Deepseek Reason
ruvnet/ruflo
Reasoning-mode completion against DeepSeek's deepseek-reasoner model (R1) via /v1/chat/completions.
Teaches how to reason from a transaction protocol’s rules to a working model.
Apache-2.0Auto-check passed
Install Transaction Protocol Reasoning
$ npx skills add benchflow-ai/skillsbench --skill transaction-protocol-reasoning -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install benchflow-ai/skillsbench transaction-protocol-reasoning --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/tictoc-unnecessary-abort-detection/environment/skills/transaction-protocol-reasoning .claude/skills/transaction-protocol-reasoning && 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 "transaction-protocol-reasoning" agent skill from https://github.com/benchflow-ai/skillsbench/tree/main/tasks/tictoc-unnecessary-abort-detection/environment/skills/transaction-protocol-reasoning into .claude/skills/transaction-protocol-reasoning/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "transaction-protocol-reasoning", 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/tictoc-unnecessary-abort-detection/environment/skills/transaction-protocol-reasoningType 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 transaction-protocol-reasoning -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install benchflow-ai/skillsbench transaction-protocol-reasoning --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/tictoc-unnecessary-abort-detection/environment/skills/transaction-protocol-reasoning .agents/skills/transaction-protocol-reasoning && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "transaction-protocol-reasoning" agent skill from https://github.com/benchflow-ai/skillsbench/tree/main/tasks/tictoc-unnecessary-abort-detection/environment/skills/transaction-protocol-reasoning into .agents/skills/transaction-protocol-reasoning/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "transaction-protocol-reasoning", 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 transaction-protocol-reasoning -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install benchflow-ai/skillsbench transaction-protocol-reasoning --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/tictoc-unnecessary-abort-detection/environment/skills/transaction-protocol-reasoning .cursor/skills/transaction-protocol-reasoning && 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 "transaction-protocol-reasoning" agent skill from https://github.com/benchflow-ai/skillsbench/tree/main/tasks/tictoc-unnecessary-abort-detection/environment/skills/transaction-protocol-reasoning into .cursor/skills/transaction-protocol-reasoning/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "transaction-protocol-reasoning", 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/tictoc-unnecessary-abort-detection/environment/skills/transaction-protocol-reasoning--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 transaction-protocol-reasoning -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install benchflow-ai/skillsbench transaction-protocol-reasoning --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/tictoc-unnecessary-abort-detection/environment/skills/transaction-protocol-reasoning .gemini/skills/transaction-protocol-reasoning && 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 "transaction-protocol-reasoning" agent skill from https://github.com/benchflow-ai/skillsbench/tree/main/tasks/tictoc-unnecessary-abort-detection/environment/skills/transaction-protocol-reasoning into .gemini/skills/transaction-protocol-reasoning/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "transaction-protocol-reasoning", 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 transaction-protocol-reasoningInstalls 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 transaction-protocol-reasoning -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/tictoc-unnecessary-abort-detection/environment/skills/transaction-protocol-reasoning .github/skills/transaction-protocol-reasoning && 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 "transaction-protocol-reasoning" agent skill from https://github.com/benchflow-ai/skillsbench/tree/main/tasks/tictoc-unnecessary-abort-detection/environment/skills/transaction-protocol-reasoning into .github/skills/transaction-protocol-reasoning/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "transaction-protocol-reasoning", 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 transaction-protocol-reasoning -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 transaction-protocol-reasoning --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/tictoc-unnecessary-abort-detection/environment/skills/transaction-protocol-reasoning .opencode/skills/transaction-protocol-reasoning && 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 "transaction-protocol-reasoning" agent skill from https://github.com/benchflow-ai/skillsbench/tree/main/tasks/tictoc-unnecessary-abort-detection/environment/skills/transaction-protocol-reasoning into .opencode/skills/transaction-protocol-reasoning/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "transaction-protocol-reasoning", 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
transaction-protocol-reasoning- GitHub stars
- 1.8k
- Token cost
- ~1k tokens
- SKILL.md length
- 365 words
- Files
- 8 (incl. references)
- Skills in repo
- 178
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Teaches how to reason from a transaction protocol’s rules to a working model.
- Works in 6 steps: Extract the contract: what does… → Inventory state: list each field, its… → Restate rules: convert prose/pseudocode… → …
- Analyzing a concurrency-control paper
- SKILL.md covers What “done” looks like, Quick Reference (pick the next…, Protocol Ledger (the “shape… and Workflow (operational), plus 1 more section
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Transaction Protocol Reasoning is an agent skill from benchflow-ai/skillsbench. Teaches how to reason from a transaction protocol’s rules to a working model. Use when analyzing a concurrency-control paper, spec, or algorithm to identify state, metadata, invariants, operation rules, examples, counterexamples, guarantees, false aborts, unsafe commits, or tradeoffs before inspecting concrete traces.
