Research Refine
zjYao36/Auto-Research-Refine
Turns a vague research direction into a focused, problem-anchored method plan through up to five review rounds with a second model.
Evaluate Jacobian reliability using recently resolved conjectures as held-out probes.
Install Recent Conjecture Evaluations
$ npx skills add morluto/jacobian --skill recent-conjecture-evaluations -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install morluto/jacobian recent-conjecture-evaluations --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/morluto/jacobian.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/recent-conjecture-evaluations .claude/skills/recent-conjecture-evaluations && 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 "recent-conjecture-evaluations" agent skill from https://github.com/morluto/jacobian/tree/main/.agents/skills/recent-conjecture-evaluations into .claude/skills/recent-conjecture-evaluations/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "recent-conjecture-evaluations", 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/morluto/jacobian/tree/main/.agents/skills/recent-conjecture-evaluationsType 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 morluto/jacobian --skill recent-conjecture-evaluations -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install morluto/jacobian recent-conjecture-evaluations --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/morluto/jacobian.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/recent-conjecture-evaluations .agents/skills/recent-conjecture-evaluations && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "recent-conjecture-evaluations" agent skill from https://github.com/morluto/jacobian/tree/main/.agents/skills/recent-conjecture-evaluations into .agents/skills/recent-conjecture-evaluations/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "recent-conjecture-evaluations", 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 morluto/jacobian --skill recent-conjecture-evaluations -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install morluto/jacobian recent-conjecture-evaluations --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/morluto/jacobian.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/recent-conjecture-evaluations .cursor/skills/recent-conjecture-evaluations && 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 "recent-conjecture-evaluations" agent skill from https://github.com/morluto/jacobian/tree/main/.agents/skills/recent-conjecture-evaluations into .cursor/skills/recent-conjecture-evaluations/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "recent-conjecture-evaluations", 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/morluto/jacobian.git --path .agents/skills/recent-conjecture-evaluations--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 morluto/jacobian --skill recent-conjecture-evaluations -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install morluto/jacobian recent-conjecture-evaluations --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/morluto/jacobian.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/recent-conjecture-evaluations .gemini/skills/recent-conjecture-evaluations && 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 "recent-conjecture-evaluations" agent skill from https://github.com/morluto/jacobian/tree/main/.agents/skills/recent-conjecture-evaluations into .gemini/skills/recent-conjecture-evaluations/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "recent-conjecture-evaluations", 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 morluto/jacobian recent-conjecture-evaluationsInstalls 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 morluto/jacobian --skill recent-conjecture-evaluations -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/morluto/jacobian.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/recent-conjecture-evaluations .github/skills/recent-conjecture-evaluations && 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 "recent-conjecture-evaluations" agent skill from https://github.com/morluto/jacobian/tree/main/.agents/skills/recent-conjecture-evaluations into .github/skills/recent-conjecture-evaluations/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "recent-conjecture-evaluations", 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 morluto/jacobian --skill recent-conjecture-evaluations -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install morluto/jacobian recent-conjecture-evaluations --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/morluto/jacobian.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/recent-conjecture-evaluations .opencode/skills/recent-conjecture-evaluations && 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 "recent-conjecture-evaluations" agent skill from https://github.com/morluto/jacobian/tree/main/.agents/skills/recent-conjecture-evaluations into .opencode/skills/recent-conjecture-evaluations/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "recent-conjecture-evaluations", 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
recent-conjecture-evaluations- GitHub stars
- 211
- Token cost
- ~816 tokens
- SKILL.md length
- 375 words
- Files
- 8 (incl. scripts, references)
- Skills in repo
- 11
- Repo updated
- First seen
- Licence
- MIT
At a glance
Evaluate Jacobian reliability using recently resolved conjectures as held-out probes.
- Tasks that involve Math and symbolic computation
- SKILL.md covers Choose the requested mode, Preserve the evidence boundary and Completion and stalls
- Runs Python scripts from its folder; calls python
What it does
Recent Conjecture Evaluations is an agent skill from morluto/jacobian. Evaluate Jacobian reliability using recently resolved conjectures as held-out probes.
Its SKILL.md is about 820 tokens, which your agent loads only when the skill is triggered. The skill folder holds 10 other files, including scripts and reference files (for example `agents/openai.yaml`, `references/action-policy.md` and `references/evaluation-and-scoring.md`).
It sits in Research & Science, covering Math and symbolic computation. It works with Model Context Protocol. The repository describes itself as: Composable mathematics tools for agents. The licence is MIT.
