@mrciphersmith/keryx 0.2.69 → 0.2.71

package/src/gdskills/bundled/skills/orchestration/task-implementer/SKILL.codex.md

@@ -11,8 +11,8 @@ metadata:
   author: "MrCipherSmith"
   version: "1.0.0"
   category: "implementation"
+  compatible_harnesses: "cursor,codex,zed,opencode"
 license: "MIT"
-compatibility: "cursor,codex,zed,opencode"
 ---
 
 # Task Implementer
@@ -284,7 +284,25 @@ npm run build-storybook   # Verify stories compile
 | Test failures | Fix failing tests, re-commit |
 | Story build failure | Fix story code, re-commit |
 
-Maximum 3 self-fix attempts per verification step. 
+Maximum 3 self-fix attempts per verification step.
+
+Three, and it is the same three `job-orchestrator` and `flow-orchestrator`
+use: one round bound, not four. *"The first three to four repair iterations
+account for most achievable gains"*
+([arXiv:2607.05197](https://arxiv.org/abs/2607.05197)); correctness falls
+**0.820 -> 0.673** across two forced revisions while cumulative ever-correct is
+**0.847** ([arXiv:2607.24604](https://arxiv.org/abs/2607.24604)) — the agent
+finds the fix and then destroys it. Aider hardcodes `max_reflections = 3`;
+OpenHands' critic uses 3.
+
+**Stop earlier on repetition, whatever the count says.** If an attempt produces
+the same failure output as the previous attempt — the same failing test with the
+same message, the same type error at the same site — do NOT spend the remaining
+attempts. The counter cannot tell "converging slowly" from "stuck", and three
+identical outputs cost the whole budget to learn what the second one already
+said. Report the block instead, naming what repeated.
+
+
 **ROLLBACK POLICY**: If implementation fatally fails (e.g. tests still failing after 3 attempts or unresolvable compilation errors), you MUST run `git reset --hard` to clean the worktree before reporting the failure in Phase 6, unless explicitly instructed to leave it dirty.
 
 **5.5 Re-commit fixes if any:**

package/src/gdskills/bundled/skills/orchestration/task-implementer/SKILL.cursor.md

@@ -11,8 +11,8 @@ metadata:
   author: "MrCipherSmith"
   version: "1.0.0"
   category: "implementation"
+  compatible_harnesses: "cursor,codex,zed,opencode"
 license: "MIT"
-compatibility: "cursor,codex,zed,opencode"
 ---
 
 # Task Implementer
@@ -284,7 +284,25 @@ npm run build-storybook   # Verify stories compile
 | Test failures | Fix failing tests, re-commit |
 | Story build failure | Fix story code, re-commit |
 
-Maximum 3 self-fix attempts per verification step. 
+Maximum 3 self-fix attempts per verification step.
+
+Three, and it is the same three `job-orchestrator` and `flow-orchestrator`
+use: one round bound, not four. *"The first three to four repair iterations
+account for most achievable gains"*
+([arXiv:2607.05197](https://arxiv.org/abs/2607.05197)); correctness falls
+**0.820 -> 0.673** across two forced revisions while cumulative ever-correct is
+**0.847** ([arXiv:2607.24604](https://arxiv.org/abs/2607.24604)) — the agent
+finds the fix and then destroys it. Aider hardcodes `max_reflections = 3`;
+OpenHands' critic uses 3.
+
+**Stop earlier on repetition, whatever the count says.** If an attempt produces
+the same failure output as the previous attempt — the same failing test with the
+same message, the same type error at the same site — do NOT spend the remaining
+attempts. The counter cannot tell "converging slowly" from "stuck", and three
+identical outputs cost the whole budget to learn what the second one already
+said. Report the block instead, naming what repeated.
+
+
 **ROLLBACK POLICY**: If implementation fatally fails (e.g. tests still failing after 3 attempts or unresolvable compilation errors), you MUST run `git reset --hard` to clean the worktree before reporting the failure in Phase 6, unless explicitly instructed to leave it dirty.
 