Its SKILL.md is about 1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 8 other files, including reference files (for example `references/counterexample-construction.md`, `references/example-construction.md` and `references/invariant-extraction.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.
When your agent uses it
- Analyzing a concurrency-control paper
- Algorithm to identify state
- Operation rules
- Counterexamples
Example prompts
- “Use the transaction-protocol-reasoning skill to teach how to reason from a transaction protocol’s rules to a working model”
- “/transaction-protocol-reasoning”
Workflow steps
6 steps, taken from the first numbered list in SKILL.md.
- Extract the contract: what does “correct” mean and what is in-scope?
- Inventory state: list each field, its scope, and what history fact it is intended to prove.
- Restate rules: convert prose/pseudocode into explicit “if … then … else abort/block” rules.
- Derive invariants: state what must always be true if the rules are correct.
- Run the example pack: step through 3–6 tiny histories and apply the rules mechanically.
- Locate conservative vs unsafe edges
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
Transaction Protocol Reasoning loads about 1k tokens when it runs, and up to ~6.7k if it reads all its reference files. Until then it costs about 88 tokens; SKILL.md has 365 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). 365 words, ~1,027 tokens.
Download SKILL.mdSave it as
.claude/skills/transaction-protocol-reasoning/SKILL.md (or your agent's skills folder). This skill also uses 7 other files; get the full folder from GitHub.- name
- transaction-protocol-reasoning
- description
- Teaches how to reason from a transaction protocol’s rules to a working model. Use when analyzing a concurrency-control paper, spec, or algorithm to identify state, metadata, invariants, operation rules, examples, counterexamples, guarantees, false aborts, unsafe commits, or tradeoffs before inspecting concrete traces.
Transaction Protocol Reasoning
Use this skill when a protocol is already given (paper, spec, pseudocode, implementation notes) and you need to understand what it guarantees and how its rules imply commit/abort behavior.
This skill does not ask you to invent a protocol. It teaches how to read a protocol description as a set of rules, turn those rules into checkable predicates/invariants, and then reason about safety vs conservatism.
What “done” looks like
By the end you should have:
- a one-page Protocol Ledger (state + rules + invariants)
- a minimal example pack (3–6 tiny histories) that exercises boundaries
- a clear statement of:
- the protocol’s proof object (what metadata it relies on), and
- its likely false-abort and unsafe-commit failure modes
Quick Reference (pick the next file to read)
| If you need… | Read |
|---|---|
| A step-by-step protocol reading workflow | protocol-analysis-workflow.md |
| Inventory protocol state + what each field proves | state-and-metadata-modeling.md |
| Restate read/write/validate/commit/abort as explicit rules | operation-rule-analysis.md |
| Extract invariants from rules (and distinguish conservative ones) | invariant-extraction.md |
| Build a small history suite that hits boundary behavior | example-construction.md |
| Build minimal counterexamples (unsafe commit vs conservative abort) | counterexample-construction.md |
| Compare two protocols by guarantees + metadata + allowed histories | protocol-comparison.md |
Protocol Ledger (the “shape ledger” equivalent)
Before you chase details, build a one-page protocol ledger:
Claimed guarantee:
Global state:
- per-object metadata: ...
- global clock/counters: ...
Per-transaction state:
- read set entries: (key, version-id?, local ts fields?, ...)
- write set entries: (key, buffered value?, lock?, ...)
- timestamps: start_ts?, commit_ts?, bounds?
Operations (as rules/predicates):
read(key): preconditions, version selection, metadata recorded/updated, failure modes
write(key): ...
validate(txn): ...
commit(txn): ...
abort/retry(txn): ...
Proof object:
- what metadata/rules constitute the correctness argument?
- what does the protocol “check” to justify commits?If you cannot fill a ledger line item without hand-waving (“it probably…”), you have found an underspecified part of the protocol. That is often where conservative aborts come from.
Show full SKILL.md (136 more words)Show less
Workflow (operational)
- Extract the contract: what does “correct” mean and what is in-scope?
- Inventory state: list each field, its scope, and what history fact it is intended to prove.
- Restate rules: convert prose/pseudocode into explicit “if … then … else abort/block” rules.
- Derive invariants: state what must always be true if the rules are correct.
- Run the example pack: step through 3–6 tiny histories and apply the rules mechanically.
- Locate conservative vs unsafe edges:
- conservative: rules reject a safe history (false abort / blocking)
- unsafe: rules accept a history that violates the contract
Common Failure Modes To Look For
- Metadata insufficiency: protocol needs old-version validity but stores only latest.
- Scope mismatch: uses per-key evidence to enforce cross-key ordering claims.
- Over-approx validation: uses a sufficient condition (safe) that is not necessary (causes false aborts).
