Ito Compute
affaan-m/ECC
Query live GPU inventory, submit an authenticated Itô fixed-rate RFQ, inspect RFQ or procurement status, revoke device credentials, and run explicitly gated node qualification through the separately…
A skill your agent uses when deciding whether and how computation appears in a FOCS (IEEE Symposium on Foundations of Computer Science) paper — a venue that accepts on theorems with no evaluation…
MITAuto-check passed
Install Focs Experiments
$ npx skills add brycewang-stanford/Awesome-Journal-Skills --skill focs-experiments -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install brycewang-stanford/Awesome-Journal-Skills focs-experiments --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/FOCS-Skills/skills/focs-experiments .claude/skills/focs-experiments && 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 "focs-experiments" agent skill from https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/FOCS-Skills/skills/focs-experiments into .claude/skills/focs-experiments/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "focs-experiments", 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/FOCS-Skills/skills/focs-experimentsType 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 focs-experiments -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install brycewang-stanford/Awesome-Journal-Skills focs-experiments --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/FOCS-Skills/skills/focs-experiments .agents/skills/focs-experiments && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "focs-experiments" agent skill from https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/FOCS-Skills/skills/focs-experiments into .agents/skills/focs-experiments/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "focs-experiments", 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 focs-experiments -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install brycewang-stanford/Awesome-Journal-Skills focs-experiments --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/FOCS-Skills/skills/focs-experiments .cursor/skills/focs-experiments && 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 "focs-experiments" agent skill from https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/FOCS-Skills/skills/focs-experiments into .cursor/skills/focs-experiments/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "focs-experiments", 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 FOCS-Skills/skills/focs-experiments--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 focs-experiments -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install brycewang-stanford/Awesome-Journal-Skills focs-experiments --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/FOCS-Skills/skills/focs-experiments .gemini/skills/focs-experiments && 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 "focs-experiments" agent skill from https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/FOCS-Skills/skills/focs-experiments into .gemini/skills/focs-experiments/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "focs-experiments", 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 focs-experimentsInstalls 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 focs-experiments -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/FOCS-Skills/skills/focs-experiments .github/skills/focs-experiments && 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 "focs-experiments" agent skill from https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/FOCS-Skills/skills/focs-experiments into .github/skills/focs-experiments/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "focs-experiments", 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 focs-experiments -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 focs-experiments --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/FOCS-Skills/skills/focs-experiments .opencode/skills/focs-experiments && 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 "focs-experiments" agent skill from https://github.com/brycewang-stanford/Awesome-Journal-Skills/tree/main/FOCS-Skills/skills/focs-experiments into .opencode/skills/focs-experiments/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "focs-experiments", 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
focs-experiments- GitHub stars
- 1.2k
- Token cost
- ~1.6k tokens
- SKILL.md length
- 859 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 and how computation appears in a FOCS (IEEE Symposium on Foundations of Computer Science) paper — a venue that accepts on theorems with no evaluation…
- Computer-discovered constructions
- SKILL.md covers Referee questions, by…, Rigor pattern for a…, Discovered objects, honestly… and Where the computation is…, plus 3 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
- Honest illustrative plots
What it does
Focs Experiments is an agent skill from brycewang-stanford/Awesome-Journal-Skills. Use when deciding whether and how computation appears in a FOCS (IEEE Symposium on Foundations of Computer Science) paper — a venue that accepts on theorems with no evaluation section expected — covering machine-verified case analyses, computer-discovered constructions, and honest illustrative plots.
Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
The repository describes itself as: 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
- Computer-discovered constructions
- Honest illustrative plots
Example prompts
- “/focs-experiments”
Requirements
- Python 3
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 (its code samples are makefile).
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
Focs Experiments loads about 1.6k tokens when it runs. Until then it costs about 80 tokens; SKILL.md has 859 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). 859 words, ~1,631 tokens.
Download SKILL.mdSave it as
.claude/skills/focs-experiments/SKILL.md (or your agent's skills folder).- name
- focs-experiments
- description
- Use when deciding whether and how computation appears in a FOCS (IEEE Symposium on Foundations of Computer Science) paper — a venue that accepts on theorems with no evaluation section expected — covering machine-verified case analyses, computer-discovered constructions, and honest illustrative plots.
FOCS Experiments
FOCS solicits research on the theory of computation; nothing in the 2026 CFP asks for an evaluation, a benchmark, or an artifact (checked 2026-07-08). Most accepted papers contain no computation at all, and a submission that needs an empirical section to be persuasive is signaling that it belongs at an algorithms-engineering venue. Yet computation does appear in strong FOCS papers — inside proofs, behind constructions, and occasionally as a figure. This skill scopes each mode so it helps rather than hurts.
