Repository navigation
Description
I highly appreciate that skills is becoming a standard that we can use across many different agent harnesses.
To make it even smoother, I believe that agreeing on a standard name for the agent skills folder would benefit everyone. This would allow different harnesses to have a default folder to find skills without requiring each project to put them in a different folder and create symlinks that match the specific folder of each harness.
Example: Claude is looking at .claude/skills/ and Github Copilot is looking at .github/skills/.
Edit: now we have Codex also looking at its own folder .codex/skills/
My suggestion for the name would be .agents/skills/, but I don't really care much about the name as long as it's agreed upon and standardized. It could even be just .skills/.
Adoption
Please help to keep the lists below up to date. 😄
Ready
- Amp: https://ampcode.com/manual#agent-skills
- Augment Code (Auggie): https://docs.augmentcode.com/cli/skills#skill-file-structure
- Goose: https://block.github.io/goose/docs/guides/context-engineering/using-skills/#skill-locations
- Codex: feat: Support loading skills from .agents/skills openai/codex#10317 and feat: Read personal skills from .agents/skills openai/codex#10437
- VS Code: Add support for .agents for skills resolution microsoft/vscode#292414
- VTCode: Deprecating and migrate .vtcode/skils to .agents/skills vinhnx/VTCode#600
- Pi: add support for reading skills from .agent/skills earendil-works/pi#1211 (configurable)
- Mistral Vibe: https://github.com/mistralai/mistral-vibe/blob/ec7f3b25eaf47c447f4005561ae2ff32545d3dff/CHANGELOG.md?plain=1#L14
- OpenCode: feat: add support for reading skills from .agents/skills directories anomalyco/opencode#11842
- OpenClaw: feat: support .agents/skills/ directory for cross-agent skill discovery openclaw/openclaw#9966
- Gemini CLI: feat(core): add .agents/skills directory alias for skill discovery google-gemini/gemini-cli#18151
- Craft Agents: Support .agents/skills convention craft-ai-agents/craft-agents-oss#171
- RooCode: [ENHANCEMENT] Support .agents/skills folder RooCodeInc/Roo-Code#11368 (implemented and released but not documented yet)
- Cursor: https://x.com/leerob/status/2024141055143383184 (released)
- Windsurf: released on version 1.9552.21 (2026-02-12)
- Google Antigravity: https://antigravity.google/docs/skills
- Gwen Code: implemented on feat: add support for reading skills from
.agents/skillsQwenLM/qwen-code#2155
Pending
- Claude Code: [Feature Request] Support the standard .agents/skills/ directory for agent skills anthropics/claude-code#16345
- KiloCode: Support .agents/skills folder Kilo-Org/kilocode#5783
- Github: Proposal: include a standard folder where agent skills should be #15 (comment) (tracking work internally, will give an update when done)
Not adopting yet
There are too many tools to list here. Anyone not mention in "ready" or "pending" is considered not adopting yet.
Activity
edu-ap commentedon Dec 19, 2025
Love the idea of converging on a standard skills folder so we can avoid every harness inventing its own layout.
One tweak I’d suggest is using
.llm/skills/(or.llm/) rather than.agent/skills/.Other ecosystems tend to name these shared hidden directories after the core runtime/capability, e.g. Python tools agree on
.venvfor virtual environments, VS Code uses.vscode/for project‑local editor and extension settings, and .NET uses.dotnet/(plus.config) for CLI tools and manifests.In the LLM world, the common denominator across frameworks is the LLM itself, while “agent” is an architectural pattern that differs a lot (and sometimes isn’t used at all). A neutral
.llm/namespace would work for:.llm/skills/),.llm/config/), andand would still make sense in projects that use LLMs directly without an “agent” concept.
Concretely: if tools like Claude, Copilot, and others agree to look in
.llm/skills/by default (while maybe still supporting their legacy.claude/skills/,.github/skills/, etc.), we’d get a cross‑tool convention that matches how other ecosystems have handled this problem.[-]Proposal: include a standard folder where agent skill will be[/-][+]Proposal: include a standard folder where agent skills should be[/+]Aranmobinarann commentedon Dec 19, 2025
Don't be really tired.
numman-ali commentedon Dec 19, 2025
it should be .agents, it aligns with AGENTS .md - and distribution is better than semantics
Without adoption we don't have much movement
douglascamata commentedon Dec 19, 2025
To have adoption, there must be an agreement, like eventually everyone agreed on AGENTS.md but at first used separate files.
BTW, Codex just launched skills support on
.codex/skills. 🤣So three symlinks already. Now we only miss Google out of the big providers.
jameskanyiri commentedon Dec 20, 2025
I agree that we should converge on a single standard, and I’d advocate for using
.agent/skills/These skills are specifically meant for agents, not just generic LLM usage, so tying the convention to the agent construct feels clearer and more intentional. Similar to how AGENTS.md became a focal convention, a dedicated agent/ namespace keeps the ecosystem conceptually aligned, avoids over-generalizing into the broader “LLM” space, and helps reinforce that this directory represents agent-oriented capabilities rather than model configuration or runtime metadata.
TabishB commentedon Dec 20, 2025
+1 This is a super important aspect of the standard. The last thing we need is every coding agent provider having a different directory location that we need to either copy over or create symlinks for.
