agentsclimarketplace

Ylf project instructions

Skill yaolifeng0629/ylf-agent-skills/skills/ylf-project-instructions

YLF agent skills for disciplined coding tasks and persistent project instructions

Install
npx -y skills add yaolifeng0629/ylf-agent-skills --skill ylf-project-instructions

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Create or update a project's AGENTS.md or CLAUDE.md with compact YLF coding standards. Use when the user asks to make their coding discipline persistent in the current project, update project instructions, sync AGENTS/CLAUDE guidance, or generate a short rule set for Codex or Claude Code.

SKILL.md

2.9 KB, 568 tokens by cl100k_base, as published. Nobody here has run it

YLF Project Instructions

Use this to make YLF coding standards persistent in a project. This skill edits instruction files; it does not execute the coding task itself.

Workflow

  1. Confirm the target.

    • If the user names AGENTS.md, update AGENTS.md.
    • If the user names CLAUDE.md, update CLAUDE.md.
    • If the user asks for both, update both.
    • If no target is named, ask which file to update before editing.
    • Completion criterion: the exact target file or files are known.

  2. Read the project.

    • Read existing AGENTS.md, CLAUDE.md, README files, package scripts, test config, and nearby project docs if they exist.
    • Project-specific facts and commands must come from the current project, not from memory.
    • Completion criterion: you know the project's existing instructions, common commands, and whether a YLF section already exists.

  3. Merge, do not overwrite.

    • Preserve existing project rules.
    • Add or update one compact YLF section rather than scattering rules through the file.
    • Avoid duplicating rules already present.
    • Keep the wording tool-appropriate: AGENTS.md for Codex, CLAUDE.md for Claude Code.
    • Completion criterion: project-specific instructions remain intact and the YLF section is short, clear, and non-duplicative.

  4. Include the YLF core.

    • Define done before non-trivial work.
    • Read current project rules and nearby code before editing.
    • Ask only for high-impact ambiguity; proceed on clear low-risk tasks.
    • Make surgical changes and avoid unrelated refactors.
    • Prefer existing dependencies or mature open-source packages over custom implementations.
    • Verify with the closest real check: tests, representative script input, browser flow, live service, or targeted fallback.
    • Do not perform git actions unless explicitly asked.
    • Do not batch-delete files or directories; delete only one explicit file path at a time.
    • Report plainly: what changed, result, verification, and any real blocker.
    • Completion criterion: all core rules are represented once, without long examples or copied essays.

  5. Verify the edit.

    • Read the final file back.
    • Check that no TODO/template text remains.
    • Check that existing project-specific instructions were not removed.
    • Do not run git commands for verification unless the user explicitly requested git.
    • Completion criterion: the target file contains the intended section and can be used as persistent project guidance.

Style

Keep the inserted section compact. Prefer a checklist over long prose. Do not paste the full Andrej-style essay or tool tutorials into project files.

Gives 0 of the 12 instructions most memory context skills give in 568 tokens

Counted across 674 of the 847 authors here whose files we hold, read 2026-08-06

  • inform the user when setup is completein 21 of 674, across 6 files
  • confirm the draft with the user before writingin 21 of 674, across 6 files
  • update the agent skills block in place if it existsin 21 of 674, across 6 files
  • present findings to the userin 20 of 674, across 5 files
  • write the three docs files from seed templatesin 20 of 674, across 5 files
  • ask the user about each decision one at a timein 19 of 674, across 4 files
  • edit CLAUDE.md if it existsin 18 of 674, across 3 files
  • explore current repo statein 18 of 674, across 3 files
  • do not overwrite user edits to surrounding sectionsin 18 of 674, across 3 files
  • back up the original file before overwritingin 16 of 674, across 8 files
  • keep the memory index under 200 linesin 15 of 674
  • Provide actionable steps and verificationin 13 of 674, across 2 files

Said here and by no other author read

  • ask which file to update if none is named
  • read existing project rules and docs before editing
  • derive project facts from the current project not memory
  • add one compact YLF section
  • tailor wording to the target tool
  • represent all YLF core rules once

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.