endor-api
Execute custom queries against the Endor Labs API for advanced use cases. Use when the user asks to query findings, projects, packages, or metrics directly, says "endor api", "raw api query", "custom query", "list resources", or needs to run API filters not covered by other endor skills. Do NOT use for standard scanning (/endor-scan), dependency checks (/endor-check), or finding display (/endor-findings).
68
82%
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 clearly defines its purpose, provides rich trigger terms, explicitly states both when to use and when NOT to use it, and distinguishes itself from related skills. The inclusion of negative boundaries (Do NOT use for...) is a best practice that further reduces conflict risk. The description is concise yet comprehensive.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'execute custom queries', 'query findings, projects, packages, or metrics directly', 'run API filters'. Also specifies what it does NOT do (scanning, dependency checks, finding display), which adds clarity. | 3 / 3 |
Completeness | Clearly answers both 'what' (execute custom queries against the Endor Labs API) and 'when' (explicit 'Use when...' clause with multiple trigger scenarios). Also includes a 'Do NOT use' clause that further clarifies boundaries, which is excellent for completeness. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'endor api', 'raw api query', 'custom query', 'list resources', 'API filters', plus domain objects like 'findings', 'projects', 'packages', 'metrics'. These are terms users would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with explicit boundary-setting via the 'Do NOT use for' clause that names specific other skills (/endor-scan, /endor-check, /endor-findings). This makes it very clear when this skill should and should not be selected, minimizing conflict risk. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid API reference skill with strong actionability—concrete commands, real filter syntax, and specific resource types make it immediately useful. The main weaknesses are a slightly verbose workflow structure (Step 1 is unnecessary for Claude) and missing validation checkpoints between query execution and result presentation. The progressive disclosure references external files that aren't provided in the bundle, making it hard to fully assess navigation quality.
Suggestions
Remove 'Step 1: Understand the Query' entirely—Claude inherently parses user requests and this section adds no value.
Add a validation checkpoint after query execution, e.g., 'If results are empty or unexpected, verify the resource type and filter syntax before presenting to the user.'
Ensure referenced files (`references/cli-parsing.md`, `references/data-sources.md`) exist in the bundle, or inline the critical information if they don't.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient with good use of tables, but includes some unnecessary structure like the 'Step 1: Understand the Query' section which tells Claude to parse user requests—something it inherently does. The MCP tools table duplicates information Claude likely already has from tool definitions. | 2 / 3 |
Actionability | Provides concrete, executable CLI commands with real filter syntax, specific resource type names, actual endpoint URLs, and copy-paste ready filter examples. The MCP tool mapping and CLI commands are directly actionable. | 3 / 3 |
Workflow Clarity | Steps are clearly sequenced, but there's no validation checkpoint—after executing a query, there's no guidance on verifying results are correct, handling empty results, or confirming the right resource/filter was used before presenting to the user. The error handling table helps but is reactive rather than proactive. | 2 / 3 |
Progressive Disclosure | References to `references/cli-parsing.md` and `references/data-sources.md` are well-signaled and one level deep, but no bundle files were provided to verify these exist. The main content includes substantial inline detail (filter syntax, all endpoints, all MCP tools) that could potentially be split out for better organization. | 2 / 3 |
Total | 9 / 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.