Offer Design
minhnv0807/ai-business-skills
Designs or repairs what a business sells, covering the promise, value stack, bonuses, guarantee, honest scarcity and a tiered ladder, rather than price or copy.
Apply expectation priming — deliberately shaping the prior context (brand, marketing, price, social proof, recommendations) that users bring to a product before they ever touch it.
$ npx skills add hashgraph-online/awesome-codex-plugins --skill expectation-effect-priming -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install hashgraph-online/awesome-codex-plugins expectation-effect-priming --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/hashgraph-online/awesome-codex-plugins.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/HDeibler/universal-design-principles/plugins/interaction-and-control-principles/skills/expectation-effect-priming .claude/skills/expectation-effect-priming && 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 "expectation-effect-priming" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/HDeibler/universal-design-principles/plugins/interaction-and-control-principles/skills/expectation-effect-priming into .claude/skills/expectation-effect-priming/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "expectation-effect-priming", 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/hashgraph-online/awesome-codex-plugins/tree/main/plugins/HDeibler/universal-design-principles/plugins/interaction-and-control-principles/skills/expectation-effect-primingType 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 hashgraph-online/awesome-codex-plugins --skill expectation-effect-priming -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install hashgraph-online/awesome-codex-plugins expectation-effect-priming --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/hashgraph-online/awesome-codex-plugins.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugins/HDeibler/universal-design-principles/plugins/interaction-and-control-principles/skills/expectation-effect-priming .agents/skills/expectation-effect-priming && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "expectation-effect-priming" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/HDeibler/universal-design-principles/plugins/interaction-and-control-principles/skills/expectation-effect-priming into .agents/skills/expectation-effect-priming/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "expectation-effect-priming", 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 hashgraph-online/awesome-codex-plugins --skill expectation-effect-priming -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install hashgraph-online/awesome-codex-plugins expectation-effect-priming --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/hashgraph-online/awesome-codex-plugins.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugins/HDeibler/universal-design-principles/plugins/interaction-and-control-principles/skills/expectation-effect-priming .cursor/skills/expectation-effect-priming && 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 "expectation-effect-priming" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/HDeibler/universal-design-principles/plugins/interaction-and-control-principles/skills/expectation-effect-priming into .cursor/skills/expectation-effect-priming/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "expectation-effect-priming", 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/hashgraph-online/awesome-codex-plugins.git --path plugins/HDeibler/universal-design-principles/plugins/interaction-and-control-principles/skills/expectation-effect-priming--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 hashgraph-online/awesome-codex-plugins --skill expectation-effect-priming -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install hashgraph-online/awesome-codex-plugins expectation-effect-priming --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/hashgraph-online/awesome-codex-plugins.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugins/HDeibler/universal-design-principles/plugins/interaction-and-control-principles/skills/expectation-effect-priming .gemini/skills/expectation-effect-priming && 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 "expectation-effect-priming" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/HDeibler/universal-design-principles/plugins/interaction-and-control-principles/skills/expectation-effect-priming into .gemini/skills/expectation-effect-priming/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "expectation-effect-priming", 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 hashgraph-online/awesome-codex-plugins expectation-effect-primingInstalls 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 hashgraph-online/awesome-codex-plugins --skill expectation-effect-priming -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/hashgraph-online/awesome-codex-plugins.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugins/HDeibler/universal-design-principles/plugins/interaction-and-control-principles/skills/expectation-effect-priming .github/skills/expectation-effect-priming && 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 "expectation-effect-priming" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/HDeibler/universal-design-principles/plugins/interaction-and-control-principles/skills/expectation-effect-priming into .github/skills/expectation-effect-priming/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "expectation-effect-priming", 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 hashgraph-online/awesome-codex-plugins --skill expectation-effect-priming -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install hashgraph-online/awesome-codex-plugins expectation-effect-priming --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/hashgraph-online/awesome-codex-plugins.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugins/HDeibler/universal-design-principles/plugins/interaction-and-control-principles/skills/expectation-effect-priming .opencode/skills/expectation-effect-priming && 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 "expectation-effect-priming" agent skill from https://github.com/hashgraph-online/awesome-codex-plugins/tree/main/plugins/HDeibler/universal-design-principles/plugins/interaction-and-control-principles/skills/expectation-effect-priming into .opencode/skills/expectation-effect-priming/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "expectation-effect-priming", 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.
expectation-effect-primingApply expectation priming — deliberately shaping the prior context (brand, marketing, price, social proof, recommendations) that users bring to a product before they ever touch it.
