TimesFM Forecasting
google-research/timesfm
Forecasts any univariate time series zero-shot with Google's TimesFM model, returning point forecasts and calibrated prediction intervals without training.
A skill your agent uses when forecasting, estimating, or sizing risk — anchor on base rates, give ranges, update prior→likelihood→posterior on evidence, and factor unmeasured quantities into…
Install Thinking Probabilistic
$ npx skills add tjboudreaux/cc-thinking-skills --skill thinking-probabilistic -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install tjboudreaux/cc-thinking-skills thinking-probabilistic --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/tjboudreaux/cc-thinking-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/thinking-probabilistic .claude/skills/thinking-probabilistic && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "thinking-probabilistic" agent skill from https://github.com/tjboudreaux/cc-thinking-skills/tree/main/skills/thinking-probabilistic into .claude/skills/thinking-probabilistic/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "thinking-probabilistic", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/tjboudreaux/cc-thinking-skills/tree/main/skills/thinking-probabilisticType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add tjboudreaux/cc-thinking-skills --skill thinking-probabilistic -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install tjboudreaux/cc-thinking-skills thinking-probabilistic --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tjboudreaux/cc-thinking-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/thinking-probabilistic .agents/skills/thinking-probabilistic && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "thinking-probabilistic" agent skill from https://github.com/tjboudreaux/cc-thinking-skills/tree/main/skills/thinking-probabilistic into .agents/skills/thinking-probabilistic/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "thinking-probabilistic", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add tjboudreaux/cc-thinking-skills --skill thinking-probabilistic -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install tjboudreaux/cc-thinking-skills thinking-probabilistic --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tjboudreaux/cc-thinking-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/thinking-probabilistic .cursor/skills/thinking-probabilistic && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "thinking-probabilistic" agent skill from https://github.com/tjboudreaux/cc-thinking-skills/tree/main/skills/thinking-probabilistic into .cursor/skills/thinking-probabilistic/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "thinking-probabilistic", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/tjboudreaux/cc-thinking-skills.git --path skills/thinking-probabilistic--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add tjboudreaux/cc-thinking-skills --skill thinking-probabilistic -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install tjboudreaux/cc-thinking-skills thinking-probabilistic --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tjboudreaux/cc-thinking-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/thinking-probabilistic .gemini/skills/thinking-probabilistic && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "thinking-probabilistic" agent skill from https://github.com/tjboudreaux/cc-thinking-skills/tree/main/skills/thinking-probabilistic into .gemini/skills/thinking-probabilistic/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "thinking-probabilistic", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install tjboudreaux/cc-thinking-skills thinking-probabilisticInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add tjboudreaux/cc-thinking-skills --skill thinking-probabilistic -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/tjboudreaux/cc-thinking-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/thinking-probabilistic .github/skills/thinking-probabilistic && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "thinking-probabilistic" agent skill from https://github.com/tjboudreaux/cc-thinking-skills/tree/main/skills/thinking-probabilistic into .github/skills/thinking-probabilistic/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "thinking-probabilistic", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add tjboudreaux/cc-thinking-skills --skill thinking-probabilistic -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install tjboudreaux/cc-thinking-skills thinking-probabilistic --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tjboudreaux/cc-thinking-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/thinking-probabilistic .opencode/skills/thinking-probabilistic && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "thinking-probabilistic" agent skill from https://github.com/tjboudreaux/cc-thinking-skills/tree/main/skills/thinking-probabilistic into .opencode/skills/thinking-probabilistic/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "thinking-probabilistic", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
thinking-probabilistic- GitHub stars
- 1.6k
- Token cost
- ~1.1k tokens
- SKILL.md length
- 624 words
- Files
- 1
- Skills in repo
- 26
- Repo updated
- First seen
- Licence
- MIT
At a glance
A skill your agent uses when forecasting, estimating, or sizing risk — anchor on base rates, give ranges, update prior→likelihood→posterior on evidence, and factor unmeasured quantities into…
- Works in 6 steps: Define a checkable claim: outcome +… → Lock a prior and challenge it: name a… → Express a range, not a point: give at… → …
- Sizing risk — anchor on base rates
- SKILL.md covers When to Use, When NOT to Use, Procedure and Output, plus 1 more section
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Thinking Probabilistic is an agent skill from tjboudreaux/cc-thinking-skills. Use when forecasting, estimating, or sizing risk — anchor on base rates, give ranges, update prior→likelihood→posterior on evidence, and factor unmeasured quantities into order-of-magnitude bounds.
Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Data & Analytics, covering Forecasting and time series. The repository describes itself as: 28 eval-informed mental models and critical-thinking skills for Claude Code, GitHub Copilot, Codex, Cursor, and other Agent Skills-compatible tools. The licence is MIT.
When your agent uses it
- Sizing risk — anchor on base rates
- Update prior→likelihood→posterior on evidence
- Factor unmeasured quantities into order-of-magnitude bounds
Example prompts
- “/thinking-probabilistic”
Workflow steps
6 steps, taken from the first numbered list in SKILL.md.
- Define a checkable claim: outcome + timeframe + unit. Prefer a falsifiable statement over vague language ("likely").
- Lock a prior and challenge it: name a reference-class base rate and at least one credible alternative path/hypothesis with its rate. Pull…
- Express a range, not a point: give at least one confidence interval (50% and 80% preferred). Assume overconfidence; widen intervals when…
- Update prior → likelihood → posterior when evidence arrives
- Fermi-bound unmeasured quantities (only when you need a magnitude you cannot measure/look up)
- State the final estimate for checking: claim, range/CIs, key uncertainties, and the observation that would prove it wrong. Stop when the…
What it can do on your machine
Read from SKILL.md and the folder at commit 7b8fece. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Thinking Probabilistic loads about 1.1k tokens when it runs. Until then it costs about 55 tokens; SKILL.md has 624 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from tjboudreaux/cc-thinking-skills at commit 7b8fece, republished under its MIT licence (© tjboudreaux). 624 words, ~1,112 tokens.
Download SKILL.mdSave it as
.claude/skills/thinking-probabilistic/SKILL.md (or your agent's skills folder).- name
- thinking-probabilistic
- description
- Use when forecasting, estimating, or sizing risk — anchor on base rates, give ranges, update prior→likelihood→posterior on evidence, and factor unmeasured quantities into order-of-magnitude bounds.
- disable-model-invocation
- true
Probabilistic Thinking
Core rule: State beliefs as numbers and ranges, not vibes. Anchor on a base rate, update with an explicit likelihood, and bound unknowns by factoring them — never invent false precision.
When to Use
- Timeline, effort, or outcome forecasts where the true value is uncertain.
- Risk sizing for a change, migration, deploy, or launch.
- Any moment you are about to state a confident single number you cannot actually know.
- New evidence arrives and a prior estimate should move.
When NOT to Use
- The quantity is measurable or look-up-able — measure or look it up.
- The decision is invariant across the whole plausible range — skip the estimate and act.
- There is no real reference class and you would invent a base rate — label it a guess, not a calibrated forecast.
- You only need a binary gate and already have a decisive observation — do not pad with ceremony.
Procedure
- Define a checkable claim: outcome + timeframe + unit. Prefer a falsifiable statement over vague language ("likely").
- Lock a prior and challenge it: name a reference-class base rate and at least one credible alternative path/hypothesis with its rate. Pull the prior toward the base rate unless you write a concrete reason for deviation. Then state the strongest evidence-based case that your chosen prior or range is wrong, what estimate it supports, and revise if that countercase survives. Convert vague words to numbers (e.g. "likely" ≈ 65–80%).
- Express a range, not a point: give at least one confidence interval (50% and 80% preferred). Assume overconfidence; widen intervals when the outside view is thin.
- Update prior → likelihood → posterior when evidence arrives:
- Prior odds = p / (1 − p).
