Refero Design
referodesign/refero_skill
Primary/default skill for UI design, product design, web design, landing pages, dashboards, product screens, redesigns, visual polish, frontend/CSS styling, design systems, components, responsive…
Score, evaluate, and iteratively improve any content or strategy using an auto-assembled panel of domain experts.
Install Expert Panel
$ npx skills add ericosiu/ai-marketing-skills --skill expert-panel -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install ericosiu/ai-marketing-skills expert-panel --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/ericosiu/ai-marketing-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/content-ops .claude/skills/expert-panel && 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 "expert-panel" agent skill from https://github.com/ericosiu/ai-marketing-skills/tree/main/content-ops into .claude/skills/expert-panel/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "expert-panel", 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/ericosiu/ai-marketing-skills/tree/main/content-opsType 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 ericosiu/ai-marketing-skills --skill expert-panel -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install ericosiu/ai-marketing-skills expert-panel --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ericosiu/ai-marketing-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/content-ops .agents/skills/expert-panel && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "expert-panel" agent skill from https://github.com/ericosiu/ai-marketing-skills/tree/main/content-ops into .agents/skills/expert-panel/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "expert-panel", 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 ericosiu/ai-marketing-skills --skill expert-panel -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install ericosiu/ai-marketing-skills expert-panel --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ericosiu/ai-marketing-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/content-ops .cursor/skills/expert-panel && 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 "expert-panel" agent skill from https://github.com/ericosiu/ai-marketing-skills/tree/main/content-ops into .cursor/skills/expert-panel/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "expert-panel", 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/ericosiu/ai-marketing-skills.git --path content-ops--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 ericosiu/ai-marketing-skills --skill expert-panel -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install ericosiu/ai-marketing-skills expert-panel --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ericosiu/ai-marketing-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/content-ops .gemini/skills/expert-panel && 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 "expert-panel" agent skill from https://github.com/ericosiu/ai-marketing-skills/tree/main/content-ops into .gemini/skills/expert-panel/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "expert-panel", 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 ericosiu/ai-marketing-skills expert-panelInstalls 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 ericosiu/ai-marketing-skills --skill expert-panel -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/ericosiu/ai-marketing-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/content-ops .github/skills/expert-panel && 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 "expert-panel" agent skill from https://github.com/ericosiu/ai-marketing-skills/tree/main/content-ops into .github/skills/expert-panel/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "expert-panel", 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 ericosiu/ai-marketing-skills --skill expert-panel -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install ericosiu/ai-marketing-skills expert-panel --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ericosiu/ai-marketing-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/content-ops .opencode/skills/expert-panel && 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 "expert-panel" agent skill from https://github.com/ericosiu/ai-marketing-skills/tree/main/content-ops into .opencode/skills/expert-panel/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "expert-panel", 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.
Facts
- Skill name
expert-panel- GitHub stars
- 3.6k
- Used in
- 2 other repos
- Token cost
- ~2.1k tokens
- SKILL.md length
- 752 words
- Files
- 27 (incl. scripts, references)
- Skills in repo
- 21
- Repo updated
- First seen
- Licence
- MIT
At a glance
Score, evaluate, and iteratively improve any content or strategy using an auto-assembled panel of domain experts.
- Works in 7 steps: Intake — Understand What's Being Scored → Auto-Assemble the Expert Panel → Select Scoring Rubric → …
- Asked to: expert panel this
- SKILL.md covers Preamble (runs on skill start), Step 1: Intake — Understand…, Step 2: Auto-Assemble the… and Step 3: Select Scoring Rubric, plus 5 more sections
- Calls python3
What it does
Expert Panel is an agent skill from ericosiu/ai-marketing-skills. Score, evaluate, and iteratively improve any content or strategy using an auto-assembled panel of domain experts. Handles copy, sequences, landing pages, strategy docs, titles, charts, recruiting evaluations, or anything else that needs a quality gate. Recursively iterates until all scores hit 90+ (max 3 rounds). Use when asked to: "expert panel this", "score this", "rate these variants", "quality check this", "panel review", "which version is better", "expert score", "evaluate this copy/strategy/page", or when…
Its SKILL.md is about 2.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 30 other files, including scripts and reference files (for example `README.md`, `config/feeds.example.json` and `experts/humanizer.md`).
