Przejdź do treści
Biblioteka skilli
Programowanie · Pisanie

agents-md

/agents-md

Tworzy i utrzymuje AGENTS.md dla prostych projektów i monorepo: deterministyczne wykrywanie, instrukcje o ograniczonym zakresie i nawigacja o niskim zużyciu tokenów.

Repozytorium
tekhne ↗
Licencja
MIT
Ostatnia zmiana repozytorium
21.10.2026

Ocena i bezpieczeństwo

100/ 100Klasa: dobry
Format25 / 25
Frontmatter z nazwą i opisem, poprawna nazwa, opis do 1024 znaków, nazwa zgodna z folderem.
Odkrywalność25 / 25
Opis mówi, kiedy użyć skilla, ma sensowną długość i jest w 3. osobie.
Treść35 / 35
Co najmniej 150 słów i do 500 linii, nagłówki, listy kroków, przykłady albo kod.
Higiena15 / 15
Bez zaślepek typu TODO, bez ścieżek Windows, z licencją.
Ryzykobrak sygnałów w skanie
Pliki w paczce
50
Skrypty
0
Komentarze HTML
0
Adresy URL w SKILL.md
0
Przestarzałość

Brak sygnałów. Repozytorium zmienione 21.10.2026, bez odwołań do wycofanych modeli i API.

Licencja

MIT, otwarta: można używać i zmieniać, z zachowaniem informacji o autorze.

Co robi i kiedy

Tworzy i utrzymuje AGENTS.md dla prostych projektów i monorepo: deterministyczne wykrywanie, instrukcje o ograniczonym zakresie i nawigacja o niskim zużyciu tokenów.

Oryginalny opis (EN)

Create and maintain AGENTS.md documentation for simple projects, complex monorepos, deterministic discovery, scoped instruction files, low-token navigation; use when generating AGENTS.md, updating agent docs, standardizing AI-facing project guidance.

Jak działa

  1. When to Use
  2. When Not to Use
  3. Principles
  4. Workflow
  5. Structure Decision
  6. Minimal Template
  7. Quick Commands
  8. Anti-Patterns
  9. Verification
  10. References
Sekcje z nagłówków SKILL.md, w oryginale · 172 linii, 690 słów
Podgląd SKILL.md
---
name: agents-md
description: Create and maintain AGENTS.md documentation for simple projects, complex monorepos, deterministic discovery, scoped instruction files, low-token navigation; use when generating AGENTS.md, updating agent docs, standardizing AI-facing project guidance.
---

# AGENTS.md Management

## When to Use

- "Create AGENTS.md for this repo."
- "Update agent documentation for this monorepo."
- "Set up hierarchical AGENTS.md files by package."
- Repository shape or tooling changed and the existing agent guidance needs a refresh.

## When Not to Use

- Pure code implementation work with no documentation update.
- One-off prompts where repository guidance files are unnecessary.
- Questions about a single function or file that need no standing project guidance.

## Principles

- Keep instructions concise, concrete, and path-specific.
- Prefer references and indices over duplicated prose.
- Optimize for nearest-file relevance in hierarchical layouts.

## Workflow

1. Discover repository shape and technologies.
Output: simple vs hierarchical documentation strategy.
2. Select structure (single root file or root + sub-files).
Output: file layout plan.
3. Generate AGENTS.md content with concrete commands and paths.
Output: actionable docs with JIT indexing.
4. Validate command correctness and duplication boundaries.
Output: clean, copy-paste-safe instruction files.
5. Re-check after major repo changes.
Output: synchronized documentation.

## Structure Decision

- Simple project: one AGENTS.md when stack and patterns are uniform.
- Complex monorepo: root AGENTS.md + scoped subdirectory AGENTS.md files.
- Consider adding subdirectory files iteratively — start minimal, expand as complexity grows.