- Likelihood ratio LR = P(E|H) / P(E|¬H). LR > 1 supports H; LR = 1 is noise; LR < 1 undermines H.
- Posterior odds = prior odds × LR (multiply even when LR < 1); p = odds / (1 + odds).
- Strength bands for distance from 1: weak ~1.5–3×, moderate 3–10×, strong 10–100×, definitive 100×+.
- Yesterday's posterior is today's prior for the next evidence. For rare events, start from the base rate — vivid positives still leave most mass on false alarms.
- Fermi-bound unmeasured quantities (only when you need a magnitude you cannot measure/look up):
- Decompose: Quantity = Factor₁ × Factor₂ × … (or sum of components).
- Bound each factor with a range; use one-significant-figure geometric means for order-of-magnitude.
- Multiply; report "~X within 3–5×"; sanity-check whether a 10× error would change the decision; replace any factor that is actually lookup-able.
- Skip Fermi when the number is cheaply measurable, when the decision needs tighter than ~3–5× precision, or when every factor is pure invention.
- State the final estimate for checking: claim, range/CIs, key uncertainties, and the observation that would prove it wrong. Stop when the decision is stable across the remaining range or the next update needs new evidence you do not have.
Show full SKILL.md (163 more words)Show less
Output
- Claim — falsifiable statement with timeframe.
- Prior — base rate, alternative path, adjustment reason, strongest countercase, and resulting prior probability.
- Range — confidence intervals (not a lone point).
- Updates — each evidence row: prior, LR (or explicit heuristic Δ), posterior.
- Fermi bounds (if used) — factor product and "~X within N×".
- Decision implication — what changes if the true value is at the low vs high end of the range.
Verification
- Falsify/stop: if you cannot name a base rate, alternative, or serious countercase, label the estimate as a guess rather than calibrated. If the decision is unchanged across the full range, stop estimating. If new evidence arrives and the number does not move (or moves without an LR/Δ), recompute.
- Over-application guard: do not dress checkable facts as probabilities, invent reference classes, or Fermi-decompose quantities you can measure. Do not report three significant figures on a 5×-uncertain product. For rare events, refuse jumps from one vivid hit to near-certainty without the base-rate prior.
© tjboudreaux, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/thinking-probabilistic of tjboudreaux/cc-thinking-skills.
Open the folder on GitHubat commit 7b8fece
Compare with similar skills
Thinking Probabilistic next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Thinking Probabilistic this skilltjboudreaux/cc-thinking-skills | 1.6k | — | ~1.1k | Automated safety check: Pass | MIT | |
| TimesFM Forecastinggoogle-research/timesfm | 34k | — | ~4.7k | Automated safety check: Pass | Apache-2.0 | |
| StatsmodelszLanqing/codex-claude-academic-skills | 4.7k | 15 repos | ~4.9k | Automated safety check: Pass | BSD-3-Clause | |
| Timesfm ForecastingzLanqing/codex-claude-academic-skills | 4.7k | 3 repos | ~7.5k | Automated safety check: Notes | Apache-2.0 | |
| Find Hypertable Candidatestimescale/pg-aiguide | 1.9k | 1 repos | ~2.6k | Automated safety check: Pass | Apache-2.0 | |
| Pensieve Searcharkohut/pensieve | 1.4k | — | ~8.2k | Automated safety check: Pass | Apache-2.0 |
Similar skills
Statsmodels
zLanqing/codex-claude-academic-skills
Statistical models library for Python. An agent skill from zLanqing/codex-claude-academic-skills.
Timesfm Forecasting
zLanqing/codex-claude-academic-skills
Zero-shot time series forecasting with Google's TimesFM foundation model.
Find Hypertable Candidates
timescale/pg-aiguide
A skill your agent uses to analyze an existing PostgreSQL database and identify which tables should be converted to Timescale/TimescaleDB hypertables.
Pensieve Search
arkohut/pensieve
Search the user's local Pensieve screenshot archive by text, app, or time range.
