Agent skill

Focal Point Finder

by gnurio in gnurio/nurijanian-skills

This skill should be used when someone needs to find, propose, or evaluate a focal point in a coordination, negotiation, or alignment problem.

MITAuto-check passed

Install Focal Point Finder

skills CLI
$ npx skills add gnurio/nurijanian-skills --skill focal-point-finder -a claude-code

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

GitHub CLI
$ gh skill install gnurio/nurijanian-skills focal-point-finder --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/gnurio/nurijanian-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/focal-point-finder .claude/skills/focal-point-finder && 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
focal-point-finder
GitHub stars
124
Token cost
~3.2k tokens
SKILL.md length
1,684 words
Files
2 (incl. references)
Skills in repo
15
Repo updated
First seen
Licence
MIT

At a glance

This skill should be used when someone needs to find, propose, or evaluate a focal point in a coordination, negotiation, or alignment problem.

  • Works in 6 steps: Map the Coordination Problem → Scan for Existing Focal Points → Diagnose Why Convergence Is Failing (If… → …
  • Where should we align?
  • SKILL.md covers When to Use, Step 1: Map the Coordination…, Step 2: Scan for Existing… and Step 3: Diagnose Why…, plus 5 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Focal Point Finder is an agent skill from gnurio/nurijanian-skills. This skill should be used when someone needs to find, propose, or evaluate a focal point in a coordination, negotiation, or alignment problem. A focal point is a solution that people converge on without explicit agreement — because it is uniquely prominent, simple, or recognizable. Based on Thomas Schelling's "The Strategy of Conflict." Triggers on "where should we align?", "how do we get everyone on the same page?", "what's the obvious choice?", "find a focal point", "Schelling point", "coordination problem"…

Its SKILL.md is about 3.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/schelling-focal-points.md`).

The repository describes itself as: Claude Code and Cursor skills for product managers — PM coaching, verbalized sampling, tech sensemaking, and more. The licence is MIT.

When your agent uses it

  • Where should we align?
  • How do we get everyone on the same page?
  • Whats the obvious choice?
  • Find a focal point

Example prompts

  • “The Strategy of Conflict.”
  • “where should we align?”
  • “how do we get everyone on the same page?”
  • “/focal-point-finder”

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Map the Coordination Problem
  2. Scan for Existing Focal Points
  3. Diagnose Why Convergence Is Failing (If It Is)
  4. Create or Propose a Focal Point
  5. Stress-Test the Focal Point
  6. Present Recommendation

What it can do on your machine

Read from SKILL.md and the folder at commit 43a0566. 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

Focal Point Finder loads about 3.2k tokens when it runs, and up to ~5k if it reads all its reference files. Until then it costs about 186 tokens; SKILL.md has 1,684 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~186
When it runs · the whole SKILL.md, loaded when a task matches
~3.2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~5k

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 gnurio/nurijanian-skills at commit 43a0566, republished under its MIT licence (© gnurio). 1,684 words, ~3,223 tokens.

Download SKILL.mdSave it as .claude/skills/focal-point-finder/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
focal-point-finder
description
This skill should be used when someone needs to find, propose, or evaluate a focal point in a coordination, negotiation, or alignment problem. A focal point is a solution that people converge on without explicit agreement — because it is uniquely prominent, simple, or recognizable. Based on Thomas Schelling's "The Strategy of Conflict." Triggers on "where should we align?", "how do we get everyone on the same page?", "what's the obvious choice?", "find a focal point", "Schelling point", "coordination problem", "how do we agree without talking?", "what would everyone pick?", "propose a standard", "set a default", or any situation where multiple parties need to converge on a single choice without full communication.

Focal Point Finder

Identify, evaluate, or create focal points in coordination and negotiation problems using Thomas Schelling's framework from The Strategy of Conflict.

A focal point is not the objectively best outcome. It is the outcome that everyone expects everyone else to expect — the one choice that stands out enough for mutual recognition. The authority is in the expectations themselves, not in the thing expectations attach to.

