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

Prompt Proximity Architecture

by elvisun in elvisun/newsjack

Turn an approved measurement charter, ICPs, and buyer jobs into a budget-aware prompt coverage blueprint across proximity bands, aided status, information acts, journey states, roles, locales…

MITAuto-check passed

Install Prompt Proximity Architecture

skills CLI
$ npx skills add elvisun/newsjack --skill prompt-proximity-architecture -a claude-code

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

GitHub CLI
$ gh skill install elvisun/newsjack prompt-proximity-architecture --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/elvisun/newsjack.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/prompt-proximity-architecture .claude/skills/prompt-proximity-architecture && 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
prompt-proximity-architecture
GitHub stars
1.5k
Token cost
~1.9k tokens
SKILL.md length
769 words
Files
1
Skills in repo
30
Repo updated
First seen
Licence
MIT

At a glance

Turn an approved measurement charter, ICPs, and buyer jobs into a budget-aware prompt coverage blueprint across proximity bands, aided status, information acts, journey states, roles, locales…

  • SKILL.md covers Inputs, Keep dimensions independent, Assign proximity and Allocate coverage, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Prompt Proximity Architecture is an agent skill from elvisun/newsjack. Turn an approved measurement charter, ICPs, and buyer jobs into a budget-aware prompt coverage blueprint across proximity bands, aided status, information acts, journey states, roles, locales, evidence grades, partitions, and measurement lanes. Use before prompt wording to define required, optional, and prohibited canonical intent cells.

Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: The open-source skills that turn your agent into a full PR team. The licence is MIT.

Example prompts

  • “/prompt-proximity-architecture”

What it can do on your machine

Read from SKILL.md and the folder at commit b5a8dc8. 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

Prompt Proximity Architecture loads about 1.9k tokens when it runs. Until then it costs about 92 tokens; SKILL.md has 769 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~92
When it runs · the whole SKILL.md, loaded when a task matches
~1.9k

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 elvisun/newsjack at commit b5a8dc8, republished under its MIT licence (© elvisun). 769 words, ~1,937 tokens.

Download SKILL.mdSave it as .claude/skills/prompt-proximity-architecture/SKILL.md (or your agent's skills folder).
name
prompt-proximity-architecture
description
Turn an approved measurement charter, ICPs, and buyer jobs into a budget-aware prompt coverage blueprint across proximity bands, aided status, information acts, journey states, roles, locales, evidence grades, partitions, and measurement lanes. Use before prompt wording to define required, optional, and prohibited canonical intent cells.
metadata.category
AI visibility

Prompt Proximity Architecture

Design the cells before writing the strings.

This skill inherits the ethical floor from skills/ETHICS.md. It enforces anti-hallucination and evidence-bound coverage. Anti-spray and human-send are not applicable.

Inputs

Require:

  • a measurement charter;
  • approved icp_hypotheses.json and buyer_jobs.json;
  • target run/review budget;
  • required locales, surfaces, and lanes;
  • any campaign partition and prior-panel constraints.

If the charter is provisional, design a provisional architecture and name the gaps. Reject a charter that says only “track AI visibility.”

Keep dimensions independent

Each intent cell fixes:

  • buyer job;
  • information act;
  • journey state;
  • material constraints;
  • persona or buying role;
  • locale and language;
  • prompt-proximity band;
  • expected answer kind.

Add independent tags for evidence grade, partition, lane eligibility, turn form, and optional funnel. Do not make funnel the schema.

Use the supported acts explain, diagnose, plan, generate, compare, recommend, verify, navigate, buy, implement, and troubleshoot. Include only acts entailed by the job evidence.

Use journey states problem_identification, exploration, requirements_building, supplier_selection, adoption, and post_purchase.

