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 san-npm/skills-ws --skill lead-scoringgit clone --depth 1 https://github.com/san-npm/skills-wsWrote 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/san-npm/skills-ws/lead-scoring)<a href="https://agentmods.dev/skills/san-npm/skills-ws/lead-scoring"><img src="https://agentmods.dev/badge/skills/san-npm/skills-ws/lead-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/san-npm/skills-ws/lead-scoring"><img src="https://agentmods.dev/badge/skills/san-npm/skills-ws/lead-scoring.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00079 | $0.05559 |
| Opus 5 | $0.00039 | $0.02780 |
| Sonnet 5 | $0.00016 | $0.01112 |
| Haiku 4.5 | $0.00008 | $0.00556 |
Grade A, and why
lead-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 9d 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 — 284 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lead Scoring
Quantify how likely a lead/account is to buy (fit) and how actively they show intent (engagement), then route the highest-probability records to sales. This skill covers the scoring math, qualification frameworks, CRM + warehouse implementation, calibration against real outcomes, and privacy/compliance.
For the broader lifecycle (stages, conversion-rate analysis, pipeline math) see the sibling sales-funnel skill. Use this skill for the scoring/qualification layer that feeds those stages.
Scoring prioritizes outreach; it does not replace human qualification. A high score means "call sooner," not "close the deal." Discovery (BANT/MEDDIC) confirms what the score predicted.
Scoring Model Design
Two-Axis Model
Score on two independent axes so a great-fit-but-cold account isn't confused with a poor-fit tire-kicker who clicks everything:
- Fit Score (0–100): how well they match your ICP (firmographic/demographic). Mostly static; changes on enrichment or job change.
- Engagement Score (0–100): how actively they show buying intent (behavioral). Time-sensitive; decays.
Both axes are hard-capped at 100. Compute raw points, then clamp:
fit = min(100, sum(fit_points))
engagement = min(100, sum(engagement_points_after_decay_and_dedup))
total = round(0.4 * fit + 0.6 * engagement) # 0–100
The 40/60 weighting favors intent over fit — flip toward fit (e.g., 60/40) in long, committee-driven enterprise sales where firmographics predict more than clicks. Calibrate the weights against won/lost data (see Calibration); do not ship the default blindly.
Use a grade × score matrix, not a single number, for routing. Collapsing fit and engagement into one total hides the most important quadrant. Route on the 2x2 below and keep
totalonly as a tiebreaker/sort key.
| Low engagement (<40) | High engagement (≥60) | |
|---|---|---|
| High fit (≥60) | Nurture, account-based ads (A2 / "right fit, not ready") | Hot — alert AE, SLA timer (A1) |
| Low fit (<40) | Disqualify / low-touch (D) | Reroute or self-serve; investigate why low-fit is so active (could be a competitor, student, or job seeker) |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 284 lines · 79 tokens per session scan A ce99f4e2ba91
lead-scoring is a skill published in the GitHub repository san-npm/skills-ws (2 stars, last pushed 2d ago), licensed MIT. It adds 79 tokens to every session and 5,559 once invoked, about $0.0004 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…