跳到正文
cccskills
免费在 GitHub 公开

likelihood-language

Use when phrasing a forward-looking statement, the user asks "how likely is X?" / "what's the likelihood?", or the tradecraft pipeline applies a probability yardstick to a finished product. Standardised likelihood language across all products.

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(1)

  • SKILL.md4.1 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Likelihood Language — Probability Yardstick

Every forward-looking assessment (prediction, forecast, risk statement) MUST use standardised likelihood language. Never use vague terms like "could", "might", or "may" without mapping them to a probability band.

The Yardstick

TermProbability RangeUsage
Almost certain>95%Use sparingly. Reserved for near-inevitable outcomes with overwhelming evidence.
Highly likely75-95%Strong evidence supporting the assessment. Limited plausible alternatives.
Likely50-75%The weight of evidence supports this outcome, but meaningful alternatives exist.
Realistic possibility25-50%Plausible outcome that cannot be discounted. Evidence is mixed or limited.
Unlikely15-25%Possible but not supported by the weight of evidence.
Highly unlikely5-15%Very limited evidence suggests this outcome. Most evidence points elsewhere.
Remote<5%Theoretically possible but requires multiple unlikely conditions to align.

How to Use

Correct usage

"It is highly likely (75-95%) that the threat actor will shift targeting to the financial sector in Q3, based on observed reconnaissance activity and historical pattern of seasonal targeting shifts."

"There is a realistic possibility (25-50%) that the exploit will be weaponised within 30 days, given the availability of a proof-of-concept but no evidence of active exploitation."

Incorrect usage

"The threat actor might target financial services." ❌ (No probability band) "It could happen in Q3." ❌ (Vague, unquantified) "We think it's likely but also possible that..." ❌ (Contradictory — pick one band)

Combining with Confidence

Likelihood and confidence are independent dimensions:

"We assess with moderate confidence that it is likely (50-75%) that Group X will conduct destructive operations against energy sector targets in the next 6 months."

  • Moderate confidence: We have some evidence but key assumptions are not fully validated
  • Likely: Based on available evidence, the probability falls in the 50-75% range

A low-confidence assessment CAN have a high likelihood term — it means "if our assessment is correct, the probability is high, but we're not fully sure our assessment is correct."

When NOT to Use Likelihood Language

  • Statements of fact: "APT28 used Fancy Bear malware in this campaign" — this is a factual claim, not a prediction. Use confidence levels instead.
  • Historical analysis: "The campaign began in January 2025" — past events don't need likelihood language.
  • Definitions and descriptions: "SIGMA rules are detection rules written in YAML" — informational, not predictive.

Mapping Informal Language

If you catch yourself writing informal probabilistic language, map it:

InformalMap to
"could", "may", "might"Determine which band and use proper term
"probably"Likely (50-75%) or Highly likely (75-95%)
"possibly"Realistic possibility (25-50%)
"unlikely"Already a valid term — check it maps to 15-25%
"almost certainly"Almost certain (>95%)
"there's a chance"Determine probability and use proper term
"can't rule out"Realistic possibility (25-50%) or Unlikely (15-25%)

Common Mistakes

  • Using multiple likelihood terms in one assessment ("likely or highly likely") — commit to one
  • Hedging with "possible" instead of making a judgment — if evidence is weak, say "unlikely" with rationale
  • Forgetting to include the percentage range in parentheses — always include for clarity
  • Confusing likelihood with confidence (see confidence-levels skill)
  • Using "almost certain" casually — this is >95% and should be rare

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

AbuseIPDB API reference. IP reputation and abuse report lookups.

中文简介正在准备中。当前显示原文说明。

Liberty91LTD/cti-skills272026年9月30日 更新

ach

免费

Analysis of Competing Hypotheses — structured technique for evaluating multiple explanations against evidence. Use when facing ambiguous attribution or multiple plausible scenarios. Prefers graded evidence items from /quality-of-information-check and runs that skill first when handed raw URLs or text. Runs on ungraded evidence when asked, labelled as such, unweighted, and capped at Moderate confidence.

中文简介正在准备中。当前显示原文说明。

Liberty91LTD/cti-skills272026年9月30日 更新

Use when documenting a named campaign across time and victims, the user asks to start or update a campaign record, or another skill identified a multi-incident cluster that warrants formal tracking. Provides the template (timeline, attribution, victimology, attack chain, Diamond Model mapping, IOC clusters) and the lifecycle from active to historical.

中文简介正在准备中。当前显示原文说明。

Liberty91LTD/cti-skills272026年9月30日 更新

Use when the user asks about carding, BIN attacks, payment-card breach markets, fullz/CVV2 trade, autoshops (BidenCash, Brian's Club, Russianmarket, B1ack's Stash), or financial-fraud TTPs. Self-updating knowledge cell.

中文简介正在准备中。当前显示原文说明。

Liberty91LTD/cti-skills272026年9月30日 更新

Censys API v2 reference. Host reconnaissance and certificate data.

中文简介正在准备中。当前显示原文说明。

Liberty91LTD/cti-skills272026年9月30日 更新

Use when the user asks about Chinese state-sponsored cyber operations or specific PRC-aligned actors (APT41, Volt Typhoon, Mustang Panda, APT10, APT31, Salt Typhoon, etc.), MSS/PLA-attributed campaigns, or PRC sector targeting. Self-updating knowledge cell.

中文简介正在准备中。当前显示原文说明。

Liberty91LTD/cti-skills272026年9月30日 更新

查看 Liberty91LTD 的全部技能

报告此技能的问题