Assign proximity

BandNameStructureDefault aided status
B0_direct_brand_productBrandNames target brand/product; asks about facts, fit, use, reputation, support, or implementationtarget_aided
B1_comparison_purchaseShortlistShortlist, recommendation, alternatives, pricing, requirements, or comparisonunaided; competitor_aided when only competitors are supplied; target_aided for a declared target-vs-competitor comparison
B2_categoryCategoryNames an accepted solution category, not the targetcategory_aided
B3_problem_needProblemDescribes pain, risk, trigger, or constraint without category/targetunaided
B4_job_goalGoalAsks for progress/outcome without supplying a solution categoryunaided
B5_broad_discovery_storyMarketTrend, event, regulation, practice, or narrative connected to the jobunaided

Use the code in prompt_architecture.json and the name in every Markdown summary. The band codes are labels for structurally different prompts, not points on a scale: do not write "B4" in prose, do not order or average them, and do not describe one band as further along than another. See "Display names" in ../build-ai-visibility-panel/references/artifact-contracts.md.

Bands and aided status are correlated by construction — Brand is always target_aided, Category always category_aided, and Problem, Goal and Market are always unaided, so only Shortlist splits. Report the two together rather than as if they were independent findings, and do not present a band breakdown that merely restates the prompted split.

campaign_exposed is an independent flag. Never combine target-aided, competitor-aided, category-aided, unaided, or campaign-exposed cells in one denominator.

Because aided_status is single-valued, a B1 prompt naming both the target and a competitor is target_aided; record the competitor stimulus in the contamination exception and keep the cell in the aided partition. A B1 prompt naming competitors but not the target is competitor_aided.

Do not assign funnel mechanically:

  • B0 can be post-purchase, not BOFU.
  • B3 can describe an urgent funded decision.
  • B1 can be early exploration.
  • funnel may be null.

B5 requires fresh dated public evidence and a decay/refresh rule.

The charter's product/capability perimeter is also a coverage dimension. For every named area, create at least one evidence-supported job/cell or a coverage_gap with an exclusion/waiver and the evidence needed. Never silently omit a named area.

Show full SKILL.md (284 more words)Show less

Allocate coverage

Cover every dimension that the evidence supports, not every Cartesian combination. Never generate a full persona × locale × act × constraint grid.

For a diagnostic default, target 30–48 unique unaided cells, two variants per cell, and three repeats per wave. For a standard panel, target 60–120 cells. Adjust to the user's budget and keep aided cells outside the unaided quota.

Stratify minimums and targets across:

  • B0–B5 where evidence supports each band;
  • job, journey, and information act;
  • ICP/role and materially distinct locale;
  • evidence grade/source type;
  • core, rotating, sentinel, control, and aided partitions;
  • closed-model, retrieval, consumer-surface, and campaign lanes.

Protect underrepresented but decision-relevant strata. Grade-D cells are rotating discovery until independently validated or explicitly promoted.

When the budget cannot meet required coverage, return an allocation conflict. Do not silently drop a band, role, locale, or control.

Prohibit unsupported cells

Mark a cell prohibited when it:

  • changes an informational need into a recommendation solely to elicit brands;
  • introduces a category not supported by the job evidence;
  • treats a competitor-named prompt as unaided;
  • uses target/campaign copy outside the allowed aided lane;
  • assumes translation is locale equivalence;
  • derives a core cell from current AI answers or target pages;
  • exceeds the declared sampling budget without a waiver.

Output

Give a Markdown coverage summary first: required dimensions, planned counts, gaps, conflicts, and why each missing band is unsupported.

Then write prompt_architecture.json:

json
{
  "schema_version": "1.0.0",
  "artifact_id": "architecture-<stable-slug>",
  "created_at": "RFC3339",
  "created_by": "declared agent or human",
  "source_manifest_hash": null,
  "warnings": ["hash_not_computed: compute source_manifest_hash before freeze"],
  "cells": [
    {
      "cell_spec_id": "spec-001",
      "job_id": "job-001",
      "icp_ids": ["icp-001"],
      "proximity_band": "B3_problem_need",
      "aided_status": "unaided",
      "campaign_exposed": false,
      "information_act": "diagnose",
      "journey_state": "problem_identification",
      "funnel": null,
      "persona_id": "role-001",
      "locale": "en-CA",
      "language": "en",
      "material_constraints": [],
      "expected_answer_kind": "diagnosis_and_options",
      "turn_form": "single_turn",
      "lane_eligibility": ["closed_model", "retrieval"],
      "partition": "core",
      "evidence_grade": "A",
      "target_variants": 2,
      "required": true,
      "reason_source_ids": ["source-001"]
    }
  ],
  "prohibited_cells": [],
  "allocation": {
    "core_cells": 36,
    "rotating_cells": 8,
    "sentinel_cells": 12,
    "control_cells": 0,
    "aided_cells": 6,
    "budget_status": "within_budget | conflict | waived"
  }
}

