Implement
sickn33/agentic-awesome-skills
Implement a piece of work based on a PRD or set of issues. An agent skill from sickn33/agentic-awesome-skills.
Implement paper-defined attention variants by extracting mechanism invariants, mapping tensor shapes, preserving module interfaces, validating numerical behavior, and integrating the custom…
Apache-2.0Auto-check passed
Install Attention Variants From Papers
$ npx skills add benchflow-ai/skillsbench --skill attention-variants-from-papers -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install benchflow-ai/skillsbench attention-variants-from-papers --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/benchflow-ai/skillsbench.git skills-src && mkdir -p .claude/skills && cp -r skills-src/tasks-extra/diff-transformer_impl/environment/skills/attention-variants-from-papers .claude/skills/attention-variants-from-papers && 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 "attention-variants-from-papers" agent skill from https://github.com/benchflow-ai/skillsbench/tree/main/tasks-extra/diff-transformer_impl/environment/skills/attention-variants-from-papers into .claude/skills/attention-variants-from-papers/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "attention-variants-from-papers", 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/benchflow-ai/skillsbench/tree/main/tasks-extra/diff-transformer_impl/environment/skills/attention-variants-from-papersType 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 benchflow-ai/skillsbench --skill attention-variants-from-papers -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install benchflow-ai/skillsbench attention-variants-from-papers --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/benchflow-ai/skillsbench.git skills-src && mkdir -p .agents/skills && cp -r skills-src/tasks-extra/diff-transformer_impl/environment/skills/attention-variants-from-papers .agents/skills/attention-variants-from-papers && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "attention-variants-from-papers" agent skill from https://github.com/benchflow-ai/skillsbench/tree/main/tasks-extra/diff-transformer_impl/environment/skills/attention-variants-from-papers into .agents/skills/attention-variants-from-papers/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "attention-variants-from-papers", 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 benchflow-ai/skillsbench --skill attention-variants-from-papers -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install benchflow-ai/skillsbench attention-variants-from-papers --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/benchflow-ai/skillsbench.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/tasks-extra/diff-transformer_impl/environment/skills/attention-variants-from-papers .cursor/skills/attention-variants-from-papers && 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 "attention-variants-from-papers" agent skill from https://github.com/benchflow-ai/skillsbench/tree/main/tasks-extra/diff-transformer_impl/environment/skills/attention-variants-from-papers into .cursor/skills/attention-variants-from-papers/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "attention-variants-from-papers", 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/benchflow-ai/skillsbench.git --path tasks-extra/diff-transformer_impl/environment/skills/attention-variants-from-papers--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 benchflow-ai/skillsbench --skill attention-variants-from-papers -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install benchflow-ai/skillsbench attention-variants-from-papers --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/benchflow-ai/skillsbench.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/tasks-extra/diff-transformer_impl/environment/skills/attention-variants-from-papers .gemini/skills/attention-variants-from-papers && 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 "attention-variants-from-papers" agent skill from https://github.com/benchflow-ai/skillsbench/tree/main/tasks-extra/diff-transformer_impl/environment/skills/attention-variants-from-papers into .gemini/skills/attention-variants-from-papers/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "attention-variants-from-papers", 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 benchflow-ai/skillsbench attention-variants-from-papersInstalls 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 benchflow-ai/skillsbench --skill attention-variants-from-papers -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/benchflow-ai/skillsbench.git skills-src && mkdir -p .github/skills && cp -r skills-src/tasks-extra/diff-transformer_impl/environment/skills/attention-variants-from-papers .github/skills/attention-variants-from-papers && 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 "attention-variants-from-papers" agent skill from https://github.com/benchflow-ai/skillsbench/tree/main/tasks-extra/diff-transformer_impl/environment/skills/attention-variants-from-papers into .github/skills/attention-variants-from-papers/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "attention-variants-from-papers", 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 benchflow-ai/skillsbench --skill attention-variants-from-papers -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install benchflow-ai/skillsbench attention-variants-from-papers --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/benchflow-ai/skillsbench.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/tasks-extra/diff-transformer_impl/environment/skills/attention-variants-from-papers .opencode/skills/attention-variants-from-papers && 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 "attention-variants-from-papers" agent skill from https://github.com/benchflow-ai/skillsbench/tree/main/tasks-extra/diff-transformer_impl/environment/skills/attention-variants-from-papers into .opencode/skills/attention-variants-from-papers/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "attention-variants-from-papers", 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
attention-variants-from-papers- GitHub stars
- 1.8k
- Token cost
- ~669 tokens
- SKILL.md length
- 260 words
- Files
- 6 (incl. references)
- Skills in repo
- 189
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Implement paper-defined attention variants by extracting mechanism invariants, mapping tensor shapes, preserving module interfaces, validating numerical behavior, and integrating the custom…
- Works in 6 steps: Read the paper for invariants, not names. → Build a shape ledger before coding. → Choose the mechanism pattern. → …
- SKILL.md covers Workflow, Checklist and Reference Map
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Attention Variants From Papers is an agent skill from benchflow-ai/skillsbench. Implement paper-defined attention variants by extracting mechanism invariants, mapping tensor shapes, preserving module interfaces, validating numerical behavior, and integrating the custom attention into an existing transformer stack.
