New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Adverse Selection Prior

by lyndonkl in lyndonkl/claude

Produces a Bayesian prior probability that an offered transaction is +EV for the recipient, given that the counterparty chose to propose it.

No licenceAuto-check passed

Install Adverse Selection Prior

skills CLI
$ npx skills add lyndonkl/claude --skill adverse-selection-prior -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install lyndonkl/claude adverse-selection-prior --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/lyndonkl/claude.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/adverse-selection-prior .claude/skills/adverse-selection-prior && rm -rf skills-src

Use ~/.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/

Facts

Skill name
adverse-selection-prior
GitHub stars
164
Token cost
~4.6k tokens
SKILL.md length
1,993 words
Files
4
Skills in repo
12
Repo updated
First seen
Licence
None found

At a glance

Produces a Bayesian prior probability that an offered transaction is +EV for the recipient, given that the counterparty chose to propose it.

  • Works in 10 steps: Base prior is always below 0.50 for… → "Seems fair" = "probably bad".… → Do not double-count adjustments. If you… → …
  • You receive an unsolicited trade/offer/proposal
  • SKILL.md covers Table of Contents, Example, Workflow and Common Patterns, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Adverse Selection Prior is an agent skill from lyndonkl/claude. Produces a Bayesian prior probability that an offered transaction is +EV for the recipient, given that the counterparty chose to propose it. Applies Akerlof market-for-lemons logic -- if they offered it, they believe it is +EV for them, so the prior that it is +EV for us is materially below 50%. Reusable across trade evaluation, waiver drops (another team dropping a player is also adverse selection), job-offer analysis, M&A, and any "someone offered me this" situation. Use when you receive an unsolicited…

Its SKILL.md is about 4.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files (for example `resources/evaluators/rubric_adverse_selection_prior.json`, `resources/methodology.md` and `resources/template.md`).

The repository describes itself as: Agents, skills and anything else to use with claude.

When your agent uses it

  • You receive an unsolicited trade/offer/proposal
  • Analyzing incoming trade prior
  • Evaluating why a counterparty proposed a deal
  • User mentions adverse selection

Example prompts

  • “someone offered me this”
  • “Use the adverse-selection-prior skill to produce a Bayesian prior probability that an offered transaction is +EV for the recipient, given that the…”
  • “/adverse-selection-prior”

Workflow steps

10 steps, taken from the first numbered list in SKILL.md.

  1. Base prior is always below 0.50 for received offers. This is the core of the market-for-lemons insight. If your prior exceeds 0.50, you…
  2. "Seems fair" = "probably bad". Counterparties who propose transactions have selected them from the space of possible transactions. A…
  3. Do not double-count adjustments. If you have already adjusted your own EV for known information (e.g., you penalized the player because…
  4. Clip priors to [0.10, 0.70]. Priors outside this band are almost always specification errors. A 0.05 prior implies near-certainty of a…
  5. Archetype signal comes from behavior, not self-report. A counterparty who claims to be a "casual player" but has made 40 waiver claims and…
  6. Panic-sell signals must be triangulated. "They seem frustrated" is not sufficient to raise the prior. Require at least two of: recent…
  7. Repeated-game reputation adjusts the prior. If you have cooperated with this counterparty 5+ times and they have never sent a -EV offer…
  8. Override hints must be actionable and specific. "Do more research" is not a hint. "If the team's closer has been pulled from the role this…
  9. The recommended adjustment is multiplicative, not additive. Downstream consumers apply adjusted_EV = own_EV x recommended_adjustment. Do…
  10. This skill produces a prior, not a verdict. Downstream decision logic (accept/counter/reject) belongs in the consumer skill (e.g…

What it can do on your machine

Read from SKILL.md and the folder at commit 4acc337. 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 (its code samples are json).

    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

Adverse Selection Prior loads about 4.6k tokens when it runs. Until then it costs about 200 tokens; SKILL.md has 1,993 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~200
When it runs · the whole SKILL.md, loaded when a task matches
~4.6k

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

Without a licence we can't republish the file, so here is its outline and opening line. It has 1,993 words (~4,565 tokens).

“Scenario: We receive a fantasy trade offer. Opponent (classified active archetype) offers us a star hitter (their side) for two of our mid-tier hitters (our side). On surface the offer looks roughly fair -- our own projection model says the…”

— opening of SKILL.md by lyndonkl
name
adverse-selection-prior

Read the full SKILL.md on GitHub

Files

SKILL.md and 3 other files in skills/adverse-selection-prior of lyndonkl/claude.

  • SKILL.md
  • resources/evaluators/rubric_adverse_selection_prior.json
  • resources/methodology.md
  • resources/template.md

Open the folder on GitHubat commit 4acc337

Compare with similar skills

Adverse Selection Prior 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.

Adverse Selection Prior compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Adverse Selection Prior this skilllyndonkl/claude164—~4.6kAutomated safety check: PassNone
Offerssickn33/agentic-awesome-skills47k1 repos~2.4kAutomated safety check: PassMIT
Offer Appointmentsickn33/agentic-awesome-skills47k1 repos~3.9kAutomated safety check: PassMIT
PyMC Bayesian Modelingdavila7/claude-code-templates33k11 repos~3.9kAutomated safety check: PassMIT
Offer Negotiationreactive-resume/reactive-resume44k—~10kAutomated safety check: PassMIT
Screen Adverse Mediasickn33/agentic-awesome-skills47k1 repos~1.1kAutomated safety check: PassApache-2.0

Similar skills

  • Offers

    sickn33/agentic-awesome-skills

    When the user wants to design, construct, or improve an offer — the thing they actually sell — including value framing, bonus stacking, guarantee design, scarcity/urgency, naming, and payment…

    47k GitHub starsUsed in 1 repo~2.4k tokens
    Auto-check passed

  • Offer Appointment

    sickn33/agentic-awesome-skills

    Offer register: candidate, position, department, employment type, offered salary and currency, offer date and expiry, joining date, probation, approver and sign-off.

