refactor: update skill paths to use .agents/skills/ for consistency and remove obsolete skill references

This commit is contained in:
2026-05-05 16:22:42 -06:00
parent e4b39c4a9e
commit f72a828805
21 changed files with 21 additions and 51 deletions

View File

@@ -19,7 +19,7 @@ The agent must keep the workspace behavior aligned with recurring user correctio
- Update `.opencode/commands/` for slash-command behavior.
- Update `prompts/` for reusable drafting shape.
- Update `.opencode/agents/` and `AGENTS.md` for default agent behavior.
- Update `.opencode/skills/` for specialized workflows.
- Update `.agents/skills/` for specialized workflows.
- Update `agent-memory/` for reusable agent operating rules.
- Update `project-knowledge/` only when the correction changes project knowledge or project-facing process documentation.
@@ -32,4 +32,3 @@ The agent must keep the workspace behavior aligned with recurring user correctio
- Agent implementation chatter.
- Generic preference notes that only affect agent behavior.
- Duplicate summaries of already-correct project facts.

View File

@@ -51,11 +51,11 @@ Commands, prompts, skills, workflows, and automation surfaces that make the work
## Skills
- Shared skills source: `.agents/skills/`
- Skills index: `.opencode/skills/index.md`
- Workspace memory curation: `.opencode/skills/workspace-memory-curation/SKILL.md`
- Professional communication: `.opencode/skills/professional-communication/SKILL.md`
- Status reporting: `.opencode/skills/status-reporting/SKILL.md`
- AI prompt engineering: `.opencode/skills/ai-prompt-engineering/SKILL.md`
- Skills index: `.agents/skills/index.md`
- Workspace memory curation: `.agents/skills/workspace-memory-curation/SKILL.md`
- Professional communication: `.agents/skills/professional-communication/SKILL.md`
- Status reporting: `.agents/skills/status-reporting/SKILL.md`
- AI prompt engineering: `.agents/skills/ai-prompt-engineering/SKILL.md`
---

View File

@@ -20,7 +20,7 @@ Keep this workspace useful as living memory instead of a pile of disconnected no
- Prefer correcting stale context over appending contradictory notes.
- Keep `project-knowledge/` human-facing and project-facing: write it as an engineer maintaining shared project notes, not as an AI maintaining its own operating instructions.
- Do not place agent-only logic, output contracts, prompting tactics, evaluation heuristics, or command-behavior rules in `project-knowledge/` unless a human engineer on the project would reasonably want that exact guidance there.
- Put agent behavior, prompt logic, formatting contracts, and slash-command rules in `agent-memory/`, `.opencode/commands/`, `prompts/`, `.opencode/agents/`, or `.opencode/skills/` instead of `project-knowledge/`.
- Put agent behavior, prompt logic, formatting contracts, and slash-command rules in `agent-memory/`, `.opencode/commands/`, `prompts/`, `.opencode/agents/`, or `.agents/skills/` instead of `project-knowledge/`.
- If a canonical note appears in an Obsidian Base, update its frontmatter properties together with the prose content.
- When changing frontmatter properties on existing canonical notes, prefer Obsidian CLI property operations through `scripts/obsidian/cli.sh` when available so YAML spacing and property formatting stay clean; fall back to direct Markdown edits only when the CLI is unavailable or the operation is unsupported.
- Keep templates under `project-knowledge/09-templates/` out of real-note Bases by filtering the template folder.
@@ -34,7 +34,7 @@ Keep this workspace useful as living memory instead of a pile of disconnected no
- `project-knowledge/01-current/work-items.md` for the compact active-work summary
- `project-knowledge/03-context/` for durable project knowledge
- `project-knowledge/04-people/` for named person context
- `.opencode/commands/`, `prompts/`, `.opencode/agents/`, `.opencode/skills/`, `agent-memory/`, `core/`, or `scripts/` for reusable behavior rules that control how the workspace responds
- `.opencode/commands/`, `prompts/`, `.opencode/agents/`, `.agents/skills/`, `agent-memory/`, `core/`, or `scripts/` for reusable behavior rules that control how the workspace responds
---

View File

@@ -54,7 +54,7 @@ When the user corrects a recurring behavior, the workspace should update the fil
- `.agents/workflows/` for slash commands (with `.opencode/commands/` for compatibility)
- `prompts/` for reusable drafting templates
- `.agents/rules/` and `AGENTS.md` for default agent behavior
- `.agents/skills/` for specialized workflows (with `.opencode/skills/` for compatibility)
- `.agents/skills/` for specialized workflows. Do not mirror into `.opencode/skills/`; OpenCode discovers `.agents/skills/` directly.
- `project-knowledge/00-start/` and `project-knowledge/03-context/process/` for project-facing onboarding and process rules
- `agent-memory/` for agent-specific behavior, learning, promotion, verification, and self-maintenance rules