endor-ai-sast
Fetch and display AI-powered SAST findings from the Endor Labs platform. Use when the user says "AI SAST results", "AI SAST findings", "AI static analysis", "endor ai sast", "show AI SAST", or wants to view pre-computed AI-driven code security findings. Do NOT use for running a new SAST scan (/endor-sast), viewing general findings (/endor-findings), or explaining a specific CVE (/endor-explain).
94
92%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Risky
Do not use without reviewing
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 scope, provides abundant natural trigger terms, and explicitly delineates boundaries with related skills. The 'Do NOT use' clause is particularly effective for disambiguation in a multi-skill environment. The description is concise yet comprehensive, using proper third-person voice throughout.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description lists concrete actions ('Fetch and display AI-powered SAST findings') and clearly specifies the source ('Endor Labs platform'). It also explicitly distinguishes what this skill does NOT do, adding further specificity. | 3 / 3 |
Completeness | Clearly answers both 'what' (fetch and display AI-powered SAST findings from Endor Labs) and 'when' (explicit 'Use when...' clause with multiple trigger phrases). Additionally includes 'Do NOT use' guidance to prevent misuse, which goes above and beyond. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms: 'AI SAST results', 'AI SAST findings', 'AI static analysis', 'endor ai sast', 'show AI SAST', and the conceptual phrase 'pre-computed AI-driven code security findings'. These are terms users would naturally say. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with explicit boundary-setting via 'Do NOT use for' clauses that reference specific competing skills (/endor-sast, /endor-findings, /endor-explain). This makes it very unlikely to conflict with related skills in the same ecosystem. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%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 workflow clarity, strong actionability through executable commands and precise output templates, and good progressive disclosure both in its own structure and in how it instructs Claude to present results. The main weakness is token efficiency — the large inline mapping tables for short titles and remediations, while valuable, could potentially be externalized to reference files to reduce the skill's footprint in the context window.
Suggestions
Consider moving the short-title mapping table and remediation mapping table to a reference file (e.g., references/sast-mappings.md) to reduce the inline token cost while keeping the main skill lean.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient and avoids explaining concepts Claude already knows, but the extensive remediation mapping tables and short-title mapping tables add significant length. While useful as reference, some of this could be externalized to a reference file to reduce token cost. | 2 / 3 |
Actionability | Every step includes fully executable bash commands with proper variable handling, specific API filters, field masks, and exact output formats. The presentation templates are copy-paste ready with concrete table structures and formatting examples. | 3 / 3 |
Workflow Clarity | The workflow is clearly sequenced (Steps 1-4) with explicit dependencies ('Only run this after Step 1 succeeds'), validation checkpoints (checking for empty namespace, empty results), and a comprehensive error handling table with specific recovery actions for each failure mode. | 3 / 3 |
Progressive Disclosure | The skill itself uses tiered output (summary → clusters → critical details → drill-down) and references external files appropriately (references/cli-parsing.md, references/data-sources.md) at one level deep with clear signals. The content is well-structured with logical sections. | 3 / 3 |
Total | 11 / 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
344e7ff
- 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.