Asd Ste100
danyuchn/asd-ste100-skill
A skill your agent uses when English text must be parsed without a human to resolve ambiguity — tool descriptions, error messages, inter-agent instructions, system prompts, status reports — and…
A skill your agent uses when the user wants to write a sports news piece — game recaps, athlete profiles, league/rule changes, injury reports, trade announcements, doping/discipline coverage — from…
$ npx skills add asgard-ai-platform/skills --skill med-sports -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install asgard-ai-platform/skills med-sports --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/asgard-ai-platform/skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/med-sports .claude/skills/med-sports && 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 "med-sports" agent skill from https://github.com/asgard-ai-platform/skills/tree/main/med-sports into .claude/skills/med-sports/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "med-sports", 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/asgard-ai-platform/skills/tree/main/med-sportsType 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 asgard-ai-platform/skills --skill med-sports -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install asgard-ai-platform/skills med-sports --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/asgard-ai-platform/skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/med-sports .agents/skills/med-sports && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "med-sports" agent skill from https://github.com/asgard-ai-platform/skills/tree/main/med-sports into .agents/skills/med-sports/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "med-sports", 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 asgard-ai-platform/skills --skill med-sports -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install asgard-ai-platform/skills med-sports --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/asgard-ai-platform/skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/med-sports .cursor/skills/med-sports && 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 "med-sports" agent skill from https://github.com/asgard-ai-platform/skills/tree/main/med-sports into .cursor/skills/med-sports/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "med-sports", 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/asgard-ai-platform/skills.git --path med-sports--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 asgard-ai-platform/skills --skill med-sports -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install asgard-ai-platform/skills med-sports --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/asgard-ai-platform/skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/med-sports .gemini/skills/med-sports && 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 "med-sports" agent skill from https://github.com/asgard-ai-platform/skills/tree/main/med-sports into .gemini/skills/med-sports/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "med-sports", 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 asgard-ai-platform/skills med-sportsInstalls 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 asgard-ai-platform/skills --skill med-sports -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/asgard-ai-platform/skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/med-sports .github/skills/med-sports && 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 "med-sports" agent skill from https://github.com/asgard-ai-platform/skills/tree/main/med-sports into .github/skills/med-sports/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "med-sports", 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 asgard-ai-platform/skills --skill med-sports -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install asgard-ai-platform/skills med-sports --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/asgard-ai-platform/skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/med-sports .opencode/skills/med-sports && 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 "med-sports" agent skill from https://github.com/asgard-ai-platform/skills/tree/main/med-sports into .opencode/skills/med-sports/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "med-sports", 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.
med-sportsA skill your agent uses when the user wants to write a sports news piece — game recaps, athlete profiles, league/rule changes, injury reports, trade announcements, doping/discipline coverage — from…
Med Sports is an agent skill from asgard-ai-platform/skills. Use when the user wants to write a sports news piece — game recaps, athlete profiles, league/rule changes, injury reports, trade announcements, doping/discipline coverage — from supplied material (box scores, interviews, official statements, stats, medical updates). Specializes med-news-reporter for the sports beat: era-adjusted stats, source vetting for sports data, medical/injury disclosure limits, athlete-as-public-figure doctrine, doping allegations vs. allegations, sports-betting sensitivity, and on-field…
Its SKILL.md is about 4.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 10 other files, including reference files (for example `examples/sample_input.md`, `examples/sample_output.md` and `references/ethics_and_law.md`).
It sits in Writing & Content, covering Copywriting. The repository describes itself as: 301 open-source coding agent skills across 22 domains — methodology, judgment & gotchas packaged as Claude Agent Skills for the Asgard AI Platform. The licence is MIT.
5 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit 4e7f4f8. 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 (its code samples are markdown).
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.
Med Sports loads about 4.4k tokens when it runs, and up to ~13k if it reads all its reference files. Until then it costs about 233 tokens; SKILL.md has 1,819 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 asgard-ai-platform/skills at commit 4e7f4f8, republished under its MIT licence (© asgard-ai-platform). 1,819 words, ~4,417 tokens.
.claude/skills/med-sports/SKILL.md (or your agent's skills folder). This skill also uses 8 other files; get the full folder from GitHub.This skill specializes med-news-reporter for the sports beat. Read med-news-reporter first for the general 6-step workflow (type selection, material audit, fact-check, balance, ethics, literacy). This file adds sports-beat-specific discipline on top.
