Repository
frenzymath/Danus agent skills
- skills
- 16
- GitHub stars
- 476
GitHub description: “Orchestrating Mathematical Reasoning Agents with Fact-Graph Memory”
- Stars
- 476 (70 forks)
- Licence
- Apache-2.0
- Last push
- Aug 2026
- Created
- Jul 2026
- agents
- ai4math
- automated-reasoning
- claude-code
- codex
- llm
- mathematics
- multi-agent
Install all skills
npx skills add frenzymath/DanusAdd --skill <name> for a single skill and -a <agent> to choose the agent (see the agent guides).
Skills in frenzymath/Danus, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Validate externally referenced theorems by querying arXiv theorem search first and Codex's built-in web search second. | frenzymath/ | 476 | — | ~852 | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 2 | Construct candidate counterexamples to test a proposed conjecture, lemma, or intermediate claim by keeping the assumptions true while making the claimed conclusion fail. | frenzymath/ | 476 | — | ~790 | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 3 | Generate and analyze simpler examples that satisfy both the assumptions and the conclusion of a theorem statement or subgoal. | frenzymath/ | 476 | — | ~541 | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 4 | Screen a decomposition plan by first trying to prove all of its subgoals directly, then identifying the key stuck points if the plan does not fully go through. | frenzymath/ | 476 | — | ~1.3k | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 5 | Synthesize the common stuck points across failed decomposition plans. | frenzymath/ | 476 | — | ~586 | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 6 | Derive immediate mathematical consequences from a theorem statement or subgoal. | frenzymath/ | 476 | — | ~587 | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 7 | Propose multiple subgoal decomposition plans for the current theorem using the information already gathered. | frenzymath/ | 476 | — | ~580 | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 8 | Find program-conditioned math results, constructions, examples, counterexamples, analogies, and background references. | frenzymath/ | 476 | — | ~3k | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 9 | Verify a markdown proof in the order it is written. An agent skill from frenzymath/Danus. | frenzymath/ | 476 | — | ~798 | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 10 | 10.Write Paper Turn a project's verified fact graph into a publishable LaTeX paper in a configurable house style — a standalone amsart .tex with a real bibliography, compiled to PDF. | frenzymath/ | 476 | — | ~18k | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 11 | Write a human-readable mathematical progress report (compiled PDF) on a project for the operator / the mathematician who posed the problem. | frenzymath/ | 476 | — | ~1.7k | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 12 | 12.Initialize First-run setup interview for a Danus deployment. An agent skill from frenzymath/Danus. | frenzymath/ | 476 | — | ~1.4k | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 13 | 13.Query Memory Recall what is already known — your own prior reasoning, the swarm's shared findings (including dead ends and verifier feedback), and the verified facts — before doing new work. | frenzymath/ | 476 | — | ~784 | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 14 | Aggregate all detected errors and gaps into the final verification report, apply strict accept/reject logic, and produce repair hints when rejected. | frenzymath/ | 476 | — | ~634 | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 15 | 15.Verify Proof Verify a result and, on acceptance, write it as a fact — via the factsubmit tool. | frenzymath/ | 476 | — | ~1.4k | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 16 | 16.Elaboration Write a high-signal mathematical synthesis from global memory and the fact graph for the Codex main agent's own strategy and worker dispatch. | frenzymath/ | 476 | — | ~3.7k | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
Questions, answered from the data.
What is the best skill in frenzymath/Danus?
Check Referenced Statements from frenzymath/Danus ranks first of the 16 skills in frenzymath/Danus listed here, with the highest score: its repository has 476 GitHub stars, its SKILL.md loads about 852 tokens and it passes the automated safety check with no findings. Next come Construct Counterexamples and Construct Toy Examples.
Are the skills in frenzymath/Danus official?
None yet. All 16 skills in frenzymath/Danus listed here come from community repositories; a skill counts as official when the product's own GitHub organization publishes it.
How do I install all skills from frenzymath/Danus?
Run npx skills add frenzymath/Danus in your project: the open-source skills CLI installs the repository's skills into your coding agent's skills folder. To install a single skill, open its page here for the exact command.
How are these skills ranked?
By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.