Skill Crossroads draft_writer_agent
rubric v1.2 · deterministic
A− 91.7/100 overall
Correctness & Structure 100 pass
Triggering & Discoverability 85 1 warn
Clarity & Instructions 100 pass
Token & Context Cost 80 2 warn
Safety & Security 93 1 warn
Verifiability & Maintainability not yet scored

Top fixes — ranked by score impact

⚠ TRIGGER-03 Invocation cues in the description
draft_writer_agent.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.
Writes the full paper draft section by section from the structured outline an…
Fix State the trigger explicitly: 'Use when the user says "…", "…", or wants to …'.
⚠ TOKEN-01 Body under line/token budget
draft_writer_agent.md500-line guidance → 686 lines
SKILL.md is 686 lines — over the ~500-line guidance. ~18,929 tokens (rough est.); ~$0.0568 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.
⚠ TOKEN-04 Recurring per-invocation cost
draft_writer_agent.mda one-time authoring cost → ~18,929 tokens (rough est.) per invocation
Every invocation carries this: ~18,929 tokens (rough est.) per invocation — ~$56.79 per 1,000 invocations at the $3/Mtok reference rate.
Fix Cut the entry file below ~8k tokens — move reference material into supporting files so every future invocation gets cheaper.
⚠ SAFETY-02 allowed-tools least-privilege
draft_writer_agent.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/FridrichMethod/awesome-skills/skills/academic-paper/agents/draft_writer_agent.md.svg)](https://skillcrossroads.com/s/FridrichMethod/awesome-skills/skills/academic-paper/agents/draft_writer_agent.md)
Grade your own Claude Code skill — evidence-cited, file-and-line, free. Scan your own skill →