Distilled from sports-journalism curricula at Ohio University Scripps, Northwestern Medill, University of Missouri, Arizona State Cronkite, University of Florida, and curricula in athletic governance (CPBL, NBA, IOC, WADA CAS procedures). Covers five main sports-news sub-types: game/event coverage / athlete profile / league governance / injury/discipline / trade/transaction.
IRON LAW: On-Field Performance ≠ Off-Field Authority
A player's elite on-court statistics are news; the same player's political
opinions, business endorsements, or social claims receive the same source-
vetting and attribution standards as any quoted figure. Do not treat
athletic celebrity as a free pass for unverified off-field claims, and do
not smuggle off-field judgments via on-field framing ("the controversial
striker scored twice" conflates sports fact with off-field stance). Separate
the performance data (verifiable, time-stamped, era-adjusted) from the claim
about what they meant or who they are off the field (requires the same rigor
as any other quoted figure's statement). When stats are accurate but used
to make a character claim, flag it.
Default LLM behavior is to assume athletic fame carries credibility across
domains. Override that assumption explicitly per subject.Why this is non-obvious: sports readers are accustomed to athlete-celebrity conflation in tabloid press. Professional sports journalism must separate statistical fact from interpretive claim — especially when an athlete's behavior (kneeling, endorsement, political statement) is described alongside their game performance. The framing "activist star backhands a critic and scores twice" treats on-field dominance as authority for off-field views. This is the failure mode the Iron Law exists to catch.
Rationalization Table — these justifications DO NOT override the Iron Law:
| Claude might think... | Why it's still a violation |
|---|---|
| "The player is famous, so their off-field opinion is newsworthy" | Fame in one domain (athletics) does not confer authority in another (politics, medicine, social policy). Quote them as an athlete-who-happens-to-comment, not as an expert. Verify claims independently. |
| "The coach said it, so it's coaching wisdom, not opinion" | Post-game soundbites are still attributed utterances, not facts. "Coach said X beats Y" ≠ "X beats Y". |
| "These stats prove the athlete is the 'best ever'" — followed by character praise | Stats without era-adjustment and comparable sample size can mislead. "Best ever" requires evidence, not just dominance in a single season or league. Always cite the era and sample. |
| "The injury report is from the team, so it's official" | Team injury reports are PR-filtered. Formal medical disclosures differ from "player is healthy and ready". Cross-check with league medical protocols if significant claim. |
| "The doping allegation is trending on social media / a prominent figure tweeted it" | Unsubstantiated doping allegations are defamatory. Use "allegation", "alleged", "claimed to have violated" (not "is a drug cheat"). Wait for WADA/CAS adjudication or corroboration. |
| "This player's controversial personal life is part of their public story" | Athletes have reasonable privacy expectation for family, mental health, medical info. Distinguish between public acts (on-field, on-camera, tournament) and private life (unless directly relevant to job performance or self-disclosed). |
| "The betting line shows this game is close, so I'll cite it as odds context" | Don't cite sports-betting lines as news sources or "neutral" metrics. Betting companies have financial interest in narrative and line movement. If the story is about betting, disclose the financial relationship. |
Trigger conditions:
Input signals:
When NOT to use:
pr-press-release or mkt-sports-content.pr-press-release.biz-* or fin-* (unless the story is "league governing body did X").Read or have already loaded med-news-reporter for: material audit, fact-checking, source-strength tagging, balance principle, media-ethics check, media-literacy self-check. Do not re-implement those steps here. This file specializes Steps 1, 2, 3, and adds sports-specific Step 7 (Stats Provenance & Performance-Authority Audit).
| Sub-type | Signals | Sub-template focus |
|---|---|---|
| Game/event coverage | Box score, play-by-play, result, player/team performance | Accuracy of stats; era context; avoiding "greatest ever" without qualification |
| Athlete profile | Life story, career arc, personality, off-field interests | Distinction between on-field fact and off-field opinion; privacy boundary; consent for personal details |
| League governance | Rule change, expansion, labor/CBA, discipline case, playoff format | Official decision source; stakeholder positions (players union, owners, athletes); implementation timeline |
| Injury/medical | Player health status, return timeline, surgery, mental health disclosure | Medical privacy law; team vs. public info; degree of disclosure propriety; player consent |
| Trade/transaction | Player signed, traded, released, drafted, retired | Contract/deal terms source; bidding competition (if reported); player statement; team official statement |
If the material spans sub-types (e.g. "star player traded due to injury"), classify by the primary news driver.