© 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 7 other files (references) in tasks/tictoc-unnecessary-abort-detection/environment/skills/transaction-protocol-reasoning of benchflow-ai/skillsbench.
- SKILL.md
- references/counterexample-construction.md
- references/example-construction.md
- references/invariant-extraction.md
- references/operation-rule-analysis.md
- references/protocol-analysis-workflow.md
- references/protocol-comparison.md
- references/state-and-metadata-modeling.md
Open the folder on GitHubat commit 9a1f4dd
Compare with similar skills
Transaction Protocol Reasoning 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 |
|---|---|---|---|---|---|---|
| Transaction Protocol Reasoning this skillbenchflow-ai/skillsbench | 1.8k | — | ~1k | Automated safety check: Pass | Apache-2.0 | |
| Deepseek Reasonruvnet/ruflo | 74k | — | ~626 | Automated safety check: Notes | MIT | |
| Teachcursor/plugins | 10k | 9 repos | ~1.4k | Automated safety check: Pass | None | |
| Crossframe Teachsickn33/agentic-awesome-skills | 47k | 1 repos | ~943 | Automated safety check: Pass | MIT | |
| Teachvinvcn/mattpocock-skills-zh-CN | 4.7k | — | ~1.4k | Automated safety check: Pass | MIT | |
| Ejentum Reasoning Harnesssickn33/agentic-awesome-skills | 47k | 1 repos | ~1.9k | Automated safety check: Pass | MIT |
Similar skills
- Official
Teach
cursor/plugins
Explain a body of work plainly so a person actually understands it.
Crossframe Teach
sickn33/agentic-awesome-skills
A skill your agent uses when CrossFrame Suite routes explicit Chinese teaching of CrossFrame concepts, misreading boundaries, plain-language examples, signals, or exercises.
Teach
vinvcn/mattpocock-skills-zh-CN
在这个工作区中教用户一个新技能或概念。
Ejentum Reasoning Harness
sickn33/agentic-awesome-skills
MCP server exposing four cognitive harness modes (reasoning, code, anti-deception, memory).
Teach
ccplugins/awesome-claude-code-plugins
Teaches the Second Brain to recognize a new external data source.
More from benchflow-ai/skillsbench
All 178 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 Transaction Protocol Reasoning
What does Transaction Protocol Reasoning do?
Teaches how to reason from a transaction protocol’s rules to a working model. Transaction Protocol Reasoning is an agent skill from benchflow-ai/skillsbench. Teaches how to reason from a transaction protocol’s rules to a working model.
When should I use Transaction Protocol Reasoning?
Transaction Protocol Reasoning fits situations like: analyzing a concurrency-control paper; algorithm to identify state; operation rules; counterexamples.
How do I install Transaction Protocol Reasoning in Claude Code?
Run `npx skills add benchflow-ai/skillsbench --skill transaction-protocol-reasoning -a claude-code`. Or copy the skill folder (tasks/tictoc-unnecessary-abort-detection/environment/skills/transaction-protocol-reasoning in benchflow-ai/skillsbench) into .claude/skills/transaction-protocol-reasoning in your project. Claude Code loads it when a task matches its description.
How do I install Transaction Protocol Reasoning in Codex?
Run `npx skills add benchflow-ai/skillsbench --skill transaction-protocol-reasoning -a codex`. Or copy the skill folder (tasks/tictoc-unnecessary-abort-detection/environment/skills/transaction-protocol-reasoning in benchflow-ai/skillsbench) into .agents/skills/transaction-protocol-reasoning in your project. Codex loads it when a task matches its description.
Can I use Transaction Protocol Reasoning 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 transaction-protocol-reasoning -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/transaction-protocol-reasoning, .gemini/skills/transaction-protocol-reasoning, .github/skills/transaction-protocol-reasoning and .opencode/skills/transaction-protocol-reasoning in your project.
What does Transaction Protocol Reasoning need to run?
SKILL.md names no scripts, command-line tools or credentials: Transaction Protocol Reasoning is instructions for the agent only.
Does Transaction Protocol Reasoning 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 Transaction Protocol Reasoning 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 Transaction Protocol Reasoning use?
Transaction Protocol Reasoning 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 Transaction Protocol Reasoning use?
About 1k tokens (SKILL.md is roughly 4.1k 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 5.7k tokens, read only when the agent opens those files.
What are the alternatives to Transaction Protocol Reasoning?
Skills that share tags, products or a category with Transaction Protocol Reasoning: Deepseek Reason (ruvnet/ruflo, 74k stars), Teach (cursor/plugins, 10k stars), Crossframe Teach (sickn33/agentic-awesome-skills, 47k stars) and Teach (vinvcn/mattpocock-skills-zh-CN, 4.7k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Transaction Protocol Reasoning?
benchflow-ai (a GitHub organization) maintains it in benchflow-ai/skillsbench, which has 1,832 GitHub stars. The repository holds 178 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.