Alphaear Predictor
ninehills/skills
Market prediction skill using Kronos. An agent skill from ninehills/skills.
More from tjboudreaux/cc-thinking-skills
All 26 skills in this repoThinking Bounded Rationality
tjboudreaux/cc-thinking-skills
A skill your agent uses when search or investigation could run forever.
Thinking Circle Of Competence
tjboudreaux/cc-thinking-skills
A skill your agent uses when a specific claim may lack grounding.
Thinking Lindy Effect
tjboudreaux/cc-thinking-skills
A skill your agent uses when longevity of a non-perishable option matters.
Thinking Via Negativa
tjboudreaux/cc-thinking-skills
A skill your agent uses when the reflex is to add a feature, layer, or process.
Thinking Cynefin
tjboudreaux/cc-thinking-skills
When the right response mode is unclear, classify the cause-effect domain first; decompose disorder.
Thinking Five Whys Plus
tjboudreaux/cc-thinking-skills
When a fault is localized and the proximate cause is known but the systemic root is not, chain evidence-linked whys with a counterfactual stop and a countermeasure.
Related
Categories
Questions about Thinking Probabilistic
What does Thinking Probabilistic do?
A skill your agent uses when forecasting, estimating, or sizing risk — anchor on base rates, give ranges, update prior→likelihood→posterior on evidence, and factor unmeasured quantities into…. Thinking Probabilistic is an agent skill from tjboudreaux/cc-thinking-skills. Use when forecasting, estimating, or sizing risk — anchor on base rates, give ranges, update prior→likelihood→posterior on evidence, and factor unmeasured quantities into order-of-magnitude bounds.
When should I use Thinking Probabilistic?
Thinking Probabilistic fits situations like: sizing risk — anchor on base rates; update prior→likelihood→posterior on evidence; factor unmeasured quantities into order-of-magnitude bounds.
How do I install Thinking Probabilistic in Claude Code?
Run `npx skills add tjboudreaux/cc-thinking-skills --skill thinking-probabilistic -a claude-code`. Or copy the skill folder (skills/thinking-probabilistic in tjboudreaux/cc-thinking-skills) into .claude/skills/thinking-probabilistic in your project. Claude Code loads it when a task matches its description.
How do I install Thinking Probabilistic in Codex?
Run `npx skills add tjboudreaux/cc-thinking-skills --skill thinking-probabilistic -a codex`. Or copy the skill folder (skills/thinking-probabilistic in tjboudreaux/cc-thinking-skills) into .agents/skills/thinking-probabilistic in your project. Codex loads it when a task matches its description.
Can I use Thinking Probabilistic in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add tjboudreaux/cc-thinking-skills --skill thinking-probabilistic -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/thinking-probabilistic, .gemini/skills/thinking-probabilistic, .github/skills/thinking-probabilistic and .opencode/skills/thinking-probabilistic in your project.
What does Thinking Probabilistic need to run?
SKILL.md names no scripts, command-line tools or credentials: Thinking Probabilistic is instructions for the agent only.
Does Thinking Probabilistic access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Thinking Probabilistic safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Thinking Probabilistic use?
Thinking Probabilistic is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Thinking Probabilistic use?
About 1.1k tokens (SKILL.md is roughly 4.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Thinking Probabilistic?
Skills that share tags, products or a category with Thinking Probabilistic: TimesFM Forecasting (google-research/timesfm, 34k stars), Statsmodels (zLanqing/codex-claude-academic-skills, 4.7k stars), Timesfm Forecasting (zLanqing/codex-claude-academic-skills, 4.7k stars) and Find Hypertable Candidates (timescale/pg-aiguide, 1.9k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Thinking Probabilistic?
tjboudreaux (a GitHub user) maintains it in tjboudreaux/cc-thinking-skills, which has 1,612 GitHub stars. The repository holds 26 skills in this directory. The repository was last updated on August 7, 2026.
Source: tjboudreaux/cc-thinking-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.