Skip to content

Commit 2003dca

Browse files
chore(agents): migrate .agent to .agents directory (#10489) (#10491)
Co-authored-by: tobiu <tobiasuhlig78@gmail.com>
1 parent 7e1bbc0 commit 2003dca

82 files changed

Lines changed: 85 additions & 101 deletions

File tree

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.
File renamed without changes.

.agents/skills/create-skill

Lines changed: 0 additions & 1 deletion
This file was deleted.
Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -4,4 +4,4 @@ description: Authoritative guide on how to architect, format, and structure new
44
triggers: Use this skill if the user asks you to create a new skill, teach an agent a new capability, or if you need to recall the exact folder structure and YAML frontmatter required for skills.
55
---
66
# Skill Creation Framework
7-
If you are tasked with creating a new Agent Skill, you MUST immediately use the `view_file` tool to read and strictly adhere to `.agent/skills/create-skill/references/skill-authoring-guide.md` before creating any files. This prevents system prompt bloat and ensures future agents can parse your skill correctly.
7+
If you are tasked with creating a new Agent Skill, you MUST immediately use the `view_file` tool to read and strictly adhere to `.agents/skills/create-skill/references/skill-authoring-guide.md` before creating any files. This prevents system prompt bloat and ensures future agents can parse your skill correctly.

.agent/skills/create-skill/references/skill-authoring-guide.md renamed to .agents/skills/create-skill/references/skill-authoring-guide.md

Lines changed: 6 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -14,7 +14,7 @@ You must **NEVER** write the entire instruction manual of a skill directly into
1414
Whenever you create a new skill named `my-new-skill`, you must scaffold the following standard directory structure:
1515

1616
```text
17-
.agent/skills/my-new-skill/
17+
.agents/skills/my-new-skill/
1818
├── SKILL.md # Required - Main lightweight router with YAML frontmatter
1919
├── references/ # Required - Documentation and heavy payload markdown files
2020
│ └── [descriptive-payload-name].md
@@ -43,9 +43,9 @@ Below the YAML block, the Markdown body MUST be a concise directive instructing
4343

4444
```markdown
4545
# [Skill Title]
46-
If you need to [do this task], you MUST immediately use the `view_file` tool to read and strictly adhere to `.agent/skills/[skill-name]/references/[descriptive-payload-name].md` before proceeding.
46+
If you need to [do this task], you MUST immediately use the `view_file` tool to read and strictly adhere to `.agents/skills/[skill-name]/references/[descriptive-payload-name].md` before proceeding.
4747
```
48-
*(Always use a relative path like `.agent/skills/...` for the `view_file` tool parameter).*
48+
*(Always use a relative path like `.agents/skills/...` for the `view_file` tool parameter).*
4949

5050
## 2. Writing the Payload (references/*.md)
5151

@@ -70,13 +70,13 @@ When a swarm agent discovers a systemic trap, an architectural pattern, or a wor
7070

7171
## 4. The Claude Symlink Mandate
7272

73-
The Neo.mjs agent swarm operates across multiple identities (e.g., Antigravity and Claude Code). While `.agent/skills/` is the canonical repository of skills, Claude Code relies on a dedicated `.claude/skills/` directory to parse its available tools at boot.
73+
The Neo.mjs agent swarm operates across multiple identities (e.g., Antigravity and Claude Code). While `.agents/skills/` is the canonical repository of skills, Claude Code relies on a dedicated `.claude/skills/` directory to parse its available tools at boot.
7474

75-
**CRITICAL:** Whenever you create a *new* skill folder in `.agent/skills/`, you **MUST** immediately create a corresponding symlink in the `.claude/skills/` directory.
75+
**CRITICAL:** Whenever you create a *new* skill folder in `.agents/skills/`, you **MUST** immediately create a corresponding symlink in the `.claude/skills/` directory.
7676

7777
```bash
7878
# Run from repository root:
79-
ln -sf ../../.agent/skills/my-new-skill .claude/skills/my-new-skill
79+
ln -sf ../../.agents/skills/my-new-skill .claude/skills/my-new-skill
8080
```
8181

8282
Failure to create this symlink will result in Claude being entirely blind to the new protocol, causing severe swarm capability desyncs.

.agent/skills/debugging-antigravity/SKILL.md renamed to .agents/skills/debugging-antigravity/SKILL.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -4,4 +4,4 @@ description: Authoritative guide on debugging Antigravity IDE MCP servers, preve
44
triggers: Use this skill if the user's Antigravity MCP server panel has a perpetual loading spinner, if MCP processes are duplicating, if sqlite workspace states are corrupted (`__store` null error), or if you need to know how to properly scope `.gemini/settings.json` vs global configurations.
55
---
66
# Antigravity Debugging Guide
7-
If you need to debug Antigravity IDE issues, MCP server duplication, database initialization race conditions, or fix workspace UI crashes (loading spinners), you MUST immediately use the `view_file` tool to read and strictly adhere to `.agent/skills/debugging-antigravity/references/debugging-guide.md` before proceeding.
7+
If you need to debug Antigravity IDE issues, MCP server duplication, database initialization race conditions, or fix workspace UI crashes (loading spinners), you MUST immediately use the `view_file` tool to read and strictly adhere to `.agents/skills/debugging-antigravity/references/debugging-guide.md` before proceeding.

.agent/skills/debugging-antigravity/references/debugging-guide.md renamed to .agents/skills/debugging-antigravity/references/debugging-guide.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -77,7 +77,7 @@ Find and destroy orphaned workspace hashes so the IDE does not re-register them
7777
find "$HOME/Library/Application Support/Antigravity/User/workspaceStorage" -name "workspace.json" 2>/dev/null
7878

7979
# Typically, you delete the folders containing stale mapping values like:
80-
# {"folder": "file://.agent/skills/ticket-intake"}
80+
# {"folder": "file://.agents/skills/ticket-intake"}
8181
```
8282

