Skill Crossroads pr-shepherd
rubric v1.2 · deterministic
A− 92.7/100 overall
Correctness & Structure 100 pass
Triggering & Discoverability 85 1 warn
Clarity & Instructions 100 pass
Token & Context Cost 86 1 warn
Safety & Security 93 1 warn
Verifiability & Maintainability not yet scored

Top fixes — ranked by score impact

⚠ TRIGGER-03 Invocation cues in the description
pr-shepherd.md:1description will match user requests → no explicit cue ('use when …', 'triggers on …', quoted user phrases) found
Pure what-it-does prose — the model has to guess when to invoke it.
Iterative PR driver for delegated use. Watches CI, fixes failures, addresses …
Fix State the trigger explicitly: 'Use when the user says "…", "…", or wants to …'.
⚠ TOKEN-01 Body under line/token budget
pr-shepherd.md500-line guidance → 548 lines
SKILL.md is 548 lines — over the ~500-line guidance. ~7,596 tokens (rough est.); ~$0.0228 per load at $3/Mtok reference rate.
Fix Move heavy reference material into supporting files and link to them (progressive disclosure), keeping SKILL.md lean.
⚠ SAFETY-02 allowed-tools least-privilege
pr-shepherd.md:1no `tools` declared → the agent inherits every tool, including Bash
Subagents without a `tools` list get unrestricted tool access.
Fix Declare a scoped `tools:` list with only what the agent needs (e.g. `tools: Read, Grep, Glob`).
Partial grade — some applicable rubric categories were not scored on this scan (e.g. LLM-assisted checks without a key) and are excluded from the overall.

Embed this badge

Skill Crossroads grade A− Always-fresh — it re-scans and updates on its own. 
[![Skill Crossroads](https://skillcrossroads.com/api/badge/Cortexa-LLC/ai-pack/plugin/agents/pr-shepherd.md.svg)](https://skillcrossroads.com/s/Cortexa-LLC/ai-pack/plugin/agents/pr-shepherd.md)
Grade your own Claude Code skill — evidence-cited, file-and-line, free. Scan your own skill →