It sits in Frontend & Design, covering Landing pages, Recruiting and HR and Quality gates. The repository describes itself as: Open-source AI marketing skills — growth experiments, sales pipeline, content ops, outbound, SEO, and finance automation. The licence is MIT.
When your agent uses it
- Asked to: expert panel this
- Rate these variants
- Quality check this
- Which version is better
Example prompts
- “expert panel this”
- “score this”
- “rate these variants”
- “/expert-panel”
Requirements
- Python 3
Workflow steps
7 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 8088e1a. 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
Ships 1 file in scripts/, which the agent can run.
Shell commands in SKILL.md call:
python3
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
Expert Panel loads about 2.1k tokens when it runs, and up to ~3k if it reads all its reference files. Until then it costs about 176 tokens; SKILL.md has 752 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.
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); the scripts in this folder are not scanned.
SKILL.md
The full file from ericosiu/ai-marketing-skills at commit 8088e1a, republished under its MIT licence (© ericosiu). 752 words, ~2,091 tokens.
Download SKILL.mdSave it as
.claude/skills/expert-panel/SKILL.md (or your agent's skills folder). This skill also uses 26 other files; get the full folder from GitHub.- name
- expert-panel
- description
- Score, evaluate, and iteratively improve any content or strategy using an auto-assembled panel of domain experts. Handles copy, sequences, landing pages, strategy docs, titles, charts, recruiting evaluations, or anything else that needs a quality gate. Recursively iterates until all scores hit 90+ (max 3 rounds). Use when asked to: "expert panel this", "score this", "rate these variants", "quality check this", "panel review", "which version is better", "expert score", "evaluate this copy/strategy/page", or when another skill needs a quality gate on its output. Also triggers on: "score this landing page", "expert panel these email variants", "rate this headline", "panel these charts".
Preamble (runs on skill start)
# Version check (silent if up to date)
python3 telemetry/version_check.py 2>/dev/null || true
# Telemetry opt-in (first run only, then remembers your choice)
python3 telemetry/telemetry_init.py 2>/dev/null || truePrivacy: This skill logs usage locally to
~/.ai-marketing-skills/analytics/. Remote telemetry is opt-in only. No code, file paths, or repo content is ever collected. Seetelemetry/README.md.
Expert Panel
General-purpose scoring and iterative improvement engine. Auto-assembles the right experts for whatever is being evaluated, scores it, and loops until 90+.
Step 1: Intake — Understand What's Being Scored
Collect or infer from context:
- Content/artifact — The thing(s) to score (paste, file path, or URL)
- Content type — Copy, sequence, landing page, strategy, title, chart, candidate eval, etc.
- Offer context — What's being sold/promoted? To whom? What domain/industry?
- Variants — Are there multiple versions to compare? (A/B/C)
- Source skill — Is this output from another skill? (e.g., cold-outbound-optimizer) If yes, note the source for feedback-to-source routing in Step 6.
If context is obvious from the conversation, don't ask — just proceed.
Step 2: Auto-Assemble the Expert Panel
Build a panel of 7–10 experts tailored to the content type and domain.