Its SKILL.md is about 670 tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including reference files (for example `references/mechanism-patterns.md`, `references/paper-to-implementation.md` and `references/shape-ledger.md`).
The repository describes itself as: SkillsBench evaluates how well skills work and how effective agents are at using them. The licence is Apache-2.0.
Example prompts
- “/attention-variants-from-papers”
Workflow steps
6 steps, taken from the first numbered list in SKILL.md.
- Read the paper for invariants, not names.
- Build a shape ledger before coding.
- Choose the mechanism pattern.
- Preserve the module boundary.
- Validate in layers.
- Integrate into the stack last.
What it can do on your machine
Read from SKILL.md and the folder at commit 9a1f4dd. 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
Attention Variants From Papers loads about 669 tokens when it runs, and up to ~2.4k if it reads all its reference files. Until then it costs about 67 tokens; SKILL.md has 260 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 benchflow-ai/skillsbench at commit 9a1f4dd, republished under its Apache-2.0 licence (© benchflow-ai). 260 words, ~669 tokens.
Download SKILL.mdSave it as
.claude/skills/attention-variants-from-papers/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.- name
- attention-variants-from-papers
- description
- Implement paper-defined attention variants by extracting mechanism invariants, mapping tensor shapes, preserving module interfaces, validating numerical behavior, and integrating the custom attention into an existing transformer stack.
Attention Variants from Papers
Use this skill when a paper changes how attention scores, branches, normalization, or head sharing work, but the module still needs to behave like a drop-in transformer attention block.
Workflow
- Read the paper for invariants, not names. Use paper-to-implementation.md to extract the external contract, the changed computation, and the training-time constraints.
- Build a shape ledger before coding. Use shape-ledger.md to track projections, head grouping, branch count, and output width.
- Choose the mechanism pattern. Use mechanism-patterns.md for subtractive attention, branch mixing, learned gates, and extra normalization.
- Preserve the module boundary. Keep the same input and output shape, mask semantics, positional encoding flow, and cache behavior unless the task explicitly changes them.
- Validate in layers. Start with random-tensor smoke tests, then compare against a baseline attention path. Use stability-and-validation.md.
- Integrate into the stack last. Swap the new module into one transformer block, verify the residual path, then roll it through the full model. Use transformer-integration.md.
Checklist
- extract the paper's invariants before writing code
- account for every reshape, branch, and repeat in a shape ledger
- preserve output width at concatenation or output projection
- apply masks and positional terms at the intended stage
- confirm random smoke tests stay finite
- compare unchanged behaviors against a baseline attention implementation
Reference Map
- paper-to-implementation.md: turn paper text into module invariants and coding decisions
- shape-ledger.md: keep dimensions consistent while branch structure changes
- mechanism-patterns.md: reusable patterns for nonstandard score composition and mixing
- stability-and-validation.md: numerical checks, smoke tests, and baseline comparisons
- transformer-integration.md: wire the custom module into an existing transformer block
© benchflow-ai, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 5 other files (references) in tasks-extra/diff-transformer_impl/environment/skills/attention-variants-from-papers of benchflow-ai/skillsbench.
- SKILL.md
- references/mechanism-patterns.md
- references/paper-to-implementation.md
- references/shape-ledger.md
- references/stability-and-validation.md
- references/transformer-integration.md
Open the folder on GitHubat commit 9a1f4dd
Compare with similar skills
Attention Variants From Papers 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 |
|---|---|---|---|---|---|---|
| Attention Variants From Papers this skillbenchflow-ai/skillsbench | 1.8k | — | ~669 | Automated safety check: Pass | Apache-2.0 | |
| Implementsickn33/agentic-awesome-skills | 47k | 5 repos | ~306 | Automated safety check: Pass | MIT | |
| Implementcodewhale-hq/Codewhale | 41k | — | ~190 | Automated safety check: Pass | MIT | |
| Papers Skillsickn33/agentic-awesome-skills | 47k | 1 repos | ~2.1k | Automated safety check: Pass | MIT | |
| Bgpt Paper SearchK-Dense-AI/scientific-agent-skills | 48k | 1 repos | ~2k | Automated safety check: Pass | MIT | |
| Extractalirezarezvani/claude-skills | 28k | — | ~1.4k | Automated safety check: Pass | MIT |
Similar skills
Implement
codewhale-hq/Codewhale
Carry an authorized, defined request or approved plan through scoped edits and proportionate verification.