## Minimal Template

```markdown
# Project Agent Guide

## Commands
- Build: `bun run build`
- Test: `bun run test`
- Lint: `bun run lint`

## Conventions
- [describe key patterns here]

## Key Paths
- Source: `src/`
- Tests: colocated `*.test.ts`
```

## Quick Commands

```bash
# Discovery baseline
rg --files
```

```bash
# Detect core config/tooling
rg -n "workspaces|nx|turbo|pnpm|yarn|packageManager|tsconfig|pytest|playwright" .
```

```bash
# Locate existing AGENTS files
find . -name AGENTS.md -o -name AI-DOCS.md
```

## Anti-Patterns

### NEVER assume a technology stack without discovery

**WHY:** incorrect assumptions produce unusable instructions.

**BAD:** generate React/Jest guidance without evidence.

**GOOD:** run discovery commands and map docs to the detected stack.

### NEVER dump encyclopedic content into root AGENTS.md

**WHY:** oversized docs increase token cost and reduce usability.

**BAD:** embed full framework manuals.

**GOOD:** keep root concise and link to scoped files or references.

### NEVER duplicate the same instructions across root and sub-files

**WHY:** duplication creates drift and maintenance overhead.

**BAD:** copy/paste identical conventions in every file.

**GOOD:** keep universal rules at root and package-specific rules locally.

### NEVER provide unverified commands

**WHY:** broken commands erode trust and block contributors.

**BAD:** include hypothetical commands.

**GOOD:** include only validated copy-paste commands.

### NEVER create a hierarchy for a simple, uniform project

**WHY:** extra files add navigation cost and drift risk when one file would do.

**BAD:** add a subdirectory AGENTS.md to every folder of a single-package repo.

**GOOD:** use one root AGENTS.md when stack and patterns are uniform.

### NEVER put package-specific rules in the root file

**WHY:** agents read the nearest file, so misplaced rules waste tokens and mislead other packages.

**BAD:** list UI build flags in the root file of a monorepo.

**GOOD:** keep package commands in that package's own AGENTS.md.

### NEVER use generic placeholder commands or paths

**WHY:** placeholders cannot be copy-pasted and give the reader nothing concrete.

**BAD:** write `<your-project>/src` or "run the tests".

**GOOD:** write the real path and the real command found during discovery.

### NEVER front-load every sub-file at once

**WHY:** speculative files describe complexity that does not exist yet and go stale.

**BAD:** generate an AGENTS.md for every package on the first pass.

**GOOD:** start minimal and add scoped files iteratively as complexity grows.

### NEVER leave documentation stale after major repository changes

**WHY:** instructions for removed tooling mislead agents and break their commands.

**BAD:** keep Jest commands after the project moved to another runner.

**GOOD:** re-run discovery, remove obsolete content, and document new scripts.

## Verification

```bash
rumdl check --include "**/AGENTS.md" .
```

```bash
bun run lint
```

## References

| Topic | Reference |
| --- | --- |
| Repository discovery commands | [references/discovery-commands.md](references/discovery-commands.md) |
| What to avoid | [references/anti-patterns.md](references/anti-patterns.md) |
| API package template | [references/api-template.md](references/api-template.md) |
| Design-system template | [references/design-system-template.md](references/design-system-template.md) |
| Database package template | [references/database-template.md](references/database-template.md) |
| Testing package template | [references/testing-template.md](references/testing-template.md) |