Before handoff, require every cells[].job_id and every cells[].icp_ids[] to resolve exactly. There is one authoritative field for each relationship. Never leave a stale ID and add a compensating alias such as job_id_authoritative; rewrite the cell or stop with an allocation/reference error.

Handoff

Pass the architecture plus a target-free blind brief to realistic-prompt-generation. Keep the contamination register outside the generator's context.

© elvisun, 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/prompt-proximity-architecture of elvisun/newsjack.

Open the folder on GitHubat commit b5a8dc8

Compare with similar skills

Prompt Proximity Architecture 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.

Prompt Proximity Architecture compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Prompt Proximity Architecture this skillelvisun/newsjack1.5k—~1.9kAutomated safety check: PassMIT
Technical Job Searchgithub/awesome-copilot40k—~1.2kAutomated safety check: PassMIT
Job Application AssistantMadsLorentzen/ai-job-search45k—~1.2kAutomated safety check: NotesMIT
Job Application Managerreactive-resume/reactive-resume44k—~13kAutomated safety check: PassMIT
Python Background Jobswshobson/agents40k—~1.8kAutomated safety check: PassMIT
Operator Approval Loopaffaan-m/ECC277k—~3.3kAutomated safety check: PassMIT

Similar skills

  • Technical Job Search

    github/awesome-copilot

    Official

    A skill your agent uses when a software engineer asks for help with job search tasks: parsing or analyzing a job description, tailoring a CV/resume, writing a cover letter, evaluating a job offer…

    40k GitHub stars~1.2k tokensUpdated 2 days ago
    Business, Finance & HRAuto-check passed

  • Job Application Assistant

    MadsLorentzen/ai-job-search

    Evaluates job postings against your profile, then tailors a LaTeX CV and cover letter and prepares interview answers for the roles you pursue.

    45k GitHub stars~1.2k tokensUpdated 2 days ago
    Business, Finance & HRAuto-check: notes

  • Job Application Manager

    reactive-resume/reactive-resume

    Runs the job-search pipeline. An agent skill from reactive-resume/reactive-resume.

    44k GitHub stars~13k tokensUpdated yesterday
    Business, Finance & HRAuto-check passed

  • Python Background Jobs

    wshobson/agents

    Python background job patterns including task queues, workers, and event-driven architecture.

    40k GitHub stars~1.8k tokensUpdated 6 days ago
    Backend & APIsAuto-check passed

  • Operator Approval Loop

    affaan-m/ECC

    Operator approval contract with internal filing notices for agent-drafted outbound messages, hashed drafts, epoch-keyed decisions, durable delivery claims and receipts, and a pre-draft baseline gate.

    277k GitHub stars~3.3k tokensUpdated today
    Auto-check passed

  • Steve Jobs

    sickn33/agentic-awesome-skills

    Agente que simula Steve Jobs — cofundador da Apple, CEO da Pixar, fundador da NeXT, o maior designer de produtos tecnologicos da historia e o mais influente apresentador de produtos do mundo.

    47k GitHub starsUsed in 2 repos~352 tokens
    Auto-check passed

More from elvisun/newsjack

All 31 skills in this repo

  • Eval Graphics

    elvisun/newsjack

    Turn an eval study's numbers into on-brand, publish-ready figures using the Newsjack chart room (the eval design system), then validate them with Playwright.