Referee questions, by computational mode
The useful frame is not "may I include code?" but "what will a theory referee ask about this computation?" — because each mode triggers a different interrogation:
| Mode | Referee's question | Your obligation |
|---|---|---|
| Case analysis inside a proof (finitely many configurations checked by program) | "If this program is wrong, is the theorem false?" | Yes → full rigor: deterministic run, published certificate, an independent checker a reader can audit |
| Search that found an object (a gadget, a code, a hard instance) later verified by hand | "Is the object's correctness independent of how it was found?" | Verify the found object analytically or by a trivially-auditable checker; describe the search in one honest sentence |
| Numerical exploration that motivated a conjecture-turned-theorem | "Does the paper claim anything based on the numerics?" | No claims may rest on it; at most a remark crediting the exploration |
| Illustrative plot of the algorithm's behavior | "Is this decoration or evidence?" | Label as illustration, disclose instance generation and seeds, make no comparative-performance claim |
The forbidden mode is the missing row: runtime comparisons against prior implementations. That evidence form has real homes — SODA's experimental track culture, ALENEX, ESA — and importing it into a FOCS submission invites the committee to judge the theorems as insufficient on their own.
Rigor pattern for a proof-bearing computation
When a lemma's truth rests on a machine check, engineer it like a proof step, because it is one. The pattern that satisfies skeptical referees:
# Lemma 4.7: no 3-colorable configuration of size <= 11 exists.
# The enumerator is complex; the checker is small enough to audit.
verify: configs.enum
python3 check_lemma47.py configs.enum # 40 lines, stdlib only
sha256sum -c configs.enum.sha256 # pin the enumerated set
configs.enum:
./enumerate --exhaustive --size 11 > configs.enumThree properties matter: the checker is short and transcribes a definition
from the paper verbatim; the enumerated evidence is content-addressed so a
re-run is comparable; and the paper's proof text says precisely what the
computation certifies ("the program verifies that each of the 2,146
configurations fails condition (ii) of Definition 4.5") rather than gesturing
at "extensive computer verification". Deposit the checker and the certificate
with the public full version (focs-artifact-evaluation).
Discovered objects, honestly credited
A construction found by simulated annealing, SAT solving, or an LLM-guided search is fully legitimate at FOCS — the community judges the object, not the finder. Honesty norms:
- Report the finder's nature truthfully; do not dress a heuristic search as exhaustive, and do not claim exhaustiveness you cannot certify (a nonexistence claim silently upgrades the computation to proof-bearing).
- If the object is small, print it in the paper; an explicit 40-entry table beats "available in our repository" for a reviewer deciding correctness.
- The interesting open question "why does this object exist?" can be posed as such — FOCS tolerates, even likes, a proof that works for reasons not yet structurally understood, provided the paper says so.
Show full SKILL.md (351 more words)Show less
Where the computation is described
Placement follows proof weight. A proof-bearing computation is described in
the proof itself — search space, what the output certifies, where the
certificate lives — because a proof with an undocumented machine step is
incomplete inside the ten-page window's promises (focs-writing-style). A
discovery gets one sentence at the construction's first appearance. An
illustration lives in a figure whose caption is self-sufficient. What never
works is a trailing "Implementation" section: it signals to a breadth
reviewer that the paper wants evaluation credit, and it buries proof-relevant
information where depth reviewers will not look for it.
Plots without performance theater
An illustration is admissible when it teaches, not when it argues. A figure showing the recursion depth of your algorithm on random instances can make an amortization argument vivid; the guardrails are a caption that names the instance distribution and seed, axes that start at zero or say why not, and no baseline curves — the presence of a competitor curve converts illustration into benchmark and triggers the missing-row problem above.
Disclosure when the finder is an AI system
Search by LLM-guided methods is entering theory workflows, and the norms above extend cleanly: the found object is still judged on its own verification, and the finder is still reported honestly ("the candidate inequality was proposed by an LLM-assisted search and verified in Lemma 5.2"). Two cautions specific to the current moment: check the live CFP for any AI-use disclosure policy before submission (none appeared in the FOCS 2026 CFP at the 2026-07-08 check; future cycles 待核实), and never let generated text stand in for a proof step — the verification obligations in the table above attach to the claim, not to the tool that produced it.
Decision rule
If deleting every computational element leaves the paper's claims intact, the
elements are decoration: keep only those that teach. If deleting one makes a
theorem unproved, that element is a proof step: give it proof-grade rigor. If
deleting them makes the paper unconvincing, the paper is at the wrong venue —
return to focs-topic-selection and route toward the algorithms-engineering
ecosystem before investing in FOCS formatting.
