Index of every page on this site: llms.txt
All skills
tristanmanchester avatar

/wordly-wisdom

@3323bc9
by Tristan Manchestertristanmanchester/agent-skills3 stars
2
Run it yourself

Analyse consequential choices with outside views, incentives, inversion, scenario arithmetic, opportunity costs, and explicit update conditions. Use for decision memos, premortems, strategy choices, or a requested red-team; not routine factual questions or a reason to overanalyse a small decision.

Use this Skill: https://skilld.dev/gh/tristanmanchester/agent-skills/wordly-wisdom

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

referencesportability-and-adaptation.md

≈319 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Portability and adaptation

Use the host's available tools without assuming a particular model, IDE, shell, or scheduler. Resolve bundled scripts from the installed skill directory. The core decision method does not depend on Python; the optional strict arithmetic helpers need Python 3.10+ and accept only --input, returning JSON on stdout.

Without executable helpers, use an available calculator or work through a small model explicitly. Apply the same fixed-anchor and scenario checks rather than silently reverting to option-dependent min-max scaling. Do not invent missing scores, probabilities, or a base rate to make the arithmetic possible.

Fresh sources are necessary for claims that could have changed. When retrieval is unavailable, use the provided evidence and state the remaining limitation; do not imply an outside view was established. Facts, assumptions, and judgement remain distinct regardless of tool access.

Adapt the final response to the requested depth and format. Give the decision, decisive evidence, main risk, and update condition without forcing every long reference's heading or model count. A written update trigger is not an active monitor or reminder. No external action follows from a recommendation without the user's authorisation.

Source: SKILL.md on GitHub

Skill behaviors

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

Third-party checks

2 warnings1mo5 checks · Risk MEDIUM
  • Gen Agent Trust Hub1mo

    The skill provides a framework for decision analysis using mental models and local Python scripts. It is flagged as medium risk due to metadata poisoning, as it claims to be authored by 'openai' while originating from an unrelated developer 'tristanmanchester'. Additionally, the skill's ingestion of untrusted user data for decision memos and script processing creates a surface for indirect prompt injection and potential arbitrary file writes.

  • Socket1mo

    No alerts

  • Snyk1mo

    Risk: LOW · No issues

  • Runlayer7mo

    1/16 files flagged

  • ZeroLeaks6mo

    Score: 93/100 · 2 sections analyzed

Provenance

Signed by skilld at 3323bc9. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 2 weeks ago.

Steadyupdated last month

Capability

Other metadata
compatibility
Core reasoning needs no special tools. Optional arithmetic helpers require Python 3.10+ and use only the standard library. Time-sensitive or specialised claims require current relevant sources.
metadata
{
  "version": "4.0.0",
  "reviewed": "2026-09-13",
  "source-book": "Poor Charlie's Almanack"
}

README badge

README badge for tristanmanchester/agent-skills/wordly-wisdom