Papers Skill
sickn33/agentic-awesome-skills
Skill for academic research workflows: search Semantic Scholar (200M+ papers), inspect citations, download arXiv PDFs, and extract PDF text.
Bgpt Paper Search
K-Dense-AI/scientific-agent-skills
Searches BGPT scientific papers by topic or DOI and retrieves claim-level evidence extracted from full text, including experiments, reported statistics, scope, limitations, and provenance.
Extract
alirezarezvani/claude-skills
Turn a proven pattern or debugging solution into a standalone reusable skill with SKILL.md, reference docs, and examples.
Slo Implementation
wshobson/agents
Define and implement Service Level Indicators (SLIs) and Service Level Objectives (SLOs) with error budgets and alerting.
More from benchflow-ai/skillsbench
All 189 skills in this repoLean4 Memories
benchflow-ai/skillsbench
This skill should be used when working on Lean 4 formalization projects to maintain persistent memory of successful proof patterns, failed approaches, project conventions, and user preferences…
Senior Data Engineer
benchflow-ai/skillsbench
World-class data engineering skill for building scalable data pipelines, ETL/ELT systems, real-time streaming, and data infrastructure.
Ac Branch Pi Model
benchflow-ai/skillsbench
AC branch pi-model power flow equations (P/Q and |S|) with transformer tap ratio and phase shift, matching acopf-math-model.md and MATPOWER branch fields.
Civ6lib
benchflow-ai/skillsbench
Civilization 6 district mechanics library. An agent skill from benchflow-ai/skillsbench.
D3 Visualization
benchflow-ai/skillsbench
Build deterministic, verifiable data visualizations with D3.js (v6).
Dc Power Flow
benchflow-ai/skillsbench
DC power flow analysis for power systems. An agent skill from benchflow-ai/skillsbench.
Questions about Attention Variants From Papers
What does Attention Variants From Papers do?
Implement paper-defined attention variants by extracting mechanism invariants, mapping tensor shapes, preserving module interfaces, validating numerical behavior, and integrating the custom…. Attention Variants From Papers is an agent skill from benchflow-ai/skillsbench. Implement paper-defined attention variants by extracting mechanism invariants, mapping tensor shapes, preserving module interfaces, validating numerical behavior, and integrating the custom attention into an existing transformer stack.
How do I install Attention Variants From Papers in Claude Code?
Run `npx skills add benchflow-ai/skillsbench --skill attention-variants-from-papers -a claude-code`. Or copy the skill folder (tasks-extra/diff-transformer_impl/environment/skills/attention-variants-from-papers in benchflow-ai/skillsbench) into .claude/skills/attention-variants-from-papers in your project. Claude Code loads it when a task matches its description.
How do I install Attention Variants From Papers in Codex?
Run `npx skills add benchflow-ai/skillsbench --skill attention-variants-from-papers -a codex`. Or copy the skill folder (tasks-extra/diff-transformer_impl/environment/skills/attention-variants-from-papers in benchflow-ai/skillsbench) into .agents/skills/attention-variants-from-papers in your project. Codex loads it when a task matches its description.
Can I use Attention Variants From Papers 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 benchflow-ai/skillsbench --skill attention-variants-from-papers -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/attention-variants-from-papers, .gemini/skills/attention-variants-from-papers, .github/skills/attention-variants-from-papers and .opencode/skills/attention-variants-from-papers in your project.
What does Attention Variants From Papers need to run?
SKILL.md names no scripts, command-line tools or credentials: Attention Variants From Papers is instructions for the agent only.
Does Attention Variants From Papers 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 Attention Variants From Papers 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 Attention Variants From Papers use?
Attention Variants From Papers is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Attention Variants From Papers use?
About 669 tokens (SKILL.md is roughly 2.7k 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 1.8k tokens, read only when the agent opens those files.
What are the alternatives to Attention Variants From Papers?
Skills that share tags, products or a category with Attention Variants From Papers: Implement (sickn33/agentic-awesome-skills, 47k stars), Implement (codewhale-hq/Codewhale, 41k stars), Papers Skill (sickn33/agentic-awesome-skills, 47k stars) and Bgpt Paper Search (K-Dense-AI/scientific-agent-skills, 48k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Attention Variants From Papers?
benchflow-ai (a GitHub organization) maintains it in benchflow-ai/skillsbench, which has 1,835 GitHub stars. The repository holds 189 skills in this directory. The repository was last updated on July 23, 2026.
Source: benchflow-ai/skillsbench on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.