agentleFS
Sign inStart free
Liberty91LTDLiberty91LTD/cti-skills/skills/likelihood-language/SKILL.md

likelihood-language

Skill35 starsChanged 45 days agoMITView on GitHub

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.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Every forward-looking assessment (prediction, forecast, risk statement) MUST use standardised likelihood language.

    line 11
  2. Distinctive:

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

    line 56

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

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

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free