Every statistic or "first time since X" claim must carry provenance:
Source tier tagging (extends med-news-reporter's tiering with sports-specific tiers):
| Tier | Examples | Treatment |
|---|---|---|
| Official league record | Box scores (NBA.com, MLB.com, CPBL, official league stats), rule book, official standings | Direct citation; note source entity |
| Third-party verified database | Baseball-Reference, Basketball-Reference, Sports-Reference, ESPN Stats, PFF (for NFL) | Cite source; note version/update date if material |
| Team official statement | Coach quote, team press release, official injury report | Quote directly; label as team-sourced; note any PR filtering |
| Athlete on-record quote | Post-game interview, press conference, official statement | Direct quote per med-news-reporter; distinguish from off-hand comment or social media |
| Analyst / commentator opinion | Ex-player analysis, sports journalist prediction, coach speculation | Label as analysis/opinion; do not treat as fact |
| Social media / fan / rumor | Athlete tweet, player agent leak, beat reporter speculation | Unusable until corroborated; or explicitly flagged as "unconfirmed report" if novel and newsworthy |
Beyond med-news-reporter's general ethics check, add:
禁藥和紀律指控 (Doping/Discipline Allegations):
傷停資訊與醫療揭露:
球員私生活邊界:
賭盤相關敏感性 (Sports Betting Disclosure):
국제경기 & 올림픽 규정:
Before output, sweep the draft for:
"Greatest" / "first" / "only" / "unprecedented" superlatives: every such claim must cite:
Comparison audit:
Injury-timeline realism: medical claims should not exceed evidence:
Performance-vs.-Context:
Use the med-news-reporter base format, with these sports additions to the meta footer:
[Headline / sub-headline / body paragraphs per med-news-reporter]
---
**稿件類型**: 即時賽事 / 運動員專訪 / 轉隊消息 / 傷停更新 / 聯盟治理
**字數**: approx. XXX
**消息來源層級**: 官方記錄 N / 隊方 N / 運動員本人 N / 分析評論 N / 民間謠傳 N
**統計數據稽核**:
- 「最佳 / 首次 / 從未」superlatives: ✅ / ⚠️ (列出未限定範圍的)
- 跨時代比較: ✅ / N/A / ⚠️ (列出未加註 era 或規則背景的)
- 跨聯盟比較: ✅ / N/A / ⚠️ (列出未加註聯盟差異的)
**醫療 / 紀律敏感項目**:
- 禁藥指控: ✅ (使用「涉嫌」) / N/A / ⚠️ (列出標籤誤用)
- 傷停資訊來源: ✅ (官方) / ⚠️ (球隊 PR / 推測分開呈現)
- 球員私生活邊界: ✅ / ⚠️ (列出可能越界的細節)
- 賭盤相關: N/A / ⚠️ (若提及,是否揭露財務利益)
**待查證事項**: ...
**倫理 / 識讀檢核摘要**: 〔交給 med-news-reporter 的 Step 4-5 footer〕| File | Purpose | When to read |
|---|---|---|
references/sources_and_beats.md | 體育新聞消息來源、國際聯盟與數據庫、台灣體育治理機構 | Step 2 source vetting |
references/glossary.md | 體育統計術語、計算公式、跨聯盟術語對照 (ERA/WHIP、TS%/PER、打擊率/上壘率) | When unfamiliar sports terminology appears |
references/ethics_and_law.md | 球員隱私 / 醫療揭露、禁藥程序、兒少法保護、賭盤敏感性、未成年運動員 | Step 3 risk check |
references/sports_data_reading.md | 進階數據 vs. 傳統數據、sample size、era-adjusted 比較、樣本不足陷阱 | Step 4 Stats Provenance Audit |
references/sports_governance.md | 各聯盟治理結構 (CPBL, MLB, NBA, IOC)、勞資協議、選秀規則、轉隊規則 | When covering league/governance stories |
Related skills:
med-news-reporter — general news workflow (this skill specializes it)med-business — for sports business / corporate strategy stories (sponsorship, broadcasting rights, franchise valuation)stat-hypothesis-testing — for statistical claims and era-adjustment rigorhum-source-criticism — for deeper vetting of sports-data sources and databases© asgard-ai-platform, MIT. 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 8 other files (references) in med-sports of asgard-ai-platform/skills.