When to Use

  • Multiple parties need to converge on a single choice (standard, deadline, meeting point, price, boundary, process)
  • Communication is limited, ambiguous, or costly
  • No formal authority can dictate the answer
  • A proposal needs to "stick" without enforcement
  • An existing default needs to be defended or displaced

Step 1: Map the Coordination Problem

Extract the structure of the situation by answering:

  1. Who are the parties? (List every actor who must align)
  2. What is being coordinated? (A location, a number, a standard, a boundary, a process, a date, a format)
  3. What are the communication constraints? (Full communication? Partial? Tacit? Asynchronous? Cross-cultural?)
  4. What happens if they fail to converge? (Cost of miscoordination — this determines urgency)
  5. Are interests aligned, divergent, or mixed? (Pure coordination, bargaining, or mixed-motive)

Present the map to the user for validation before proceeding.

Step 2: Scan for Existing Focal Points

Before proposing anything new, identify what focal points already exist. Check each source:

The Five Magnets

Uniqueness — Is there one option that stands alone, qualitatively different from all others? Test: "If not this, what?" — if there is no clear alternative, it is focal.

Example: On a map with many crossroads but one house, all 11 people who picked the house met. The 4 who picked crossroads each chose a different one and none met. Three houses would have destroyed the focal point — uniqueness avoids ambiguity.

Simplicity — Is there a clean, discrete option vs. many that differ only by degree? Test: "Can this be stated in one sentence without qualifiers?"

Example: Poison gas was not used in WWII despite no formal treaty. "No gas" is binary and unambiguous. "Some gas" (how much? where? against whom?) creates impossible coordination. The simplicity of total abstention made it the only tacitly achievable limit.

Precedent — Has this been done before in a similar situation? Is there a pattern everyone knows? Test: "What happened last time?"

Example: Middle Eastern oil royalties converged on the 50-50 formula within years of the first deal setting that pattern. Subsequent negotiations had "no heart left in the bargaining" under the shadow of that precedent.

Symmetry — Is there a mathematically or aesthetically balanced option (50-50, equal, round numbers)? Test: "Does this feel 'fair' by default?"

Example: Two strangers secretly divide $100 into piles A and B. If splits match, both keep $100. 36 out of 40 chose $50/$50 — not because it is fair, but because it is the only split both can be certain the other will also pick.

Cultural Salience — Is there something that this specific group of people would all recognize as obvious? Test: "Would a newcomer to this group guess the same answer?"

Example: "Meet somewhere in NYC, no instructions." Most chose Grand Central Station, information booth, 12 noon. The answer depends entirely on the people — a sample from Tokyo would converge elsewhere.

For each candidate focal point found, rate its strength:

  • Strong: passes 3+ magnet tests, no competing focal points
  • Moderate: passes 1-2 magnet tests, one or two competitors
  • Weak: arguable, multiple equally valid alternatives exist

If a strong focal point already exists, present it and stop. The user's job is to recognize it, not to invent a new one.

Step 3: Diagnose Why Convergence Is Failing (If It Is)

If there is no existing focal point or the obvious one is being ignored, diagnose why:

SymptomLikely CauseSchelling Remedy
Too many options, no one commitsNo option has qualitative uniquenessStrip away options until one stands alone
Everyone has a different "obvious" answerCultural salience differs across partiesFind common ground — shared precedent, shared reference points
The obvious answer is unfair to one partyThe focal point discriminatesAccept it if miscoordination is worse, or find an equally prominent alternative
Someone introduced conflicting dataNoise is drowning the signalSimplify: remove extraneous variables
The old default was breachedPrecedent was broken without a replacementEstablish a new bright line quickly, before the vacuum fills with chaos
Agreement in principle, but endless debate on degreeTrying to compromise on a continuumFind a qualitative boundary (river, not "some miles")

Step 4: Create or Propose a Focal Point

When no natural focal point exists, create one using these techniques (ordered by reliability).

Key principle: finding a focal point requires imagination, not just logic. Schelling notes that "poets may do better than logicians at this game, which is perhaps more like 'puns and anagrams' than like chess." Accidental arrangements, humor, and even whimsy can become focal if they are the only things that stand out.