When your agent uses it
- Tasks that involve Math and symbolic computation
Example prompts
- “/recent-conjecture-evaluations”
Requirements
- Python 3
What it can do on your machine
Read from SKILL.md and the folder at commit 9dc2aaf. 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
Ships 1 file in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
python
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
Recent Conjecture Evaluations loads about 816 tokens when it runs, and up to ~4.1k if it reads all its reference files. Until then it costs about 29 tokens; SKILL.md has 375 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); the scripts in this folder are not scanned.
SKILL.md
The full file from morluto/jacobian at commit 9dc2aaf, republished under its MIT licence (© morluto). 375 words, ~816 tokens.
Download SKILL.mdSave it as
.claude/skills/recent-conjecture-evaluations/SKILL.md (or your agent's skills folder). This skill also uses 7 other files; get the full folder from GitHub.- name
- recent-conjecture-evaluations
- description
- Evaluate Jacobian reliability using recently resolved conjectures as held-out probes.
Recent Conjecture Evaluations
Use recently resolved conjectures to probe Jacobian reliability. The outcome is an evidence-backed diagnosis, not a collection of solved examples. This skill owns source selection, deterministic replay, optional model comparisons, and attribution; Harbor packaging is a separate workflow.
Choose the requested mode
- Probe: read probe workflow for one source cycle, including source gating, independent oracle, current-main replay, and reporting.
- Review: inspect the completed cycle against source gating, the oracle and frozen inputs, and the applicable scoring rules. Use report fields to identify missing evidence. Reproduce disputed deterministic claims where useful; do not repeat model arms.
- Coordinate: search saved reports, reservations, and issue/PR ownership for the source and root mechanism. Use the inventory helper shown below and the ownership rules in action policy. Do not begin a new probe merely to answer a coordination question.
python .agents/skills/recent-conjecture-evaluations/scripts/search_inventory.py \
"source or root-cause phrase" outputs benchmarks/resultsPreserve the evidence boundary
Bind prompts, payloads, and oracles to the exact intended input. Reconstruct gold independently of evaluated model arms and distinguish source-supplied replay from an independent oracle. Record precise source status and dates. Computation, verification, imported theorems, and unproved claims establish different things. Timeouts, unavailable operations, and missing witnesses are non-conclusions. Never attribute a model's fallback or transcription error to Jacobian.
Audit new probes deterministically on current main before paid model calls. Run comparisons only when they resolve uncertainty that direct evidence cannot, with user-authorized cost boundaries and frozen control/treatment conditions. Do not weaken verification or create a benchmark-specific operation to make a probe pass. Before external action, apply the action policy within existing user authorization. This evaluation workflow produces at most a localized draft PR; merging is a separate user-authorized task.
Show full SKILL.md (104 more words)Show less
Completion and stalls
Complete one requested cycle by default, including rejected and deterministic-only outcomes. An oracle disagreement stops dependent model evaluation while allowing bounded diagnosis. A known unavailable operation skips dependent work, not the attribution and report. Preserve checkpoints and raw evidence at phase boundaries; inspect a phase without a checkpoint for 30 minutes.
Additional cycles or model calls must fit the operator's requested scope and cost limits. Retry a cancelled call only with new diagnostic evidence. Stop collecting examples for an owned root cause once the agreed independence threshold is met. Report unresolved evidence and a distinct next direction without silently starting it.
© morluto, MIT. 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 (scripts, references) in .agents/skills/recent-conjecture-evaluations of morluto/jacobian.
- SKILL.md
- agents/openai.yaml
- references/action-policy.md
- references/evaluation-and-scoring.md
- references/probe.md
- references/report-schema.md
- references/source-gating.md
- scripts/search_inventory.py
Open the folder on GitHubat commit 9dc2aaf
Compare with similar skills
Recent Conjecture Evaluations 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 |
|---|---|---|---|---|---|---|
| Recent Conjecture Evaluations this skillmorluto/jacobian | 211 | — | ~816 | Automated safety check: Pass | MIT | |
| Research RefinezjYao36/Auto-Research-Refine | 128 | 6 repos | ~6.9k | Automated safety check: Notes | None | |
| Read GitHubAgentTeam-TaichuAI/ScienceClaw | 671 | 2 repos | ~638 | Automated safety check: Pass | None | |
| Proof Run Orchestratorwanshuiyin/Auto-claude-code-research-in-sleep | 17k | 1 repos | ~4.7k | Automated safety check: Pass | MIT | |
| FirstdataMLT-OSS/FirstData | 183 | — | ~3.1k | Automated safety check: Pass | MIT | |
| Fin Generate Ideacsmar432/finai-research | 109 | — | ~2.5k | Automated safety check: Pass | MIT |
Similar skills
Read GitHub
AgentTeam-TaichuAI/ScienceClaw
Read and search GitHub repository documentation via gitmcp.io MCP service.
