sparring
Skill0 starsChanged 2 months agoMITView on GitHub
Teach an engineer to defend an agent-built repository through a verified survey, a catalogue-backed lesson, and one-question-at-a-time drills.
6 other projects use a version of this.
Adopted by
Most recently taken up by
- nyxandro/sparring-skilltheir own version, first seen Nov 5, 2026
- JeremyHo1123/claude-codex-sparringtheir own version, first seen Oct 8, 2026
- marcogalluccio/company-brain-ostheir own version, first seen Sep 28, 2026
- MbappeWU/murder-boardtheir own version, first seen Sep 25, 2026
- gavishap/omnia-vaulttheir own version, first seen Aug 28, 2026
- gyujeongion/claude-code-sparringtheir own version, first seen Jul 1, 2026
Other versions6 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 6
- gavishap/omnia-vault★ 53same name
- MbappeWU/murder-board★ 15same name
- marcogalluccio/company-brain-os★ 7same name
- nyxandro/sparring-skill★ 3same name
- JeremyHo1123/claude-codex-sparring★ 1same name
- gyujeongion/claude-code-sparring★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository4 other files it gives its agents.
- skill/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- opus-as-fableSkill
- sparringSkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.
0
Common
Most of the 6 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Use this skill when the user asks for a repository survey, project map, lesson, drill, mock interview, or grade review.
“Common” is measured: kept by at least 6 in 10 of the 6 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Sparring
Use this skill when the user asks for a repository survey, project map, lesson, drill, mock interview, or grade review. Make the learner retrieve and defend the code instead of outsourcing the explanation to the agent. Evidence: docs/research/2026-09-10-learning-science.md, findings 1, 8, and 9.
Select a mode
| User request | Mode | Read next |
| Survey a repository, make a project map, or start a project | survey | references/survey.md |
| Teach a project, topic, or drill gap | lesson | references/lesson.md |
| Drill, quiz, test, or run spaced review | drill | references/drill.md |
Load references/interviewer-rules.md for every mode. Load references/components.md before authoring a lesson. Load only the references required by the selected mode.
Working contract
- Build a verified repository map before writing a deep lesson. Keep coverage boundaries visible and preserve claim provenance. Evidence:
docs/research/2026-09-12-large-repository-survey.md, findings 1, 9, 10, and 11. - Assemble lessons from the closed component catalogue. Supply field content; let the application own layout, interaction, and grading. Evidence:
docs/2026-09-12-sparring-as-software-design.md, sections 3.1 and 4;docs/research/2026-09-10-learning-science.md, findings 5, 6, and 9. - Make the learner commit an answer before revealing a rubric or grounding. Ask one question at a time and record every attempt. Evidence:
docs/research/2026-09-10-learning-science.md, findings 1, 8, 9, and 11.
The connected server owns the due queue, rubrics, records, contests, projects, topics, cards, lessons, and survey submissions. The reference files name the server tools and their order.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.