4a. Be First (Unilateral Innovation)

Make a visible, specific proposal before anyone else does. Even a mediocre proposal gains power from being the only proposal.

"The strongest argument in favor of R is the rhetorical question, 'If not R, what then?'"

Requirements for this to work:

  • The proposal must be visible to all parties
  • It must be specific (not vague)
  • It must remain unchallenged long enough to acquire default status
4b. Use a Mediator or Third Party

Recruit someone respected by all parties to make a "dramatic suggestion." The suggestion fills the vacuum of indeterminacy.

The mediator's power comes not from the quality of the suggestion but from the fact that it exists. A traffic cop at a jammed intersection helps even the drivers most disadvantaged by the routing.

4c. Frame the Problem

Reformulate the situation to make a favorable outcome appear as the "obvious" choice:

  • Choose which data to present (income figures → proportional split)
  • Choose which precedents to invoke
  • Choose which analogies to draw
  • Name the problem in a way that implies the answer
Show full SKILL.md (688 more words)Show less
4d. Introduce Noise (Defensive)

If the existing focal point is unfavorable, flood the situation with additional variables until the old signal is drowned out and parties retreat to a simpler default (often 50-50).

4e. Find a Qualitative Boundary

Replace "how much?" questions with "which category?" questions. Continuous variables have no focal point. Discrete categories do.

  • Bad: "How much budget should marketing get?" (any percentage is defensible)
  • Good: "Should marketing own the launch budget, yes or no?" (binary = focal)
  • Bad: "How many weapons are acceptable?" (any number is debatable)
  • Good: "Nuclear or conventional?" (bright line = focal)
4f. Act, Don't Talk (Moves as Signals)

In strategic conflict, actions authenticate intentions more than words. Incur a visible cost or risk to make a proposal credible. A team that migrates its codebase to a new framework before the "standards meeting" has created a focal point through action, not argument.

4g. Leverage Irrelevant Alternatives

An option that is not even available can still magnetize expectations. The "shadow" of a 50-50 split coordinates expectations even when the rules make an exact 50-50 impossible. When proposing a focal point, reference a familiar benchmark even if it cannot be achieved exactly — it pulls the final answer toward it.

Step 5: Stress-Test the Focal Point

Before presenting the proposed focal point, verify it passes these tests:

  1. The "If Not Here, Where?" Test: If this focal point is rejected, is there an equally obvious alternative? If yes, it is too weak.
  2. The Newcomer Test: Would someone unfamiliar with the negotiation history arrive at the same answer from the situation alone?
  3. The Breach Test: If someone violates this focal point, would everyone notice? If the violation is ambiguous, the focal point is not crisp enough.
  4. The Concession Test: Can this focal point survive small adjustments? (Focal points that depend on exact numbers like 50% collapse if compromised to 47%. This is a feature, not a bug — it makes them harder to erode.)
  5. The Stability Test: Once established, does this focal point create a groove that makes future coordination easier?

Anti-Patterns — Check Output Against These

Before presenting a recommendation, verify it does not fall into these traps:

Optimizing instead of coordinating. The recommendation proposes the "best" answer instead of the most recognizable one. A territory split along the most equitable population line is objectively better than the river — but nobody can independently identify the same equitable line. The river wins because both sides can find it without talking.

Bad: "Divide the region by population density, giving each side roughly equal citizens." Good: "The river. It is the only line both sides will independently draw."

Proposing quantitative limits on a continuum. The recommendation suggests a specific number or percentage when a qualitative boundary exists. Nuance kills coordination — any number can slide to the next number.

Bad: "Limit chemical weapons to 50kg per engagement with monitoring provisions." Good: "No chemical weapons. Binary, unambiguous, no negotiation needed."

Offering multiple options. The recommendation presents 3 "equally good" alternatives and asks the user to choose. The entire purpose of a focal point is singularity — one answer that commands attention by having no competitor. Presenting options is the opposite of finding a focal point.

Bad: "Here are three viable pricing models: per-seat, per-action, or flat monthly." Good: "Per-seat monthly. It has the most precedent from adjacent SaaS. The others may be better, but this is the one everyone will independently guess."

