Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/mturac/simulacra/skill-scorernpx skills add mturac/simulacra --skill skill-scorergit clone --depth 1 https://github.com/mturac/simulacraWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/mturac/simulacra/skill-scorer)<a href="https://agentmods.dev/skills/mturac/simulacra/skill-scorer"><img src="https://agentmods.dev/badge/skills/mturac/simulacra/skill-scorer.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00196 | $0.02658 |
| Opus 5 | $0.00098 | $0.01329 |
| Sonnet 5 | $0.00039 | $0.00532 |
| Haiku 4.5 | $0.00020 | $0.00266 |
Grade A, and why
skill-scorer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 317 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Scorer — 0-100 Rating for Any SKILL.md
Calibrated against Anthropic's own skill-creator guidelines and the patterns of 50k+ star repos (Superpowers, Caveman, mattpocock/skills). Average skill scores 45-55. If yours scores 80+, ship it.
Dependencies
None. Standalone. Reads any SKILL.md content.
CRITICAL: Auto-start
SKILL.md content in the message or just created in conversation → skip to Step 2. No preamble.
Step 1. Get the skill
Content in context? Use it. Otherwise:
Paste your SKILL.md or tell me which skill to score.
If the user names a skill in the current environment, read it.
Step 2. Score 10 Dimensions (each 0-10)
Be precise. 6.5 is 6.5, not 7. Every score needs one sentence of evidence referencing the actual skill content.
D1: Trigger Precision (0-10)
Will it fire when it should? Will it stay quiet when it shouldn't?
Evaluate the YAML description field:
- Specific trigger phrases listed? (+2)
- Natural language variations covered? (+2)
- "Pushy" quality per Anthropic guidance? (+2)
- Edge-case triggers (bare paste, implicit intent)? (+2)
- False positive risk controlled? (+2)
| Range | Calibration |
|---|---|
| 0-3 | Vague description, undertriggers or fires on everything |
| 4-6 | Some triggers but gaps in natural phrasing |
| 7-8 | Solid coverage, most natural phrasings caught |
| 9-10 | Comprehensive — includes implicit triggers and edge cases |
D2: Instruction Clarity (0-10)
Can Claude follow this without improvising?
- Unambiguous step sequence? (+2)
- Decision points with explicit branches? (+2)
- Deterministic enough that two instances produce similar output? (+3)
- No contradictory instructions? (+1.5)
- Clear scope boundaries (what it does AND doesn't do)? (+1.5)
D3: Output Predictability (0-10)
Does the user know what they'll get?
- Output format explicitly defined? (+3)
- Templates or examples provided? (+3)
- Length/scope appropriate and specified? (+2)
- Structured data output (JSON, table) available? (+2)
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 317 lines · 196 tokens per session scan A 212e1fa50a36
skill-scorer is a skill published in the GitHub repository mturac/simulacra (58 stars, last pushed 3mo ago), licensed MIT. It adds 196 tokens to every session and 2,658 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
archify
Create polished, validated architecture, workflow, sequence, data-flow, and lifecycle/state diagrams as explorable standalone HTML with inline SVG, dark/light themes, optional trace motion, and PNG/JPEG/WebP/SVG/WebM export. Accept plain-language requirements or pasted Mermaid flowchart, sequenceDiagram, and…
vox-director
Turn ONE topic into a finished Vox-style paper-collage explainer / ad video, end to end on the Atlas Cloud API + local ffmpeg — script, collage keyframes, motion, voice-over, music, captions, all automated. Use this whenever the user wants a "Vox style" video, a paper/torn-paper collage animation, a "motion collage"…
social-post
學習使用者的 Facebook／Instagram／YouTube／Threads／X 語氣與受眾，規劃、撰寫、確認後發佈內容；以已登入 Chrome 受控掃描、草擬及回覆 FB／IG／Threads 留言；並作為流量、留存與轉化的結構化帳本。使用者說「發文」「用我的口氣」「回覆留言」「自動回留言」「掃留言」「查流量」「演算法」「把數據訓練進去」「比較貼文」「優化 pattern」時使用。.
higgsfield
Use this skill whenever the user asks anything about Higgsfield AI — writing or refining video/image prompts, choosing a model (Kling, Sora 2, Veo, Wan, Seedance, Minimax Hailuo, DoP, Soul, Nano Banana, Seedream, Flux, GPT Image, etc.), camera controls, named motion presets, Soul ID character consistency, Cinema…
higgsfield-camera
Use when the user asks about camera movements, shot types, or how to describe camera behavior in a Higgsfield prompt. Contains all named camera controls with descriptions, best use cases, and example prompt phrases.
higgsfield-troubleshoot
Use when a Higgsfield generation fails, produces poor quality, looks wrong, doesn't match the prompt, or the user needs to fix or improve an output.