China AI Compliance Audit
jnMetaCode/shellward
按中国法规（网安法 / PIPL / 等保2.0 / 数据出境 / AI生成内容标识）审计一个 AI 项目的代码仓库，产出每条都带 文件:行 取证、经独立复核、经脚本校验的合规报告。当用户问「这个项目上线合不合规」「调用了 OpenAI/Claude 算不算数据出境」「要不要做 AI 标识」「帮我做合规自查/等保/PIPL 检查」时使用。Audit an AI project's…
A skill your agent uses when deciding whether a responsible-AI project belongs at ACM FAccT or should route to a pure-ML venue (NeurIPS/ICML/ICLR), an HCI venue (CHI/CSCW), a law/policy venue, or an…
Install Facct Topic Selection
$ npx skills add brycewang-stanford/Awesome-Journal-Skills --skill facct-topic-selection -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install brycewang-stanford/Awesome-Journal-Skills facct-topic-selection --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/brycewang-stanford/Awesome-Journal-Skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/FAccT-Skills/skills/facct-topic-selection .claude/skills/facct-topic-selection && 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 "facct-topic-selection" agent skill from https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/FAccT-Skills/skills/facct-topic-selection into .claude/skills/facct-topic-selection/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "facct-topic-selection", 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/brycewang-stanford/Awesome-Journal-Skills/tree/main/FAccT-Skills/skills/facct-topic-selectionType 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 brycewang-stanford/Awesome-Journal-Skills --skill facct-topic-selection -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install brycewang-stanford/Awesome-Journal-Skills facct-topic-selection --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/brycewang-stanford/Awesome-Journal-Skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/FAccT-Skills/skills/facct-topic-selection .agents/skills/facct-topic-selection && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "facct-topic-selection" agent skill from https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/FAccT-Skills/skills/facct-topic-selection into .agents/skills/facct-topic-selection/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "facct-topic-selection", 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 brycewang-stanford/Awesome-Journal-Skills --skill facct-topic-selection -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install brycewang-stanford/Awesome-Journal-Skills facct-topic-selection --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/brycewang-stanford/Awesome-Journal-Skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/FAccT-Skills/skills/facct-topic-selection .cursor/skills/facct-topic-selection && 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 "facct-topic-selection" agent skill from https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/FAccT-Skills/skills/facct-topic-selection into .cursor/skills/facct-topic-selection/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "facct-topic-selection", 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/brycewang-stanford/Awesome-Journal-Skills.git --path FAccT-Skills/skills/facct-topic-selection--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 brycewang-stanford/Awesome-Journal-Skills --skill facct-topic-selection -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install brycewang-stanford/Awesome-Journal-Skills facct-topic-selection --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/brycewang-stanford/Awesome-Journal-Skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/FAccT-Skills/skills/facct-topic-selection .gemini/skills/facct-topic-selection && 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 "facct-topic-selection" agent skill from https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/FAccT-Skills/skills/facct-topic-selection into .gemini/skills/facct-topic-selection/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "facct-topic-selection", 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 brycewang-stanford/Awesome-Journal-Skills facct-topic-selectionInstalls 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 brycewang-stanford/Awesome-Journal-Skills --skill facct-topic-selection -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/brycewang-stanford/Awesome-Journal-Skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/FAccT-Skills/skills/facct-topic-selection .github/skills/facct-topic-selection && 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 "facct-topic-selection" agent skill from https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/FAccT-Skills/skills/facct-topic-selection into .github/skills/facct-topic-selection/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "facct-topic-selection", 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 brycewang-stanford/Awesome-Journal-Skills --skill facct-topic-selection -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install brycewang-stanford/Awesome-Journal-Skills facct-topic-selection --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/brycewang-stanford/Awesome-Journal-Skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/FAccT-Skills/skills/facct-topic-selection .opencode/skills/facct-topic-selection && 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 "facct-topic-selection" agent skill from https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/FAccT-Skills/skills/facct-topic-selection into .opencode/skills/facct-topic-selection/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "facct-topic-selection", 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
facct-topic-selection- GitHub stars
- 1.2k
- Token cost
- ~1.7k tokens
- SKILL.md length
- 677 words
- Files
- 1
- Skills in repo
- 2,387
- Repo updated
- First seen
- Licence
- MIT
At a glance
A skill your agent uses when deciding whether a responsible-AI project belongs at ACM FAccT or should route to a pure-ML venue (NeurIPS/ICML/ICLR), an HCI venue (CHI/CSCW), a law/policy venue, or an…
- Deciding whether a responsible-AI project belongs at ACM FAccT
- SKILL.md covers The routing question that…, Sibling-venue routing table, Contribution shapes FAccT… and The two sharpening tests, plus 3 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
- Should route to a pure-ML venue (NeurIPS/ICML/ICLR)
What it does
Facct Topic Selection is an agent skill from brycewang-stanford/Awesome-Journal-Skills. Use when deciding whether a responsible-AI project belongs at ACM FAccT or should route to a pure-ML venue (NeurIPS/ICML/ICLR), an HCI venue (CHI/CSCW), a law/policy venue, or an AI-ethics venue (AIES), by testing whether fairness, accountability, or transparency is a first-class contribution and whether the interdisciplinary framing is native rather than bolted on.
Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Legal & Compliance, covering LLM guardrails and AI governance. The repository describes itself as: Journal-specific Claude Code/Codex skill packs covering mainstream journals — AER, QJE, Nature, Cell, 管理世界, 经济研究 & 200+ more — your fast track to getting published. ｜ 覆盖主流期刊的… The licence is MIT.
When your agent uses it
- Deciding whether a responsible-AI project belongs at ACM FAccT
- Should route to a pure-ML venue (NeurIPS/ICML/ICLR)
- An HCI venue (CHI/CSCW)
- A law/policy venue
Example prompts
- “/facct-topic-selection”
What it can do on your machine
Read from SKILL.md and the folder at commit 932eb23. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Facct Topic Selection loads about 1.7k tokens when it runs. Until then it costs about 98 tokens; SKILL.md has 677 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); files beside SKILL.md are not scanned.
SKILL.md
The full file from brycewang-stanford/Awesome-Journal-Skills at commit 932eb23, republished under its MIT licence (© brycewang-stanford). 677 words, ~1,693 tokens.
Download SKILL.mdSave it as
.claude/skills/facct-topic-selection/SKILL.md (or your agent's skills folder).- name
- facct-topic-selection
- description
- Use when deciding whether a responsible-AI project belongs at ACM FAccT or should route to a pure-ML venue (NeurIPS/ICML/ICLR), an HCI venue (CHI/CSCW), a law/policy venue, or an AI-ethics venue (AIES), by testing whether fairness, accountability, or transparency is a first-class contribution and whether the interdisciplinary framing is native rather than bolted on.
FAccT Topic Selection
Decide the venue before drafting. ACM FAccT — the Conference on Fairness, Accountability, and Transparency — is the flagship interdisciplinary responsible-AI venue. Its reviewer pool spans computer science, law, the social sciences, the humanities, and policy, and its defining demand is that fairness, accountability, or transparency (FAccT) is a first-class contribution, not a fairness paragraph appended to a systems result. A technically strong paper whose real center is a new model, a new interaction technique, or a doctrinal legal argument — with FAccT concerns merely gestured at — is respected and then rejected as out of scope.
The routing question that matters most
The decisive question is rarely "does this touch fairness/AI?" but "is a fairness, accountability, or transparency question the actual contribution, and is the sociotechnical framing native?" FAccT uniquely rewards work that takes the social and the technical as inseparable. A paper that would lose nothing if you deleted the equity framing belongs elsewhere; a paper whose whole point is who is harmed, who is accountable, or what can be made legible belongs here.
Sibling-venue routing table
| Signal in your project | Better home | Why |
|---|---|---|
| Fairness/accountability/transparency is the contribution; social + technical are entangled | ACM FAccT | The interdisciplinary responsible-AI flagship; FAccT concerns are first-class |
| A new model/algorithm whose fairness angle is a secondary evaluation | NeurIPS / ICML / ICLR | ML flagships; a fairness metric alone does not make it FAccT |
| A new interaction technique or system; the study is about use more than justice/power | CHI / CSCW | HCI flagships; FAccT wants the accountability/harm question central |
| Primarily doctrinal legal analysis or regulatory design for a legal readership | Law reviews / policy venues | FAccT welcomes law, but wants cross-disciplinary reach, not doctrine alone |
| AI-ethics argument aimed at a philosophy/ethics readership | AIES and adjacent | Overlapping sibling; FAccT leans empirical + sociotechnical + policy-facing |
| Critical/qualitative/participatory engagement better as a session than a paper | FAccT CRAFT track | Participatory and world-building formats live in CRAFT, not the paper track |
Contribution shapes FAccT rewards
FAccT is genuinely pluralistic — the following are all native, and a good program mixes them:
- Algorithmic fairness / interpretability method — a new measure, algorithm, or auditing technique for bias, recourse, explainability, or transparency, evaluated on real data (the fairness-metrics lineage).
- Empirical audit — measuring disparate performance or harm in a deployed or commercial system across subgroups (the Gender Shades lineage).
- Documentation / accountability infrastructure — datasheets, model cards, data statements, audit frameworks, and impact-assessment tooling that change how the field builds and reports (the Model Cards / Datasheets lineage).