Ignoring discrimination. The recommendation rejects a focal point because it is "unfair" to one party, when the cost of miscoordination is worse than the unfairness. Schelling: "beggars cannot be choosers about the source of their signal." A discriminatory focal point that coordinates is often better than a fair proposal that nobody can independently identify.

Bad: "The river disadvantages the eastern population, so we should find a more equitable line." Good: "The river disadvantages the east, but the 15 people who tried to draw a 'fairer' line produced 14 different answers. The river is the only line that works."

Step 6: Present Recommendation

Structure the output as:

## Focal Point Analysis

**Situation**: [One-sentence description of the coordination problem]
**Parties**: [Who must align]
**Stakes of Miscoordination**: [What happens if they fail to converge]

### Existing Focal Points
[List any found in Step 2 with strength ratings]

### Diagnosis
[If convergence is failing, why — from Step 3]

### Recommended Focal Point
[The specific proposal]

**Why this works**:
- [Which magnets it activates: uniqueness, simplicity, precedent, symmetry, cultural salience]
- [Why alternatives are weaker]

**How to establish it**:
- [Which technique from Step 4: be first, mediator, framing, noise, qualitative boundary]
- [Specific actions to take]

**Risks**:
- [What could undermine it]
- [What happens if it is breached]

**Stress Test Results**:
- If Not Here, Where? → [pass/fail]
- Newcomer Test → [pass/fail]
- Breach Test → [pass/fail]
- Concession Test → [pass/fail]
- Stability Test → [pass/fail]

Reference Material

For detailed source quotes, examples, and the full Schelling methodology, read references/schelling-focal-points.md.

© gnurio, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (references) in skills/focal-point-finder of gnurio/nurijanian-skills.

  • SKILL.md
  • references/schelling-focal-points.md

Open the folder on GitHubat commit 43a0566

Compare with similar skills

Focal Point Finder 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.

Focal Point Finder compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Focal Point Finder this skillgnurio/nurijanian-skills124—~3.2kAutomated safety check: PassMIT
Sponsor Findergithub/awesome-copilot40k1 repos~3kAutomated safety check: PassMIT
Flutter PR Checks Finderflutter/flutter180k—~1.3kAutomated safety check: PassBSD-3-Clause
Smart Contract Entry Point Analyzertrailofbits/skills7.5k1 repos~2.4kAutomated safety check: NotesCC-BY-SA-4.0
Extension PointsBuilderIO/agent-native7.1k—~2.4kAutomated safety check: PassNone
Extension Pointsdotnet/skills5.6k1 repos~2.9kAutomated safety check: PassMIT

Similar skills

  • Sponsor Finder

    github/awesome-copilot

    Official

    Find which of a GitHub repository's dependencies are sponsorable via GitHub Sponsors.

    40k GitHub starsUsed in 1 repo~3k tokens
    Productivity & AutomationAuto-check passed
  • Find failing checks on a Flutter PR and locate the corresponding LUCI log URLs.

    180k GitHub stars~1.3k tokensUpdated today
    MobileAuto-check passed
  • Official

    Maps the state-changing entry points of a smart contract codebase and sorts them by access level, producing a structured audit report that leaves out read-only functions.

    7.5k GitHub starsUsed in 1 repo~2.4k tokens
    SecurityAuto-check: notes
  • Extension Points

    BuilderIO/agent-native

    How extensions render as widgets inside other apps via named UI slots — the framework's optional extension system.

    7.1k GitHub stars~2.4k tokensUpdated yesterday
    Auto-check passed
  • Extension Points

    dotnet/skills

    Official

    Own MSBuild import and hook discovery. An agent skill from dotnet/skills.

    5.6k GitHub starsUsed in 1 repo~2.9k tokens
    Auto-check passed
  • Data Finder

    brycewang-stanford/Auto-Empirical-Research-Skills

    Find and assess datasets for a research question. An agent skill from brycewang-stanford/Auto-Empirical-Research-Skills.