Assembly rules
Start with content-type experts. Read
experts/directory for pre-built panels matching the content type. If an exact match exists (e.g.,experts/linkedin.mdfor a LinkedIn post), use it as the base.Add domain/offer experts. Based on the offer context, add 1–3 experts who understand the specific industry or domain. Examples:
- Scoring bakery marketing → add Food & Beverage Marketing Expert
- Scoring SaaS landing page → add SaaS Conversion Expert
- Scoring recruiting outreach → add Agency Recruiter + Talent Market Expert
- Scoring medical device copy → add Healthcare Compliance Expert
Always include these two:
- AI Writing Detector — See
experts/humanizer.md. Weight: 1.5x. Non-negotiable. - Brand Voice Match — Checks alignment with the configured brand voice and
known rejection patterns from
references/patterns.md(if present).
- AI Writing Detector — See
Check learned patterns. If
references/patterns.mdexists, read it. If any patterns apply to this content type, brief the panel on them. Dock points for known-bad patterns.Cap at 10 experts. If you have more than 10, merge overlapping roles.
Panel output format
List each expert with: Name, lens/focus, what they check.
Step 3: Select Scoring Rubric
Choose the appropriate rubric from scoring-rubrics/:
| Content type | Rubric file |
|---|---|
| Blog, social, email, newsletter, scripts | scoring-rubrics/content-quality.md |
| Strategy, recommendations, analysis | scoring-rubrics/strategic-quality.md |
| Landing pages, ads, CTAs | scoring-rubrics/conversion-quality.md |
| Charts, data viz, infographics | scoring-rubrics/visual-quality.md |
| Candidate evaluations | scoring-rubrics/evaluation-quality.md |
| Other | Synthesize a rubric from the two closest matches |
Read the selected rubric file for detailed criteria and point allocation.
Step 4: Score — Recursive Loop Until 90+
Target: 90/100 across all experts. Non-negotiable. Max 3 rounds.
Each round produces:
## Round [N] — Score: [AVG]/100
| Expert | Score | Key Feedback |
|--------|-------|--------------|
| [Name] | [0-100] | [One-line rationale] |
| ... | ... | ... |
**Aggregate:** [weighted average — humanizer at 1.5x]
**Top 3 weaknesses:** [ranked]
**Changes made:** [specific edits addressing each weakness]Then the revised content/artifact.
Rules
- Scores must be brutally honest. No padding to 90.
- Humanizer score weighted 1.5x in the aggregate.
- If aggregate < 90: identify top 3 weaknesses → revise → next round.
- If aggregate ≥ 90: finalize and proceed to output.
- After 3 rounds, if still < 90: return best version with honest score + note on what's holding it back.
- Show ALL rounds in output — the iteration trail is part of the value.
Show full SKILL.md (275 more words)Show less
Variant comparison mode
When scoring multiple variants (A/B/C):
- Score each variant independently through the full panel.
- After scoring, rank variants by aggregate score.
- If top variant is < 90, iterate on the best one (don't iterate all of them).
Step 5: Output Format
Winner + Score (always at top)
## 🏆 Result: [SCORE]/100 — [PASS ✅ | NEEDS WORK ⚠️]
[Final content/artifact here]
**Iterations:** [N] rounds
**Panel:** [Expert names, comma-separated]If variants: show winner first, then runner-up scores.
## 🏆 Winner: Variant [X] — [SCORE]/100
[Winning content]
### Runner-up scores
- Variant A: 87/100
- Variant B: 82/100
- Variant C: 91/100 ← WinnerFeedback History (below the result)
Show full scoring rounds.
---
<details>
<summary>📊 Scoring History (N rounds)</summary>
[All round tables from Step 4]
</details>Step 6: Feedback-to-Source (When Scoring Another Skill's Output)
When the scored content came from another skill, generate a Source Improvement Brief:
## 🔁 Feedback for [Source Skill]
### What scored low
- [Pattern]: [Specific example from this content]
### Suggested skill improvements
- [Concrete change to the source skill's process/rubric/prompt]
### Patterns to add to source skill
- [Any recurring weakness that should become a rule]This brief can be used to update the source skill's SKILL.md or rubrics.
Step 7: Memory — Learn from Approvals and Rejections
After the user approves or rejects panel output:
On approval (score ≥ 90, user accepts)
Note what worked. No action needed unless a new positive pattern emerges.