    1.5k GitHub stars~2k tokensUpdated today
    Auto-check passed

  • AI Visibility Writing

    elvisun/newsjack

    Audit, question, suggest, or fact-preservingly revise a press release, blog post, contributed article, or expert explainer so AI answer systems can more easily retrieve, understand, quote, and cite…

    1.5k GitHub stars~2.6k tokensUpdated today
    Auto-check passed

  • Coverage Reel

    elvisun/newsjack

    Turn a user-owned coverage CSV and reviewed press-clip captures into an honest, source-linked earned-media dashboard and a motion-designed highlight reel (MP4) that scrolls each real article to the…

    1.5k GitHub stars~3.9k tokensUpdated today
    Auto-check passed

  • Icp Evidence Analysis

    elvisun/newsjack

    Turn a source-bound company and market dossier into testable ideal-customer-profile hypotheses, buying roles, triggers, constraints, disqualifiers, standing, counterevidence, and research gaps.

    1.5k GitHub stars~1.4k tokensUpdated today
    Auto-check passed

  • Build AI Visibility Panel

    elvisun/newsjack

    Research any company, product, or service from a URL plus description and build a comprehensive, evidence-bound AEO/GEO/AI-visibility prompt panel across buyer jobs, information acts, journey…

    1.5k GitHub stars~3.1k tokensUpdated today
    Auto-check passed

  • Reactive Comment

    elvisun/newsjack

    Triage inbound journalist source queries and draft a response only when the user's expertise is a real fit.

    1.5k GitHub stars~5.6k tokensUpdated today
    Auto-check passed

Questions about Prompt Proximity Architecture

What does Prompt Proximity Architecture do?

Turn an approved measurement charter, ICPs, and buyer jobs into a budget-aware prompt coverage blueprint across proximity bands, aided status, information acts, journey states, roles, locales…. Prompt Proximity Architecture is an agent skill from elvisun/newsjack. Turn an approved measurement charter, ICPs, and buyer jobs into a budget-aware prompt coverage blueprint across proximity bands, aided status, information acts, journey states, roles, locales, evidence grades, partitions, and measurement lanes.

How do I install Prompt Proximity Architecture in Claude Code?

Run `npx skills add elvisun/newsjack --skill prompt-proximity-architecture -a claude-code`. Or copy the skill folder (skills/prompt-proximity-architecture in elvisun/newsjack) into .claude/skills/prompt-proximity-architecture in your project. Claude Code loads it when a task matches its description.

How do I install Prompt Proximity Architecture in Codex?

Run `npx skills add elvisun/newsjack --skill prompt-proximity-architecture -a codex`. Or copy the skill folder (skills/prompt-proximity-architecture in elvisun/newsjack) into .agents/skills/prompt-proximity-architecture in your project. Codex loads it when a task matches its description.

Can I use Prompt Proximity Architecture 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 elvisun/newsjack --skill prompt-proximity-architecture -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/prompt-proximity-architecture, .gemini/skills/prompt-proximity-architecture, .github/skills/prompt-proximity-architecture and .opencode/skills/prompt-proximity-architecture in your project.

What does Prompt Proximity Architecture need to run?

SKILL.md names no scripts, command-line tools or credentials: Prompt Proximity Architecture is instructions for the agent only.

Does Prompt Proximity Architecture 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 Prompt Proximity Architecture 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 Prompt Proximity Architecture use?

Prompt Proximity Architecture 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 Prompt Proximity Architecture use?

About 1.9k tokens (SKILL.md is roughly 7.7k 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 Prompt Proximity Architecture?

Skills that share tags, products or a category with Prompt Proximity Architecture: Technical Job Search (github/awesome-copilot, 40k stars), Job Application Assistant (MadsLorentzen/ai-job-search, 45k stars), Job Application Manager (reactive-resume/reactive-resume, 44k stars) and Python Background Jobs (wshobson/agents, 40k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Prompt Proximity Architecture?

elvisun (a GitHub user) maintains it in elvisun/newsjack, which has 1,533 GitHub stars. The repository holds 30 skills in this directory. The repository was last updated on October 7, 2026.

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