© 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 FOCS-Skills/skills/focs-experiments of brycewang-stanford/Awesome-Journal-Skills.
Open the folder on GitHubat commit 932eb23
Compare with similar skills
Focs Experiments 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 |
|---|---|---|---|---|---|---|
| Focs Experiments this skillbrycewang-stanford/Awesome-Journal-Skills | 1.2k | — | ~1.6k | Automated safety check: Pass | MIT | |
| Ito Computeaffaan-m/ECC | 275k | 1 repos | ~1.7k | Automated safety check: Pass | MIT | |
| Finding ExperimentsPostHog/posthog | 40k | — | ~783 | Automated safety check: Pass | Custom licence | |
| ExperimentsArize-ai/phoenix | 12k | — | ~1.8k | Automated safety check: Pass | Custom licence | |
| Scroll Experiencesickn33/agentic-awesome-skills | 47k | 2 repos | ~534 | Automated safety check: Pass | MIT | |
| Webgl Experiencenexu-io/open-design | 100k | — | ~903 | Automated safety check: Pass | Apache-2.0 |
Similar skills
- Official
Finding Experiments
PostHog/posthog
Resolves a PostHog experiment reference from natural language to a concrete experiment ID by browsing experiment-list (not feature-flag tools), with disambiguation when multiple experiments match.
Experiments
Arize-ai/phoenix
Run, read, and compare dataset-backed experiments to find evidence that a prompt or pipeline is improving.
Scroll Experience
sickn33/agentic-awesome-skills
Expert in building immersive scroll-driven experiences - parallax storytelling, scroll animations, interactive narratives, and cinematic web experiences.
Webgl Experience
nexu-io/open-design
A full-screen, real-time WebGL/WebGL2 experience — animated shaders, 3D scenes, generative visuals, particle fields — rendered live on the GPU with a typographic overlay.
- Official
Creating Experiments
PostHog/posthog
Guides agents through experiment creation: reading the project's setup with experiment-setup-context, defining the hypothesis, configuring rollout and bucketing, setting up analytics and running…
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…
Questions about Focs Experiments
What does Focs Experiments do?
A skill your agent uses when deciding whether and how computation appears in a FOCS (IEEE Symposium on Foundations of Computer Science) paper — a venue that accepts on theorems with no evaluation…. Focs Experiments is an agent skill from brycewang-stanford/Awesome-Journal-Skills. Use when deciding whether and how computation appears in a FOCS (IEEE Symposium on Foundations of Computer Science) paper — a venue that accepts on theorems with no evaluation section expected — covering machine-verified case analyses, computer-discovered constructions, and honest illustrative plots.
When should I use Focs Experiments?
Focs Experiments fits situations like: computer-discovered constructions; honest illustrative plots.
How do I install Focs Experiments in Claude Code?
Run `npx skills add brycewang-stanford/Awesome-Journal-Skills --skill focs-experiments -a claude-code`. Or copy the skill folder (FOCS-Skills/skills/focs-experiments in brycewang-stanford/Awesome-Journal-Skills) into .claude/skills/focs-experiments in your project. Claude Code loads it when a task matches its description.
How do I install Focs Experiments in Codex?
Run `npx skills add brycewang-stanford/Awesome-Journal-Skills --skill focs-experiments -a codex`. Or copy the skill folder (FOCS-Skills/skills/focs-experiments in brycewang-stanford/Awesome-Journal-Skills) into .agents/skills/focs-experiments in your project. Codex loads it when a task matches its description.
Can I use Focs Experiments 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 focs-experiments -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/focs-experiments, .gemini/skills/focs-experiments, .github/skills/focs-experiments and .opencode/skills/focs-experiments in your project.
What does Focs Experiments need to run?
SKILL.md names no scripts, command-line tools or credentials: Focs Experiments is instructions for the agent only. Our summary lists: Python 3.
Does Focs Experiments 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 Focs Experiments 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 Focs Experiments use?
Focs Experiments 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 Focs Experiments use?
About 1.6k tokens (SKILL.md is roughly 6.5k 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 Focs Experiments?
Skills that share tags, products or a category with Focs Experiments: Ito Compute (affaan-m/ECC, 275k stars), Finding Experiments (PostHog/posthog, 40k stars), Experiments (Arize-ai/phoenix, 12k stars) and Scroll Experience (sickn33/agentic-awesome-skills, 47k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Focs Experiments?
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.