On rejection (user overrides the panel or rejects 90+ content)
- Ask why (or infer from context).
- Add a new pattern to
references/patterns.mdusing this format:
## [Pattern Name]
- **Type:** rejection | preference | override
- **Content types:** [which types this applies to]
- **Rule:** [What to always/never do]
- **Example:** [The specific instance that triggered this]
- **Date:** [YYYY-MM-DD]
- **Point dock:** [-N points when detected]- Confirm: "Added pattern: [one-line summary]. Panel will dock [N] points for this going forward."
Pattern enforcement
Every scoring round, check references/patterns.md against the content. Apply point docks
before expert scoring begins. This means known-bad patterns are penalized even if individual
experts miss them.
Reference Files
| File | Purpose | When to read |
|---|---|---|
experts/humanizer.md | AI writing detection rubric (24 patterns) | Every scoring run |
experts/[domain].md | Pre-built expert panels for common domains | When domain matches |
scoring-rubrics/content-quality.md | Content scoring rubric | Content scoring |
scoring-rubrics/strategic-quality.md | Strategy scoring rubric | Strategy scoring |
scoring-rubrics/conversion-quality.md | Landing page/ad/CTA rubric | Conversion scoring |
scoring-rubrics/visual-quality.md | Chart/data viz/infographic rubric | Visual scoring |
scoring-rubrics/evaluation-quality.md | Candidate/assessment rubric | Eval scoring |
references/patterns.md | Learned rejection patterns | Every scoring run |
references/expert-assembly.md | Domain-expert examples for auto-assembly | When building unfamiliar panels |
© ericosiu, 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 26 other files (scripts, references) in content-ops of ericosiu/ai-marketing-skills.
- SKILL.md
- .env.example
- README.md
- config/feeds.example.json
- experts/humanizer.md
- experts/instagram.md
- experts/linkedin.md
- experts/newsletter.md
- experts/podcast-quotes.md
- experts/recruiting.md
- experts/seo-strategy.md
- experts/x-articles.md
- experts/youtube-shorts.md
- references/expert-assembly.md
- references/patterns.md
- requirements.txt
- scoring-rubrics/content-quality.md
- … and 10 more
Open the folder on GitHubat commit 8088e1a
Used in 2 other repositories
We found 2 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 2 other GitHub owners. This page covers the copy in ericosiu/ai-marketing-skills, which our catalogue first saw on October 7, 2026.
Compare with similar skills
Expert Panel 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 |
|---|---|---|---|---|---|---|
| Expert Panel this skillericosiu/ai-marketing-skills | 3.6k | 2 repos | ~2.1k | Automated safety check: Pass | MIT | |
| Refero Designreferodesign/refero_skill | 292 | — | ~5.3k | Automated safety check: Pass | MIT | |
| Managing Use Case PagesComfy-Org/workflow_templates | 1.3k | — | ~3.5k | Automated safety check: Pass | MIT | |
| OpenClaw Design Auditopenclaw/clawhub | 9.5k | — | ~498 | Automated safety check: Pass | MIT | |
| Ads Funnelzubair-trabzada/ai-ads-claude | 267 | — | ~6.6k | Automated safety check: Pass | MIT | |
| Screenshotsaiskillstore/marketplace | 430 | 5 repos | ~3.2k | Automated safety check: Pass | None |
Similar skills
Managing Use Case Pages
Comfy-Org/workflow_templates
Creates and edits SEO use-case landing pages at comfy.org/workflows/use-cases.
OpenClaw Design Audit
openclaw/clawhub
Audits OpenClaw frontend code and rendered pages for token misuse, reimplemented primitives, accessibility and responsive defects and off-brand copy, with an evidence-based report.
Ads Funnel
zubair-trabzada/ai-ads-claude
Full Ads Funnel Architect. An agent skill from zubair-trabzada/ai-ads-claude.