8383
After performing these purges, closing and restarting the IDE forces the UI to cleanly rebuild the workspace payload based only on the actively opened directory.

.agents/skills/epic-review

Lines changed: 0 additions & 1 deletion
This file was deleted.
Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -5,6 +5,6 @@ triggers: Use this skill when an agent is about to pick up its first sub from an
55
---
66
# Epic Review Skill
77

8-
If you are about to pick up your first sub-issue from an epic that your model-identity has not yet reviewed, you MUST immediately use the `view_file` tool to read and strictly adhere to `.agent/skills/epic-review/references/epic-review-workflow.md` before running `ticket-intake` or any sub-work steps.
8+
If you are about to pick up your first sub-issue from an epic that your model-identity has not yet reviewed, you MUST immediately use the `view_file` tool to read and strictly adhere to `.agents/skills/epic-review/references/epic-review-workflow.md` before running `ticket-intake` or any sub-work steps.
99

1010
Subsequent sub pickups from the same epic by the same model-identity cite the prior review by URL reference instead of re-running the skill.

.agent/skills/epic-review/assets/epic-review-comment-template.md renamed to .agents/skills/epic-review/assets/epic-review-comment-template.md

File renamed without changes.

.agent/skills/epic-review/references/epic-review-workflow.md renamed to .agents/skills/epic-review/references/epic-review-workflow.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -105,7 +105,7 @@ Missing traps are an **extension opportunity**, not a blocker — flag them in t
105105

106106
## 4. Comment Output Format
107107

108-
Post the review as a comment on the epic ticket using `manage_issue_comment` with action `create`. Use the template at `.agent/skills/epic-review/assets/epic-review-comment-template.md` as the structural skeleton.
108+
Post the review as a comment on the epic ticket using `manage_issue_comment` with action `create`. Use the template at `.agents/skills/epic-review/assets/epic-review-comment-template.md` as the structural skeleton.
109109

110110
**Short form** (stage 1 or 2 failure):
111111
- Header: `Epic Review — Stage [1|2] Challenge by [model-identity]`

0 commit comments

Comments
 (0)