- Critical / conceptual / position work — an argument that reframes what the field takes for granted about harm, power, or measurement (the Stochastic Parrots lineage).
- Qualitative / sociotechnical study — interviews, ethnography, or a case study of how a system affects an affected community or institution, with sound method.
- Law & policy — legal, regulatory, or governance analysis that engages the technical substrate and reaches a mixed audience.
Show full SKILL.md (211 more words)Show less
The two sharpening tests
- Delete-the-equity test: remove every sentence about fairness, accountability, transparency, harm, or power. If a complete, publishable contribution remains, the FAccT framing is decoration — route to the ML/HCI/legal home of the surviving core. If nothing coherent remains without it, FAccT is right.
- Mixed-reviewer test: imagine your paper read by a computer scientist, a lawyer, and a qualitative social scientist at once. FAccT-shaped work gives each of them something to hold and survives all three; a paper that only one of them can evaluate is usually a sibling-venue paper wearing a FAccT title.
Interdisciplinary rigor, not interdisciplinary gesture
Fit is necessary but not sufficient. FAccT reviewers penalize thin interdisciplinarity: a CS paper that cites one sociology book without method, or a critical paper that name-drops an algorithm it never engages. Whichever lane you sit in, meet that lane's standard of rigor — statistical care and honest baselines for a method/audit paper; coding schemes, saturation, and reflexivity for a qualitative paper; doctrinal precision for a legal paper — and then connect it across the divide.
Cheap reconnaissance before committing
[Scope] scan the last two FAccT programs (facctconference.org, ACM DL, dblp db/conf/fat) for
your topic -> several recent papers = a reviewer pool exists; none = opening or mismatch
[Focus areas] can you name a primary + secondary FAccT focus area (algorithm development; data &
algorithm evaluation; applications; human factors; privacy & security; law; policy;
critical/humanistic/social-scientific) that genuinely fit? -> if not, reconsider the venue
[Audience] would a lawyer AND a computer scientist both find a contribution? -> that dual pull is
the FAccT signature; a single-discipline pull points to a sibling venueDecision procedure
[Who is affected] whose fairness/accountability/transparency changes if the claim holds?
[Contribution type] method / audit / documentation-infra / critical-conceptual / qualitative / law-policy
[First-class check] delete-the-equity test -> does a contribution survive without the FAccT framing?
[Interdisciplinary check] mixed-reviewer test -> do a CS + a law + a social-science reader each hold something?
[Format check] is it a paper, or a participatory session? -> paper track vs CRAFT
[Verdict] FAccT paper track / FAccT CRAFT / sibling venue (NeurIPS/ICML/CHI/AIES/law), one-line reasonRun this before the writing skills; a wrong venue decision wastes every later step. When the verdict
is FAccT, continue with facct-workflow for the calendar and facct-writing-style for the paper
shape.
© brycewang-stanford, 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 FAccT-Skills/skills/facct-topic-selection of brycewang-stanford/Awesome-Journal-Skills.
Open the folder on GitHubat commit 932eb23
Compare with similar skills
Facct Topic Selection 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 |
|---|---|---|---|---|---|---|
| Facct Topic Selection this skillbrycewang-stanford/Awesome-Journal-Skills | 1.2k | — | ~1.7k | Automated safety check: Pass | MIT | |
| China AI Compliance AuditjnMetaCode/shellward | 140 | — | ~1.1k | Automated safety check: Pass | Apache-2.0 | |
| Iso42001Sushegaad/Claude-Skills-Governance-Risk-and-Compliance | 942 | 1 repos | ~3.7k | Automated safety check: Pass | MIT | |
| AI GovernanceHack23/cia | 239 | — | ~1.4k | Automated safety check: Pass | Apache-2.0 | |
| Stuart RussellK-Dense-AI/mimeo | 282 | — | ~1.6k | Automated safety check: Pass | MIT | |
| Yoshua BengioK-Dense-AI/mimeo | 282 | — | ~1.8k | Automated safety check: Pass | MIT |
Similar skills
Iso42001
Sushegaad/Claude-Skills-Governance-Risk-and-Compliance
Expert ISO 42001 AI Management System (AIMS) compliance advisor.
AI Governance
Hack23/cia
AI governance, EU AI Act compliance, OWASP LLM security, responsible AI practices for GitHub Copilot agents
Stuart Russell
K-Dense-AI/mimeo
Applies the reasoning of Stuart Russell, AI safety expert, UC Berkeley professor, and co-author of 'Artificial Intelligence: A Modern Approach'.
Yoshua Bengio
K-Dense-AI/mimeo
Applies the reasoning, AI safety frameworks, and deep learning principles of Yoshua Bengio (Turing Award winner, Mila).