Screenshots
aiskillstore/marketplace
Generate marketing screenshots of your app using Playwright.
Screenshots Marketing
nexu-io/open-design
Generate marketing screenshots with Playwright. An agent skill from nexu-io/open-design.
More from ericosiu/ai-marketing-skills
All 21 skills in this repoCold Outbound Optimizer
ericosiu/ai-marketing-skills
Design, analyze, and optimize cold outbound email campaigns for Instantly.
Finance Ops
ericosiu/ai-marketing-skills
AI-powered financial analysis suite. An agent skill from ericosiu/ai-marketing-skills.
Leveling Up Content Engine
ericosiu/ai-marketing-skills
Diagnose and transform any authorized video URL, upload, recording, transcript, podcast, interview, presentation, screen recording, webinar, ad, or published video into the strongest justified…
Net New Video Editor
ericosiu/ai-marketing-skills
Turn newly recorded talking-head footage into review-ready vertical video drafts with an explicit edit plan, deterministic FFmpeg rendering, captions, hook cards, audio normalization, and visual QA.
Packaging Youtube Thumbnails
ericosiu/ai-marketing-skills
A skill your agent uses when a user supplies new video content or a channel and wants on-brand YouTube titles, thumbnail concepts, rendered variants, A/B packaging, identity profiling, precise…
Shortform Idea Grill
ericosiu/ai-marketing-skills
Interview a founder or senior marketer one question at a time, mine current work and owned proof for net-new short-form video ideas, and return a ranked table with one five-second overlay hook…
Related
Questions about Expert Panel
What does Expert Panel do?
Score, evaluate, and iteratively improve any content or strategy using an auto-assembled panel of domain experts. Expert Panel is an agent skill from ericosiu/ai-marketing-skills. Score, evaluate, and iteratively improve any content or strategy using an auto-assembled panel of domain experts.
When should I use Expert Panel?
Expert Panel fits situations like: asked to: expert panel this; rate these variants; quality check this; which version is better.
How do I install Expert Panel in Claude Code?
Run `npx skills add ericosiu/ai-marketing-skills --skill expert-panel -a claude-code`. Or copy the skill folder (content-ops in ericosiu/ai-marketing-skills) into .claude/skills/expert-panel in your project. Claude Code loads it when a task matches its description.
How do I install Expert Panel in Codex?
Run `npx skills add ericosiu/ai-marketing-skills --skill expert-panel -a codex`. Or copy the skill folder (content-ops in ericosiu/ai-marketing-skills) into .agents/skills/expert-panel in your project. Codex loads it when a task matches its description.
Can I use Expert Panel 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 ericosiu/ai-marketing-skills --skill expert-panel -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/expert-panel, .gemini/skills/expert-panel, .github/skills/expert-panel and .opencode/skills/expert-panel in your project.
What does Expert Panel need to run?
Going by SKILL.md and its folder, Expert Panel needs the command-line tools its instructions call (python3). Our summary lists: Python 3.
Does Expert Panel 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 Expert Panel 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Expert Panel use?
Expert Panel 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 Expert Panel use?
About 2.1k tokens (SKILL.md is roughly 8.4k 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 952 tokens, read only when the agent opens those files.
What are the alternatives to Expert Panel?
Skills that share tags, products or a category with Expert Panel: Refero Design (referodesign/refero_skill, 292 stars), Managing Use Case Pages (Comfy-Org/workflow_templates, 1.3k stars), OpenClaw Design Audit (openclaw/clawhub, 9.5k stars) and Ads Funnel (zubair-trabzada/ai-ads-claude, 267 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Expert Panel?
ericosiu (a GitHub user) maintains it in ericosiu/ai-marketing-skills, which has 3,611 GitHub stars. The repository holds 21 skills in this directory. The repository was last updated on September 22, 2026.
Source: ericosiu/ai-marketing-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.