Expectation Effect Priming is an agent skill from hashgraph-online/awesome-codex-plugins. Apply expectation priming — deliberately shaping the prior context (brand, marketing, price, social proof, recommendations) that users bring to a product before they ever touch it. Use when planning a launch, choosing positioning copy, deciding pricing tier, designing the marketing surface, or framing a feature for first encounter. Pre-encounter priming is often more powerful than in-product polish, because it sets the lens through which the in-product experience will be interpreted. The skill is calibrating…
Its SKILL.md is about 2.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/priming-channels.md`).
It sits in Marketing & SEO, covering Marketing psychology, Pricing strategy and Positioning and messaging. The repository describes itself as: A curated list of awesome OpenAI Codex / ChatGPT plugins, skills, and resources. The 1 Codex Marketplace. See live plugins at: https://hol.org/plugins/best-codex-plugins. The licence is Apache-2.0.
Read from SKILL.md and the folder at commit 78497e5. It shows what the files ask for, not the result of running them.
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.
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.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Expectation Effect Priming loads about 2.8k tokens when it runs, and up to ~4.9k if it reads all its reference files. Until then it costs about 149 tokens; SKILL.md has 1,552 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.
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.
The full file from hashgraph-online/awesome-codex-plugins at commit 78497e5, republished under its Apache-2.0 licence (© hashgraph-online). 1,552 words, ~2,797 tokens.
.claude/skills/expectation-effect-priming/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.Pre-encounter priming is everything that happens before the user touches the product. It includes branding, marketing copy, screenshots and demos, price, channel of arrival, social proof, and the user's prior associations with similar products. Priming sets the lens through which the user will perceive every subsequent interaction.
The leverage on perception from priming is often larger than the leverage from in-product polish, because priming operates first and sets the baseline expectations that the product is then measured against.
Priming happens through several distinct channels.
Brand and visual identity. A logotype, a color palette, a typography choice, an aesthetic register. Apple's brand primes "premium, simple, designed-for-humans." Mailchimp's brand primes "small-business friendly, casual, illustrated." Stripe's brand primes "developer-respected, technically credible, clean." These are sustained over years of consistent use and color how every new product or feature is initially read.
Pricing. Price is one of the strongest single priming signals. A $200/year tool primes users to expect substantial value, a polished experience, and responsive support. A $5/month tool primes users to expect basic competence and limited support. A free tool primes users to expect ads, limitations, or unstable feature sets. Pricing within a category band signals "this is a premium variant" or "this is a budget variant" with high reliability.
Marketing copy and positioning. "The world's most powerful X" primes users to expect breadth and capability. "A simple Y for everyday use" primes users to expect ease and modesty. "Built for serious professionals" primes users to expect a steeper learning curve and more depth. The exact words shape what users will look for in the product.
Screenshots, demos, and trailers. Visual evidence of the product before use sets very specific expectations about what's inside. Curated screenshots showing the polished happy path prime users to expect that level of polish in their own use; if the actual experience is rougher, the gap reads as broken promises.
Social proof. Reviews, testimonials, customer logos, recommendation by trusted sources. A friend's recommendation primes users much more strongly than an ad — they expect the product to be good and they actively look for confirmation. A 1-star review average primes the opposite. Social proof is one of the few priming signals that compounds: reviews shape expectations of new users, who then write reviews that shape the next cohort.
Channel of arrival. Users who arrive through a search for a specific need have different expectations than users who arrive through a banner ad. Search-driven users expect the product to solve their stated need; ad-driven users have lower commitment and require the product to surprise them.
Category convention. Users come to a "calendar app" with expectations shaped by every calendar app they've used before. Deviating from category convention (a calendar app that doesn't show a month grid, for instance) requires either explicit framing ("the calendar reimagined as...") or a strong onboarding moment to reset expectations.
The goal of priming is to set expectations slightly above the median in-product experience, so that the actual use confirms or modestly exceeds them. Set expectations too low and qualified users dismiss the product; set them too high and users churn after a disappointing first session.
The calibration involves a few moves:
Match marketing register to in-product register. If the product is a serious enterprise tool, the marketing should be sober and precise; if the product is playful and casual, the marketing should match. Mismatches produce a jolt at the moment of first use that primes users to mistrust both the marketing and the product.
Show the actual product, not a stylized version. Marketing screenshots that are photoshopped beyond what the product can actually render set expectations the product can't meet. Show the real thing, even if it's slightly less photogenic than an idealized render.
Be specific about what's included. Vague positioning ("everything you need to manage your business") sets expectations that any specific shortcoming can violate. Specific positioning ("invoicing, expense tracking, and tax prep for solo consultants") sets expectations the product can actually meet.
Match price to perceived value, not to ambition. Pricing too high without the substance to back it up generates immediate disappointment. Pricing too low for the substance you've built leaves money on the table and signals "low quality" to users for whom price is a quality cue.
Use social proof that survives investigation. Featured customer logos that turn out to be one-time users, testimonials from people without verifiable accounts, review ratings that drop sharply when filtered for verified purchases — these all damage the priming effect when discovered. Honest social proof, even if more modest, sustains expectations.
