and '/endor-findings' filter reference, but the bundle has no files. The content is reasonably organized with tables and sections, but the inline policy templates could potentially be split into a reference file, and the data-sources reference points to a non-existent file. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- endorlabs/skills-ideas
- Commit
b958adc
- Reviewed
Table of Contents
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.