Setting a standard on a common directory name is crucial.
skillcreatorai commentedon Dec 20, 2025
While the path standardization debate continues, there's a practical alternative: tooling that abstracts the paths.
For example, ai-agent-skills lets you install with one command:
Users don't need to know where skills go. The CLI handles the mapping internally.
This doesn't require any agent to change their paths - just a layer that knows the current mapping. Not saying this replaces standardization, but it solves the user pain point today while the discussion continues.
airtonix commentedon Dec 30, 2025
or just use symlinks.
I use comtrya to manage my dotfiles and i just have all this symlinked to the different directories.
this thread just feels like a huge bike shed tbh.
Dyrits commentedon Dec 31, 2025
That's a big issue. There should be a standard to provide context to the agents.
The ecosystem has standardized the technical layers (tools, communication) but not the semantic layers (instructions, context). That's a problem.
airtonix commentedon Jan 2, 2026
So what happens when people need to source skills from more than one place?
xxchan commentedon Jan 4, 2026
I think the key here is lifecycle: agent skills are meant to be created and iterated constantly (often by the agent itself). Without a shared, standard folder, this becomes fragmented across harnesses and quickly turns into sync chaos. A canonical repo path (name doesn’t matter much) would make skills a first-class, continuously evolving asset rather than per-harness copies.
Codex doesn't event support symlinks btw
verdie-g commentedon Jan 7, 2026
@ericharmeling @klazuka could you share what are you thoughts about this? 🙏
mderazon commentedon Jan 8, 2026
I agree, this is frustrating. It creates a vendor lock-in for specific agent that is more of a nuisance than lock-in because it can be hacked to be circumvented by symlinks / copying the skills folder across
.gemini/.claude/.githubfolders.Same for agent instructions, this whole thing is a mess
mderazon commentedon Jan 8, 2026
This copies (duplicates) the skills across folders, to me that's horrible
124 remaining items
Aesthermortis commentedon Jun 17, 2026
Codex reads universal paths, and you can also set a path outside of the supported ones, and through load map in agents.md the AI loads the content indicated in the path you have set.
feat: Support loading skills from .agents/skills (#10317)
feat: Read personal skills from .agents/skills (#10437)
lancy69 commentedon Aug 13, 2026
People have mentioned using
$XDG_CONFIG_HOME/agents/skills. But it might be better to use$XDG_DATA_HOME/agents/skillsIMHO, for some skills contain large, less edit-friendly resources.tmccombs commentedon Aug 15, 2026
Or both?
lancy69 commentedon Aug 20, 2026
Both would also be great! 👍 This way the existing workflows will not break while those who prefer XDG can get what they want.
karlhorky commentedon Aug 26, 2026
@douglascamata would you also be open to keeping your original issue description updated to track documentation / implementation PRs in the popular
skillsCLI?For example, I noticed just today that the
skillsCLI implementation and documentation is outdated for Codex (~/.codex/skills/instead of~/.agents/skills/):So that would mean that if you used
npx skills ...commands, they are currently installed in the~/.codex/skills/folder for Codex.Only a few "universal agents" have been implemented and documented so far (Cline, Dexto, Kimi Code CLI, Loaf, Warp, Zed):
I did a PR just now for updating the implementation and documentation for using
~/.agents/skills/for Codex:~/.agents/skillsfor Codex global skills vercel-labs/skills#2067Another similar older (merged) PR for Cline:
Aesthermortis commentedon Aug 26, 2026
I cancelled Claude's PRO account because it's terrible. It doesn't read the instructions in the specified paths, and everything is opaque; you can't tell if it's doing anything or not. Codex, on the other hand, displays the commands, reads the files in any path you specify, and follows the rules precisely. It also shows you exactly when each skill is used.
yordis commentedon Aug 27, 2026
@Aesthermortis I think that is an skills issue, good to know. Thanks for sharing here, very insightful!
douglascamata commentedon Aug 28, 2026
@karlhorky unfortunately I can't keep up with updating this issue anymore and tracking here behavior of an external tool, in this case owned by Vercel and not affiliated in any way with this organization, doesn't make sense, imho.
Dakta commentedon Sep 8, 2026
Previous discussion in the
AGENTS.mdrepo got sidetracked badly by debating Claude's Rules feature. Other past efforts at standardizing this have all succumbed to similar scope-creep. Therefore I propose some guidelines to begin an open standard for consolidated project configuration in.agents/without being bogged down inventing other standards: agentsmd/agents.md#71 (comment)Let's pick the existing standards:
AGENTS.md, Agent Skills, and the de-factomcp.jsonstandard, and use them as the basis:As new standards arise for things like Rules, Tasks, Personas, Memory, or (in my view the most pressing) Sub-Agents, their configurations can be incorporated by reference. But we don't need to wait for any of those things to get started.
Pjrich1313 commentedon Sep 8, 2026
Add to build
Aesthermortis commentedon Sep 9, 2026
The solution would be to isolate Claude while everyone follows fairer and less selfish standards.
Pjrich1313 commentedon Sep 9, 2026
I use both Claude and Grok
Pjrich1313 commentedon Sep 10, 2026