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 skills add crevideo/crevideo-reach --skill creator-fit-scoringgit clone --depth 1 https://github.com/crevideo/crevideo-reachWrote 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/crevideo/crevideo-reach/creator-fit-scoring)<a href="https://agentmods.dev/skills/crevideo/crevideo-reach/creator-fit-scoring"><img src="https://agentmods.dev/badge/skills/crevideo/crevideo-reach/creator-fit-scoring/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/crevideo/crevideo-reach/creator-fit-scoring"><img src="https://agentmods.dev/badge/skills/crevideo/crevideo-reach/creator-fit-scoring.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00117 | $0.01416 |
| Opus 5 | $0.00059 | $0.00708 |
| Sonnet 5 | $0.00023 | $0.00283 |
| Haiku 4.5 | $0.00012 | $0.00142 |
Grade A, and why
creator-fit-scoring 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 12d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Creator Fit Scoring · 达人契合打分
Role: turn a creator's profile/history/performance into an evidence-based judgment of "worth collaborating for this product/brand?". Only judges fit + recommendation strength — does not set tier (creator-tier-resolver), validate commission (offer-policy-checker), or write copy (outreach-message-composer).
Output language
Write every output in the merchant's working language, using that market's native seller terminology:
- US Local sellers → English: tier / all-in take-rate / outreach waterfall / Target Collaboration / DM / sample …
- China POP sellers → 中文: 分级 / 真实抽成 / 触达阶梯 / 定向邀约 / 私信 / 寄样 …
Tool names (e.g.
preview_target_collab,find_similar_creators) stay identical in both languages. If unsure which market, ask once before producing output.
When to use / not use
- Use: score/rank a creator or a sample pool, decide whether to contact, run lookalike-expansion recruiting.
- Don't use: the user only wants report data (→ performance-diagnosis); only wants copy (→ outreach-message-composer).
Inputs (ask if missing, max 3 questions)
- Creator data source: preview_target_collab sample, list_affiliate_creators results, or a profile the user pastes.
- Target product: name/category/price (for fit; product must be ACTIVATE).
- Optional: the user's preferred tier or headcount.
Steps (in order)
- Exclude first (before ranking/scoring): cross-check the backend blocklist + project
Knowledge/do-not-contact(incl. cooldown-not-elapsed, whole-category avoidance); matches go to "Excluded" and are not scored (check both seeds and results). - Extract evidence per creator (only real fields you actually have; write N/A for missing, never fill with "industry average"): conversion signal (GMV per view / orders), audience fit (category + audience vs product), trust signal (fulfillment rate / past collaborations), risk signal (recent complaints / fulfillment drop).
- Apply "conversion > followers" as the first principle: follower count is reference only, never the primary basis.
- Per creator, output: fit (high/mid/low) + 3 concrete fit reasons + 1 uncertainty + suggested product + suggested outreach (as input for creator-tier-resolver / outreach). If you cannot give 3 concrete reasons → output HOLD (do not contact yet); do not pad.
- Pool-level assessment: headcount, fit distribution, whether to loosen/tighten the filter.
- Lookalike-expansion mode (when the user wants "find similar / scale up"): seed find_similar_creators only with sustained-sales creators (look at repeat/continuous conversion, not one GMV spike); re-exclude the blocklist on both seeds and results; output a "suggested new-invite candidates" table (same 3 reasons + 1 uncertainty).
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.
- 12d ago First seen · 75 lines · 117 tokens per session scan A 9cebbb3a260a
creator-fit-scoring is a skill published in the GitHub repository crevideo/crevideo-reach (7 stars, last pushed yesterday), licensed MIT. It adds 117 tokens to every session and 1,416 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
markifact-overview
Reference — what Markifact is, what the MCP server exposes, and the discover→inspect→run pattern. Always loaded into the performance-marketer agent.
safe-write-operations
Reference — rules for safely executing write/destructive operations against ad accounts. Always loaded into the performance-marketer agent.
dev
Software development planning. Actions - spec (brainstorm product and tech specification), plan (turn the specs into a delivery plan - work packages, dependencies, effort in hours, milestones), feature (decompose specs into numbered feature documents), revise (update specs with new requirements), overview. Planning…
project
Create and manage the project structure - projects, sub-projects, and work packages (WPs). Actions - new project, new subproject, new WP, overview. Hierarchy depth (2 or 3 levels) is fixed at creation. All work happens in WPs; projects and sub-projects are pure structure.
ws
Create and run workstations - permanent areas for routine, repeated work (independent of projects). Actions - new WS, new subWS, new area, new routine, run, from project, list, overview. Hierarchy depth (2 or 3 levels) is fixed at creation.
cease-desist
Draft a cease-and-desist letter (send mode) or triage one you received (receive mode). Use when asserting your rights against an infringer with a demand letter calibrated to your enforcement posture, or when an incoming C&D needs triage into a structured options memo with a recommendation.