| Troubleshooting | [references/troubleshooting.md](references/troubleshooting.md) |
Pliki w paczce (50)
  • CHANGELOG.md 1 KB
  • SKILL.md 5 KB
  • .audits/latest 1 KB
  • .audits/2026-02-21/analysis.md 8 KB
  • .audits/2026-02-21/audit.json 1 KB
  • .audits/2026-02-21/remediation-plan.md 1 KB
  • .audits/2026-02-22/analysis.md 8 KB
  • .audits/2026-02-22/audit.json 1 KB
  • .audits/2026-02-22/remediation-plan.md 1 KB
  • .audits/2026-02-23/analysis.md 8 KB
  • .audits/2026-02-23/audit.json 1 KB
  • .audits/2026-02-23/remediation-plan.md 1 KB
  • .audits/2026-03-02/analysis.md 1 KB
  • .audits/2026-03-02/audit.json 1 KB
  • .audits/2026-03-18/analysis.md 1 KB
  • .audits/2026-03-18/audit.json 1 KB
  • .audits/2026-03-18/remediation-plan.md 2 KB
  • .audits/2026-04-08/analysis.md 1 KB
  • .audits/2026-04-08/audit.json 1 KB
  • .audits/2026-04-27/Analysis.md 1 KB
  • .audits/2026-04-27/Remediation.md 1 KB
  • .audits/2026-04-27/audit.json 1 KB
  • .audits/2026-10-02/Analysis.md 1 KB
  • .audits/2026-10-02/Remediation.md 1 KB
  • .audits/2026-10-02/audit.json 1 KB
  • .tekhne/plugin.json 1 KB
  • evals/instructions.json 4 KB
  • evals/summary.json 1 KB
  • evals/scenario-1/capability.txt 1 KB
  • evals/scenario-1/criteria.json 3 KB
  • evals/scenario-1/task.md 1 KB
  • evals/scenario-2/capability.txt 1 KB
  • evals/scenario-2/criteria.json 3 KB
  • evals/scenario-2/task.md 1 KB
  • evals/scenario-3/capability.txt 1 KB
  • evals/scenario-3/criteria.json 3 KB
  • evals/scenario-3/task.md 1 KB
  • evals/scenario-4/capability.txt 1 KB
  • evals/scenario-4/criteria.json 2 KB
  • evals/scenario-4/task.md 1 KB
  • evals/scenario-5/capability.txt 1 KB
  • evals/scenario-5/criteria.json 3 KB
  • evals/scenario-5/task.md 1 KB
  • references/anti-patterns.md 4 KB
  • references/api-template.md 3 KB
  • references/database-template.md 3 KB
  • references/design-system-template.md 3 KB
  • references/discovery-commands.md 6 KB
  • references/testing-template.md 3 KB
  • references/troubleshooting.md 4 KB

Wersje

RepozytoriumWynikLicencja
Ta strona · pantheon-org/tekhne100MIT
mblode/agent-skills100MIT
akunzai/agent-skills100MIT
hugrverk/riggverk100MIT
getsentry/skills100Apache-2.0
mc0571/mc-skills100MIT
jscraik/Agent-Skills100Apache-2.0
LiHongwei-cn/lihongwei-cn100MIT
caidanw/skills100MIT

Migawka bazy z 13.11.2026 · wersja paczki 6ebed11d93d5 (skrót SHA-256 całej paczki)

Pobrania w ostatnich 30 dniach: 0 · ranking

Zgłoś problem z tym skillem: szkodliwa treść, błędny opis albo prośba autora o usunięcie.

Podobne skille

  • 95instructions-method
    Przygotowuje instrukcje dla agentów kodujących w AGENTS.md lub CLAUDE.md, z kontrolą jakości każdej reguły.
  • 95instructions-method
    Tworzy trwałe instrukcje projektu w plikach AGENTS.md lub CLAUDE.md według przyjętej metody.
  • 100create-agents-md
    Tworzy plik AGENTS.md lub CLAUDE.md z konwencjami projektu, aby agenci kodujący znali zasady pracy w repozytorium.
  • 100agents-md-authoring
    Tworzy i utrzymuje pliki AGENTS.md uruchamiające kontekst agentów AI: standard agents.md, blok instrukcji ładowania kontekstu i mostek CLAUDE.md dla Claude Code.
  • 100rc
    Tworzy, zmienia i optymalizuje reguły, instrukcje AGENTS.md i skille dla agentów AI.
  • 100nx
    Obsługuje system budowania i narzędzia monorepo Nx: orkiestrację zadań, generatory, wtyczki, polecenia affected i granice modułów w dużych monorepo wielotechnologicznych.

Uwagi i zgłoszenia

Wiadomość trafi do Bartosza Sokolińskiego. Adres e-mail jest potrzebny tylko do odpowiedzi. Szczegóły w polityce prywatności.