    4.6k GitHub stars~1.7k tokensUpdated 5 days ago
    Research & ScienceAuto-check passed

More from gnurio/nurijanian-skills

All 15 skills in this repo
  • Vibe Code Leaf Finder

    gnurio/nurijanian-skills

    This skill should be used when a user wants to identify which parts of a codebase are safe to modify with AI ("vibe code") and which require careful human engineering.

    124 GitHub stars~1.9k tokensUpdated 1 mo ago
    Auto-check: notes
  • Corporate Misalignment Finder

    gnurio/nurijanian-skills

    Find, diagnose, and fix misalignment in corporate settings. An agent skill from gnurio/nurijanian-skills.

    124 GitHub stars~2.1k tokensUpdated 1 mo ago
    Auto-check passed
  • Verbalized Sampling

    gnurio/nurijanian-skills

    Generate diverse outputs by prompting for a probability distribution instead of a single response.

    124 GitHub stars~2k tokensUpdated 1 mo ago
    Auto-check: warnings
  • Orchestrate Pm Alignment

    gnurio/nurijanian-skills

    PM alignment coach and router. An agent skill from gnurio/nurijanian-skills.

    124 GitHub stars~1.5k tokensUpdated 1 mo ago
    Auto-check passed
  • Tech Sensemaking

    gnurio/nurijanian-skills

    Analyze technology announcements to surface non-obvious strategic implications using Verbalized Sampling.

    124 GitHub stars~1.8k tokensUpdated 1 mo ago
    Auto-check passed
  • Adversarial Roleplay

    gnurio/nurijanian-skills

    PM stress-test roleplay. An agent skill from gnurio/nurijanian-skills.

    124 GitHub stars~1.8k tokensUpdated 1 mo ago
    Auto-check passed

Questions about Focal Point Finder

What does Focal Point Finder do?

This skill should be used when someone needs to find, propose, or evaluate a focal point in a coordination, negotiation, or alignment problem. Focal Point Finder is an agent skill from gnurio/nurijanian-skills. This skill should be used when someone needs to find, propose, or evaluate a focal point in a coordination, negotiation, or alignment problem.

When should I use Focal Point Finder?

Focal Point Finder fits situations like: where should we align?; how do we get everyone on the same page?; whats the obvious choice?; find a focal point.

How do I install Focal Point Finder in Claude Code?

Run `npx skills add gnurio/nurijanian-skills --skill focal-point-finder -a claude-code`. Or copy the skill folder (skills/focal-point-finder in gnurio/nurijanian-skills) into .claude/skills/focal-point-finder in your project. Claude Code loads it when a task matches its description.

How do I install Focal Point Finder in Codex?

Run `npx skills add gnurio/nurijanian-skills --skill focal-point-finder -a codex`. Or copy the skill folder (skills/focal-point-finder in gnurio/nurijanian-skills) into .agents/skills/focal-point-finder in your project. Codex loads it when a task matches its description.

Can I use Focal Point Finder 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 gnurio/nurijanian-skills --skill focal-point-finder -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/focal-point-finder, .gemini/skills/focal-point-finder, .github/skills/focal-point-finder and .opencode/skills/focal-point-finder in your project.

What does Focal Point Finder need to run?

SKILL.md names no scripts, command-line tools or credentials: Focal Point Finder is instructions for the agent only.

Does Focal Point Finder 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 Focal Point Finder 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 Focal Point Finder use?

Focal Point Finder 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 Focal Point Finder use?

About 3.2k tokens (SKILL.md is roughly 13k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.8k tokens, read only when the agent opens those files.

What are the alternatives to Focal Point Finder?

Skills that share tags, products or a category with Focal Point Finder: Sponsor Finder (github/awesome-copilot, 40k stars), Flutter PR Checks Finder (flutter/flutter, 180k stars), Smart Contract Entry Point Analyzer (trailofbits/skills, 7.5k stars) and Extension Points (BuilderIO/agent-native, 7.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Focal Point Finder?

gnurio (a GitHub user) maintains it in gnurio/nurijanian-skills, which has 124 GitHub stars. The repository holds 15 skills in this directory. The repository was last updated on August 13, 2026.

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