A new $99/month accounting tool launches with sophisticated marketing: a film-quality demo video, prestigious customer logos, a confident tagline. Users arrive primed for premium. The product opens to a clean dashboard, a confident onboarding, and a guided first task. Premium framing met. The in-product experience confirms the priming, and users rate the product significantly better than they would have without the priming.
If the same product had launched with placeholder marketing and a $9 price, users would have arrived with low expectations. The same in-product experience would have read as "surprisingly good for the price" — but few users would have arrived to begin with, and those who did would have struggled to recommend it to peers ("it's good, but the website looks unprofessional, so I'm not sure I'd send my CFO to it").
A weather app redesigns its main view from the conventional "current temperature, hourly forecast, daily forecast" layout to a more abstract "weather as ambient light visualization." Users arriving with category-conventional expectations find the new view confusing. The fix: explicit framing in the App Store description ("Weather, reimagined as ambient atmosphere") and a brief first-launch screen explaining the metaphor. The framing resets expectations to make the design choice readable rather than confusing.
A productivity tool offers a generous free tier. Users who try the free tier and find it polished and complete are primed to believe the paid tier is also polished and complete; conversion to paid is high. A different productivity tool offers a deliberately limited, somewhat clunky free tier (designed to "encourage upgrade") and finds that users don't upgrade — they instead form a negative impression of the entire product based on their free experience.
The lesson: free experiences prime expectations of paid experiences. Don't sabotage the free tier to drive upgrades; that primes negatively for the paid product too.
A user is told by a respected colleague that "X is the best tool for Y." They arrive with high expectations and active interest in confirming the recommendation. They notice features and strengths that they would have skimmed past otherwise. Their evaluation is positively biased and they're more likely to recommend the product themselves. This is the most powerful form of priming and the hardest to engineer; it generally requires the product to actually be excellent and to spread by word of mouth.
Premium marketing on an early-stage product. A startup with a polished marketing site and a half-built product creates a credibility gap when users actually try the product. The fix is usually either to restrain the marketing to match the current product, or to frame the marketing as "early access / beta / building toward" so expectations include the rough edges.
Vague positioning that can't be falsified. "Reimagining how teams work together" doesn't set specific expectations, which sounds harmless but actually primes users to expect something special without telling them what. They form their own (often wildly varying) interpretations and are then disappointed when the product doesn't match. Specific positioning is more constraining but also more reliably met.
Inflated user counts and customer logos. Users learn to discount inflated claims, and once discounted they spread to other claims. Modest, honest social proof builds more durable trust than spectacular but suspect claims.
Pricing that doesn't match perceived complexity. A $5/month tool that requires a 30-day onboarding and integration with multiple data sources is mispriced — its complexity primes users to expect enterprise-tier support, which a $5/month price can't sustain.
Channel-of-arrival mismatches. Driving paid traffic to a feature that hasn't been polished for first-time users. The paid traffic primes high expectations (the user clicked an ad, expecting something specific) and the feature can't meet them. Reserve paid acquisition for the parts of the product that survive scrutiny.
For each new launch or redesign, ask: What are the dominant priming signals users will encounter before touching the product? List them. What expectations will those signals set? Be specific about the level and kind. Does the actual experience match those expectations? If not, which side moves: the priming, or the experience? What channel are users arriving from, and what does that channel imply about their expectations? Optimize the post-arrival experience for the priming each channel produces.
expectation-effect-design-cues — for the in-product cues that set expectations within a session, complementing the pre-encounter priming this skill covers.aesthetic-usability-effect — the in-product version of priming, where surface beauty primes perceived usability.mental-model — expectations are part of the mental model the user brings.archetypes — brand and category archetypes are powerful priming devices.references/priming-channels.md — a working catalog of priming signals and their relative strengths.© hashgraph-online, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 1 other file (references) in plugins/HDeibler/universal-design-principles/plugins/interaction-and-control-principles/skills/expectation-effect-priming of hashgraph-online/awesome-codex-plugins.