Proof Run Orchestrator
wanshuiyin/Auto-claude-code-research-in-sleep
Runs a mathematical proof project as a stateful pipeline of run directories: a local attempt first, then a manual GPT Pro handoff package, with an optional DeepSeek audit.
Firstdata
MLT-OSS/FirstData
Find official portals, APIs, and download paths for authoritative primary data sources (governments, international organizations, research institutions, etc.).
Fin Generate Idea
csmar432/finai-research
针对经济金融研究方向的创意生成与评估。生成8-12个可发表的研究idea，过滤后在数据可行的情况下进行小规模实证验证，输出排序后的研究想法报告。
- Official
Math Proof Solo
anthropics/claude-plugins-official
Solves one hard mathematics problem in a single session without subagents, keeping settled steps in a notes file and ending with a self-contained proof.md.
More from morluto/jacobian
All 11 skills in this repoHarbor Benchmarks
morluto/jacobian
Author, package, validate, or run mathematical evaluations as Jacobian Harbor datasets.
Audit Public Operation Contracts
morluto/jacobian
Design or audit a Jacobian operation’s mathematical contract, boundedness, exact results, and composition.
Decompose Mathematical Solution Corpora
morluto/jacobian
Extract reusable Jacobian capabilities from a mathematical solution corpus, rather than one agent trajectory.
Evaluate MCP Tool Adoption
morluto/jacobian
Investigate MCP tool availability, discovery, and selection, including controlled adoption evaluations.
Learn From Math Agent Trajectories
morluto/jacobian
Review mathematical agent trajectories for evidence-backed Jacobian improvements; do not resume solving.
Verifier Evaluations
morluto/jacobian
Design, audit, or repair mathematical benchmark verifiers, submission contracts, and scoring.
Related
Works with
Categories
Questions about Recent Conjecture Evaluations
What does Recent Conjecture Evaluations do?
Evaluate Jacobian reliability using recently resolved conjectures as held-out probes. Recent Conjecture Evaluations is an agent skill from morluto/jacobian. Evaluate Jacobian reliability using recently resolved conjectures as held-out probes.
When should I use Recent Conjecture Evaluations?
Recent Conjecture Evaluations fits situations like: tasks that involve Math and symbolic computation.
How do I install Recent Conjecture Evaluations in Claude Code?
Run `npx skills add morluto/jacobian --skill recent-conjecture-evaluations -a claude-code`. Or copy the skill folder (.agents/skills/recent-conjecture-evaluations in morluto/jacobian) into .claude/skills/recent-conjecture-evaluations in your project. Claude Code loads it when a task matches its description.
How do I install Recent Conjecture Evaluations in Codex?
Run `npx skills add morluto/jacobian --skill recent-conjecture-evaluations -a codex`. Or copy the skill folder (.agents/skills/recent-conjecture-evaluations in morluto/jacobian) into .agents/skills/recent-conjecture-evaluations in your project. Codex loads it when a task matches its description.
Can I use Recent Conjecture Evaluations 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 morluto/jacobian --skill recent-conjecture-evaluations -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/recent-conjecture-evaluations, .gemini/skills/recent-conjecture-evaluations, .github/skills/recent-conjecture-evaluations and .opencode/skills/recent-conjecture-evaluations in your project.
What does Recent Conjecture Evaluations need to run?
Going by SKILL.md and its folder, Recent Conjecture Evaluations needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python 3.
Does Recent Conjecture Evaluations 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 Recent Conjecture Evaluations 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Recent Conjecture Evaluations use?
Recent Conjecture Evaluations 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 Recent Conjecture Evaluations use?
About 816 tokens (SKILL.md is roughly 3.3k 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 3.3k tokens, read only when the agent opens those files.
What are the alternatives to Recent Conjecture Evaluations?
Skills that share tags, products or a category with Recent Conjecture Evaluations: Research Refine (zjYao36/Auto-Research-Refine, 128 stars), Read GitHub (AgentTeam-TaichuAI/ScienceClaw, 671 stars), Proof Run Orchestrator (wanshuiyin/Auto-claude-code-research-in-sleep, 17k stars) and Firstdata (MLT-OSS/FirstData, 183 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Recent Conjecture Evaluations?
morluto (a GitHub user) maintains it in morluto/jacobian, which has 211 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on October 5, 2026.
Source: morluto/jacobian on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.