Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use when you need to generate an AGENTS.md file for a Java repository — covering project conventions, tech stack, file structure, commands, Git workflow, and contributor boundaries — through a modular, step-based interactive process that adapts to your specific project needs. This should trigger for requests such as Create AGENTS.md; Update AGENTS.md file; Add agent instructions; Generate contributor instructions for Java agents; Document repository conventions in AGENTS.md. Part of Plinth Toolk
.claude/skills/jabrena-200-agents-md/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -41% | 0% |
| case-08 | ✗→✓ | ▲ Improved | 229% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 11% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 33% | 0% |
| case-24 | ✗→✓ | ▲ Improved | -20% | 0% |
Generate a comprehensive AGENTS.md file for Java repositories through a modular, step-based interactive process that covers role definition, tech stack, file structure, commands, Git workflow, and contributor boundaries. This is an interactive SKILL.
What is covered in this Skill?
No Maven validation is required before generating AGENTS.md. Review the project structure and existing documentation before starting to provide accurate answers during Step 1.
Inspect project structure and existing documentation to prepare accurate responses for the AGENTS.md discovery phase.
Read references/200-agents-md.md and follow its generation patterns and safeguards.
Gather role, tech stack, commands, workflow, and boundaries in a modular step-based conversation.
Create AGENTS.md with ✅ Always do / ⚠ Ask first / 🚫 Never do boundaries and repository-specific conventions.
For detailed guidance, examples, and constraints, see references/200-agents-md.md.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 18,402 | 7,596 | -59% | 1 | 1 | 0% | 2,798 | 1,646 | -41% | 0 | 0 | — |
case-02 | fail→fail | 6,487 | 5,055 | -22% | 1 | 1 | 0% | 1,005 | 846 | -16% | 0 | 0 | — |
case-03 | fail→fail | 20,413 | 2,098 | -90% | 1 | 1 | 0% | 3,121 | 854 | -73% | 0 | 0 | — |
case-04 | pass→pass | 12,113 | 10,511 | -13% | 1 | 1 | 0% | 2,230 | 2,420 | +9% | 0 | 0 | — |
case-05 | pass→pass | 7,262 | 5,458 | -25% | 1 | 1 | 0% | 1,171 | 1,480 | +26% | 0 | 0 | — |
case-06 | pass→pass | 10,890 | 11,224 | +3% | 1 | 1 | 0% | 1,904 | 2,479 | +30% | 0 | 0 | — |
case-23 | pass→pass | 15,536 | 5,910 | -62% | 1 | 1 | 0% | 2,365 | 1,415 | -40% | 0 | 0 | — |
case-07 | pass→fail | 6,392 | 2,196 | -66% | 1 | 1 | 0% | 940 | 798 | -15% | 0 | 0 | — |
case-08 | fail→pass | 5,363 | 3,637 | -32% | 1 | 1 | 0% | 294 | 966 | +229% | 0 | 0 | — |
case-09 | fail→pass | 8,353 | 5,663 | -32% | 1 | 1 | 0% | 1,195 | 1,330 | +11% | 0 | 0 | — |
case-10 | fail→pass | 35,739 | 7,044 | -80% | 1 | 1 | 0% | 1,140 | 1,511 | +33% | 0 | 0 | — |
case-24 | fail→pass | 13,342 | 7,363 | -45% | 1 | 1 | 0% | 2,106 | 1,691 | -20% | 0 | 0 | — |
case-11 | fail→pass | 12,295 | 5,504 | -55% | 1 | 1 | 0% | 1,950 | 1,420 | -27% | 0 | 0 | — |
case-12 | pass→pass | 13,413 | 5,698 | -58% | 1 | 1 | 0% | 2,293 | 1,522 | -34% | 0 | 0 | — |
case-13 | pass→pass | 17,271 | 11,950 | -31% | 1 | 1 | 0% | 2,644 | 2,313 | -13% | 0 | 0 | — |
case-14 | pass→pass | 7,526 | 2,671 | -65% | 1 | 1 | 0% | 1,059 | 869 | -18% | 0 | 0 | — |
case-15 | fail→pass | 11,129 | 3,403 | -69% | 1 | 1 | 0% | 1,629 | 1,031 | -37% | 0 | 0 | — |
case-16 | pass→pass | 15,393 | 4,807 | -69% | 1 | 1 | 0% | 2,252 | 1,231 | -45% | 0 | 0 | — |
case-17 | fail→fail | 14,369 | 14,455 | +1% | 1 | 1 | 0% | 2,438 | 2,991 | +23% | 0 | 0 | — |
case-18 | fail→pass | 9,628 | 1,729 | -82% | 1 | 1 | 0% | 1,391 | 786 | -43% | 0 | 0 | — |
case-19 | pass→pass | 19,545 | 8,786 | -55% | 1 | 1 | 0% | 2,924 | 1,920 | -34% | 0 | 0 | — |
case-20 | pass→pass | 17,319 | 8,362 | -52% | 1 | 1 | 0% | 2,449 | 1,780 | -27% | 0 | 0 | — |
case-21 | pass→pass | 9,993 | 2,247 | -78% | 1 | 1 | 0% | 1,519 | 868 | -43% | 0 | 0 | — |
case-22 | fail→pass | 11,190 | 2,660 | -76% | 1 | 1 | 0% | 1,666 | 1,001 | -40% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 24 cases were attempted, and 21 counted toward the lift figure. The other 3 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +33 percentage points is the difference between those two pass rates over the 21 comparable cases. 3 cases got worse with the skill loaded, and they are included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.