    47k GitHub starsUsed in 1 repo~3.9k tokens
    Auto-check passed

  • PyMC Bayesian Modeling

    davila7/claude-code-templates

    Builds, fits, checks and compares Bayesian models in PyMC, from priors and NUTS sampling to variational inference, LOO and WAIC comparison, and diagnostics.

    33k GitHub starsUsed in 11 repos~3.9k tokens
    Data & AnalyticsAuto-check passed

  • Offer Negotiation

    reactive-resume/reactive-resume

    Evaluates and negotiates job offers. An agent skill from reactive-resume/reactive-resume.

    44k GitHub stars~10k tokensUpdated today
    Business, Finance & HRAuto-check passed

  • Screen Adverse Media

    sickn33/agentic-awesome-skills

    Screen a person or organisation for adverse media coverage, PEP status, and sanctions exposure — corroboration-gated, returns "review" never "guilty".

    47k GitHub starsUsed in 1 repo~1.1k tokens
    SecurityAuto-check passed

  • Offer Comparison Analyzer

    davila7/claude-code-templates

    Compare multiple job offers side-by-side with total compensation analysis.

    33k GitHub starsUsed in 2 repos~2.3k tokens
    Business, Finance & HRAuto-check passed

More from lyndonkl/claude

All 12 skills in this repo

  • Abstraction Concrete Examples

    lyndonkl/claude

    Builds structured abstraction ladders that translate high-level principles into concrete, actionable examples across 3-5 levels.

    164 GitHub stars~1.1k tokensUpdated 1 mo ago
    Auto-check passed

  • Academic Letter Architect

    lyndonkl/claude

    Guides the creation of evidence-based academic recommendation letters, reference letters, and award nominations that combine concrete examples, meaningful comparisons, and genuine enthusiasm.

    164 GitHub stars~2.5k tokensUpdated 1 mo ago
    Auto-check passed

  • Adr Architecture

    lyndonkl/claude

    Documents significant architectural and technical decisions with full context, alternatives considered, trade-offs analyzed, and consequences understood.

    164 GitHub stars~1.5k tokensUpdated 1 mo ago
    Auto-check passed

  • Alignment Values North Star

    lyndonkl/claude

    Creates actionable alignment frameworks that give teams a shared North Star (direction), values (guardrails), and decision tenets (behavioral standards).

    164 GitHub stars~1.6k tokensUpdated 1 mo ago
    Auto-check passed

  • Analogy Weight Check

    lyndonkl/claude

    For every analogy in a substacker draft, verifies it carries mechanical weight — the analogy does real work explaining the mechanism, not merely decorates it.

    164 GitHub stars~1.1k tokensUpdated 1 mo ago
    Auto-check passed

  • Anomaly Fraud Scanner

    lyndonkl/claude

    Scans transactions for fraud and anomaly signals — duplicate charges within 48 hours, transactions more than 3 standard deviations above a merchant's historical average, first-ever transaction with…

    164 GitHub stars~2k tokensUpdated 1 mo ago
    Auto-check passed

Questions about Adverse Selection Prior

What does Adverse Selection Prior do?

Produces a Bayesian prior probability that an offered transaction is +EV for the recipient, given that the counterparty chose to propose it. Adverse Selection Prior is an agent skill from lyndonkl/claude. Produces a Bayesian prior probability that an offered transaction is +EV for the recipient, given that the counterparty chose to propose it.

When should I use Adverse Selection Prior?

Adverse Selection Prior fits situations like: you receive an unsolicited trade/offer/proposal; analyzing incoming trade prior; evaluating why a counterparty proposed a deal; user mentions adverse selection.

How do I install Adverse Selection Prior in Claude Code?

Run `npx skills add lyndonkl/claude --skill adverse-selection-prior -a claude-code`. Or copy the skill folder (skills/adverse-selection-prior in lyndonkl/claude) into .claude/skills/adverse-selection-prior in your project. Claude Code loads it when a task matches its description.

How do I install Adverse Selection Prior in Codex?

Run `npx skills add lyndonkl/claude --skill adverse-selection-prior -a codex`. Or copy the skill folder (skills/adverse-selection-prior in lyndonkl/claude) into .agents/skills/adverse-selection-prior in your project. Codex loads it when a task matches its description.

Can I use Adverse Selection Prior 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 lyndonkl/claude --skill adverse-selection-prior -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/adverse-selection-prior, .gemini/skills/adverse-selection-prior, .github/skills/adverse-selection-prior and .opencode/skills/adverse-selection-prior in your project.

What does Adverse Selection Prior need to run?

SKILL.md names no scripts, command-line tools or credentials: Adverse Selection Prior is instructions for the agent only.

Does Adverse Selection Prior 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 Adverse Selection Prior 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 Adverse Selection Prior use?

No licence was found for Adverse Selection Prior or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Adverse Selection Prior use?

About 4.6k tokens (SKILL.md is roughly 18k 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 Adverse Selection Prior?

Skills that share tags, products or a category with Adverse Selection Prior: Offers (sickn33/agentic-awesome-skills, 47k stars), Offer Appointment (sickn33/agentic-awesome-skills, 47k stars), PyMC Bayesian Modeling (davila7/claude-code-templates, 33k stars) and Offer Negotiation (reactive-resume/reactive-resume, 44k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Adverse Selection Prior?

lyndonkl (a GitHub user) maintains it in lyndonkl/claude, which has 164 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on September 1, 2026.

Source: lyndonkl/claude on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.