Iso42001 AI Management
borghei/Claude-Skills
ISO 42001 AI Management System (AIMS) compliance. An agent skill from borghei/Claude-Skills.
More from brycewang-stanford/Awesome-Journal-Skills
All 2,387 skills in this repoAaag Data Analysis
brycewang-stanford/Awesome-Journal-Skills
A skill your agent uses when running and reporting the analysis for an Annals of the American Association of Geographers manuscript — spatial statistics and modeling, remote-sensing accuracy, or…
Aaag Literature Positioning
brycewang-stanford/Awesome-Journal-Skills
A skill your agent uses when positioning an Annals of the American Association of Geographers manuscript in the literature — engaging geographic scholarship across the relevant area and the…
Aaag Rebuttal
brycewang-stanford/Awesome-Journal-Skills
A skill your agent uses when responding to an Annals of the American Association of Geographers decision letter (major/minor revision) — building a point-by-point response to the subject editor and…
Aaag Research Design
brycewang-stanford/Awesome-Journal-Skills
A skill your agent uses when defending the research design of an Annals of the American Association of Geographers manuscript — spatial/quantitative analysis and GIScience, remote-sensing and…
Aaag Review Process
brycewang-stanford/Awesome-Journal-Skills
A skill your agent uses when you need to understand how the Annals of the American Association of Geographers evaluates a manuscript — double-anonymous review routed through a subject editor by…
Aaag Submission
brycewang-stanford/Awesome-Journal-Skills
A skill your agent uses when running the final pre-submission preflight for the Annals of the American Association of Geographers via ScholarOne Manuscripts — area/article-type selection…
Related
Categories
Questions about Facct Topic Selection
What does Facct Topic Selection do?
A skill your agent uses when deciding whether a responsible-AI project belongs at ACM FAccT or should route to a pure-ML venue (NeurIPS/ICML/ICLR), an HCI venue (CHI/CSCW), a law/policy venue, or an…. Facct Topic Selection is an agent skill from brycewang-stanford/Awesome-Journal-Skills. Use when deciding whether a responsible-AI project belongs at ACM FAccT or should route to a pure-ML venue (NeurIPS/ICML/ICLR), an HCI venue (CHI/CSCW), a law/policy venue, or an AI-ethics venue (AIES), by testing whether fairness, accountability, or transparency is a first-class contribution and whether the interdisciplinary framing is native rather than bolted on.
When should I use Facct Topic Selection?
Facct Topic Selection fits situations like: deciding whether a responsible-AI project belongs at ACM FAccT; should route to a pure-ML venue (NeurIPS/ICML/ICLR); an HCI venue (CHI/CSCW); A law/policy venue.
How do I install Facct Topic Selection in Claude Code?
Run `npx skills add brycewang-stanford/Awesome-Journal-Skills --skill facct-topic-selection -a claude-code`. Or copy the skill folder (FAccT-Skills/skills/facct-topic-selection in brycewang-stanford/Awesome-Journal-Skills) into .claude/skills/facct-topic-selection in your project. Claude Code loads it when a task matches its description.
How do I install Facct Topic Selection in Codex?
Run `npx skills add brycewang-stanford/Awesome-Journal-Skills --skill facct-topic-selection -a codex`. Or copy the skill folder (FAccT-Skills/skills/facct-topic-selection in brycewang-stanford/Awesome-Journal-Skills) into .agents/skills/facct-topic-selection in your project. Codex loads it when a task matches its description.
Can I use Facct Topic Selection 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 brycewang-stanford/Awesome-Journal-Skills --skill facct-topic-selection -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/facct-topic-selection, .gemini/skills/facct-topic-selection, .github/skills/facct-topic-selection and .opencode/skills/facct-topic-selection in your project.
What does Facct Topic Selection need to run?
SKILL.md names no scripts, command-line tools or credentials: Facct Topic Selection is instructions for the agent only.
Does Facct Topic Selection 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 Facct Topic Selection 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 Facct Topic Selection use?
Facct Topic Selection 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 Facct Topic Selection use?
About 1.7k tokens (SKILL.md is roughly 6.8k 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 Facct Topic Selection?
Skills that share tags, products or a category with Facct Topic Selection: China AI Compliance Audit (jnMetaCode/shellward, 140 stars), Iso42001 (Sushegaad/Claude-Skills-Governance-Risk-and-Compliance, 942 stars), AI Governance (Hack23/cia, 239 stars) and Stuart Russell (K-Dense-AI/mimeo, 282 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Facct Topic Selection?
brycewang-stanford (a GitHub user) maintains it in brycewang-stanford/Awesome-Journal-Skills, which has 1,219 GitHub stars. The repository holds 2,387 skills in this directory. The repository was last updated on September 27, 2026.
Source: brycewang-stanford/Awesome-Journal-Skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.