Open the folder on GitHubat commit 78497e5
Expectation Effect Priming 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 |
|---|---|---|---|---|---|---|
| Expectation Effect Priming this skillhashgraph-online/awesome-codex-plugins | 1.2k | — | ~2.8k | Automated safety check: Pass | Apache-2.0 | |
| Offer Designminhnv0807/ai-business-skills | 608 | — | ~1.1k | Automated safety check: Pass | MIT | |
| Competitive Teardownalirezarezvani/claude-skills | 28k | 2 repos | ~2.1k | Automated safety check: Pass | MIT | |
| Counter Narrativeindranilbanerjee/digital-marketing-pro | 855 | 1 repos | ~2.4k | Automated safety check: Pass | MIT | |
| Isr Literature Positioningfranklee16/academic-research-skills | 223 | 1 repos | ~902 | Automated safety check: Pass | None | |
| Positioning AuditOotto-AI/claude-content-skills | 112 | — | ~947 | Automated safety check: Pass | MIT |
minhnv0807/ai-business-skills
Designs or repairs what a business sells, covering the promise, value stack, bonuses, guarantee, honest scarcity and a tiered ladder, rather than price or copy.
alirezarezvani/claude-skills
Analyzes competitor products and companies by synthesizing data from pricing pages, app store reviews, job postings, SEO signals, and social media into structured competitive intelligence.
indranilbanerjee/digital-marketing-pro
Build a counter-narrative playbook responding to a competitor's positioning move — rebrand, category claim, aggressive campaign, price change, or partnership.
franklee16/academic-research-skills
A skill your agent uses when positioning an Information Systems Research (ISR) manuscript in the IS literature — naming the conversation(s) you join, bridging behavioral, economic, design-science…
Ootto-AI/claude-content-skills
Audit a brand's social positioning from its profile, offer, customer proof, and competitor material.
brycewang-stanford/Awesome-Journal-Skills
A skill your agent uses when staking a Journal of Consumer Psychology (JCP) manuscript's contribution against the consumer-psychology literature and its siblings (JCR, JMR, Marketing Science…
hashgraph-online/awesome-codex-plugins
Create original anime-style reaction stickers as looping GIFs and MP4 previews, using generated character pose sheets and timed key poses.
hashgraph-online/awesome-codex-plugins
Manage and query Calibre libraries with the calibredb CLI (local paths or Calibre Content server URLs).
hashgraph-online/awesome-codex-plugins
A skill your agent uses when adding, changing, testing, or debugging Rust HTTP APIs and services, especially when Codex needs black-box integration tests, random-port app startup, real database test…
hashgraph-online/awesome-codex-plugins
Make a studio's game look like something at build time — a cover from a real frame of the game (free), painted covers, backdrops, textures and character plates from image models through the…
hashgraph-online/awesome-codex-plugins
Balance game difficulty, resources, rewards, probability, progression, economies, and dominant strategies.
hashgraph-online/awesome-codex-plugins
Analyze nonfiction manuscripts for reader engagement signals, including heading-level word counts, slow starts, long slogs, weak takeaway titles, value pacing, beta-reader comment dropoff, and…
Categories
Apply expectation priming — deliberately shaping the prior context (brand, marketing, price, social proof, recommendations) that users bring to a product before they ever touch it. Expectation Effect Priming is an agent skill from hashgraph-online/awesome-codex-plugins. Apply expectation priming — deliberately shaping the prior context (brand, marketing, price, social proof, recommendations) that users bring to a product before they ever touch it.
Expectation Effect Priming fits situations like: planning a launch; choosing positioning copy; deciding pricing tier; designing the marketing surface.
Run `npx skills add hashgraph-online/awesome-codex-plugins --skill expectation-effect-priming -a claude-code`. Or copy the skill folder (plugins/HDeibler/universal-design-principles/plugins/interaction-and-control-principles/skills/expectation-effect-priming in hashgraph-online/awesome-codex-plugins) into .claude/skills/expectation-effect-priming in your project. Claude Code loads it when a task matches its description.
Run `npx skills add hashgraph-online/awesome-codex-plugins --skill expectation-effect-priming -a codex`. Or copy the skill folder (plugins/HDeibler/universal-design-principles/plugins/interaction-and-control-principles/skills/expectation-effect-priming in hashgraph-online/awesome-codex-plugins) into .agents/skills/expectation-effect-priming in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add hashgraph-online/awesome-codex-plugins --skill expectation-effect-priming -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/expectation-effect-priming, .gemini/skills/expectation-effect-priming, .github/skills/expectation-effect-priming and .opencode/skills/expectation-effect-priming in your project.
SKILL.md names no scripts, command-line tools or credentials: Expectation Effect Priming is instructions for the agent only.
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.
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.
Expectation Effect Priming is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.8k tokens (SKILL.md is roughly 11k 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 2.1k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Expectation Effect Priming: Offer Design (minhnv0807/ai-business-skills, 608 stars), Competitive Teardown (alirezarezvani/claude-skills, 28k stars), Counter Narrative (indranilbanerjee/digital-marketing-pro, 855 stars) and Isr Literature Positioning (franklee16/academic-research-skills, 223 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
hashgraph-online (a GitHub organization) maintains it in hashgraph-online/awesome-codex-plugins, which has 1,242 GitHub stars. The repository holds 686 skills in this directory. The repository was last updated on October 8, 2026.
Source: hashgraph-online/awesome-codex-plugins on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.