Open the folder on GitHubat commit 4e7f4f8
Med Sports 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 |
|---|---|---|---|---|---|---|
| Med Sports this skillasgard-ai-platform/skills | 242 | — | ~4.4k | Automated safety check: Pass | MIT | |
| Asd Ste100danyuchn/asd-ste100-skill | 4.3k | — | ~4.1k | Automated safety check: Pass | MIT | |
| AI Copywritermikiarlo3/ai-copywriter | 1.2k | — | ~12k | Automated safety check: Pass | MIT | |
| Brand Voice Guideluongnv89/claude-howto | 42k | — | ~609 | Automated safety check: Pass | MIT | |
| Ralph Copywritermuratcankoylan/ralph-wiggum-marketer | 778 | — | ~2.4k | Automated safety check: Pass | None | |
| Humanities Writing Companiontizzy916/humanities-writing-companion | 436 | — | ~3.4k | Automated safety check: Pass | CC-BY-NC-4.0 |
danyuchn/asd-ste100-skill
A skill your agent uses when English text must be parsed without a human to resolve ambiguity — tool descriptions, error messages, inter-agent instructions, system prompts, status reports — and…
mikiarlo3/ai-copywriter
Write copy that converts and doesn't sound like a robot. An agent skill from mikiarlo3/ai-copywriter.
luongnv89/claude-howto
Ensure all communication matches brand voice and tone guidelines. Use when creating marketing copy, customer communications, public-facing content, or when…
muratcankoylan/ralph-wiggum-marketer
A skill your agent uses when the user asks to "analyze my content", "learn my writing style", "research competitors", "find content angles", "improve my blog", "write like me", "embody my brand…
tizzy916/humanities-writing-companion
Help with humanities scholarly writing: sharpen research questions, map supplied readings, plan and draft arguments, review chapters, preserve authorial voice, and respond to reviewers.
crawfordxx/xiaoma-durex-copywriter
用杜蕾斯黄金期(2011-2017 环时互动)那套「双层语义 + 留白」的方法产出文案与海报。先识别用户意图并给 3-5 个方案供选,再出短文案(长文案可选)+ 五种比例配图。适用于借势热点、节日节气、产品卖点、课程/知识付费推广、自媒体标题与封面、品牌人格化运营。当用户说「写个文案」「借势热点」「节日海报」「想句…
asgard-ai-platform/skills
Implement BM25 ranking function for e-commerce product search relevance scoring.
asgard-ai-platform/skills
Calculate Cpk process capability index to assess whether a process meets specification requirements.
asgard-ai-platform/skills
Calculate price elasticity of demand to quantify how price changes affect sales volume.
asgard-ai-platform/skills
Apply Bayesian averaging to rank items by combining observed ratings with prior expectations.
asgard-ai-platform/skills
Implement Elo rating system to rank items or players from pairwise comparison outcomes.
asgard-ai-platform/skills
Calculate Wilson Score confidence intervals for ranking items by positive proportion with sample size correction.
Categories
A skill your agent uses when the user wants to write a sports news piece — game recaps, athlete profiles, league/rule changes, injury reports, trade announcements, doping/discipline coverage — from…. Med Sports is an agent skill from asgard-ai-platform/skills. Use when the user wants to write a sports news piece — game recaps, athlete profiles, league/rule changes, injury reports, trade announcements, doping/discipline coverage — from supplied material (box scores, interviews, official statements, stats, medical updates).
Med Sports fits situations like: the user wants to write a sports news piece — game recaps; athlete profiles; league/rule changes; trade announcements.
Run `npx skills add asgard-ai-platform/skills --skill med-sports -a claude-code`. Or copy the skill folder (med-sports in asgard-ai-platform/skills) into .claude/skills/med-sports in your project. Claude Code loads it when a task matches its description.
Run `npx skills add asgard-ai-platform/skills --skill med-sports -a codex`. Or copy the skill folder (med-sports in asgard-ai-platform/skills) into .agents/skills/med-sports 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 asgard-ai-platform/skills --skill med-sports -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/med-sports, .gemini/skills/med-sports, .github/skills/med-sports and .opencode/skills/med-sports in your project.
SKILL.md names no scripts, command-line tools or credentials: Med Sports 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.
Med Sports is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 4.4k tokens (SKILL.md is roughly 18k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 8.5k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Med Sports: Asd Ste100 (danyuchn/asd-ste100-skill, 4.3k stars), AI Copywriter (mikiarlo3/ai-copywriter, 1.2k stars), Brand Voice Guide (luongnv89/claude-howto, 42k stars) and Ralph Copywriter (muratcankoylan/ralph-wiggum-marketer, 778 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
asgard-ai-platform (a GitHub organization) maintains it in asgard-ai-platform/skills, which has 242 GitHub stars. The repository holds 207 skills in this directory. The repository was last updated on June 6, 2026.
Source: asgard-ai-platform/skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.