 **5.5 Re-commit fixes if any:**

package/src/gdskills/bundled/skills/orchestration/task-implementer/SKILL.md

@@ -1,5 +1,6 @@
 ---
 name: task-implementer
+model_tier: standard
 description: "Use when implementing a single decomposed task from issue-analyzer end-to-end, or executing autonomous code changes from a JSON task object."
 triggers:
   - "Implement task"
@@ -12,8 +13,8 @@ metadata:
   version: "1.2.0"
   category: "implementation"
   agent_worthy: true
+  compatible_harnesses: "cursor,codex,zed,opencode"
 license: "MIT"
-compatibility: "cursor,codex,zed,opencode"
 ---
 
 # Task Implementer
@@ -333,7 +334,25 @@ npm run build-storybook   # Verify stories compile
 | Test failures | Fix failing tests, re-commit |
 | Story build failure | Fix story code, re-commit |
 
-Maximum 3 self-fix attempts per verification step. 
+Maximum 3 self-fix attempts per verification step.
+
+Three, and it is the same three `job-orchestrator` and `flow-orchestrator`
+use: one round bound, not four. *"The first three to four repair iterations
+account for most achievable gains"*
+([arXiv:2607.05197](https://arxiv.org/abs/2607.05197)); correctness falls
+**0.820 -> 0.673** across two forced revisions while cumulative ever-correct is
+**0.847** ([arXiv:2607.24604](https://arxiv.org/abs/2607.24604)) — the agent
+finds the fix and then destroys it. Aider hardcodes `max_reflections = 3`;
+OpenHands' critic uses 3.
+
+**Stop earlier on repetition, whatever the count says.** If an attempt produces
+the same failure output as the previous attempt — the same failing test with the
+same message, the same type error at the same site — do NOT spend the remaining
+attempts. The counter cannot tell "converging slowly" from "stuck", and three
+identical outputs cost the whole budget to learn what the second one already
+said. Report the block instead, naming what repeated.
+
+
 **ROLLBACK POLICY**: If implementation fatally fails (e.g. tests still failing after 3 attempts or unresolvable compilation errors), you MUST run `git reset --hard` to clean the worktree before reporting the failure in Phase 6, unless explicitly instructed to leave it dirty.
 
 **5.5 Re-commit fixes if any:**
@@ -531,7 +550,7 @@ Run task-1 (which creates pipeline.ts) before re-dispatching this task, or provi
 - (nothing — blocked before implementation could start)
 ```
 
-See `rules/core/subagent-status-protocol.md` for full format specification and all four status types.
+See `rules/core/subagent-status-protocol.md` for the full format specification. Four statuses are yours as a skill worker; the fifth, `FAILED`, belongs to harness child workers and you must never emit it — report `BLOCKED` instead.
 
 ---
 

package/src/gdskills/bundled/skills/orchestration/task-implementer/SKILL.opencode.md

@@ -11,8 +11,8 @@ metadata:
   author: "MrCipherSmith"
   version: "1.0.0"
   category: "implementation"
+  compatible_harnesses: "cursor,codex,zed,opencode"
 license: "MIT"
-compatibility: "cursor,codex,zed,opencode"
 ---
 
 # Task Implementer
@@ -284,7 +284,25 @@ npm run build-storybook   # Verify stories compile
 | Test failures | Fix failing tests, re-commit |
 | Story build failure | Fix story code, re-commit |
 
-Maximum 3 self-fix attempts per verification step. 
+Maximum 3 self-fix attempts per verification step.
+
+Three, and it is the same three `job-orchestrator` and `flow-orchestrator`
+use: one round bound, not four. *"The first three to four repair iterations
+account for most achievable gains"*
+([arXiv:2607.05197](https://arxiv.org/abs/2607.05197)); correctness falls
+**0.820 -> 0.673** across two forced revisions while cumulative ever-correct is
+**0.847** ([arXiv:2607.24604](https://arxiv.org/abs/2607.24604)) — the agent
+finds the fix and then destroys it. Aider hardcodes `max_reflections = 3`;
+OpenHands' critic uses 3.
+
+**Stop earlier on repetition, whatever the count says.** If an attempt produces
+the same failure output as the previous attempt — the same failing test with the
+same message, the same type error at the same site — do NOT spend the remaining
+attempts. The counter cannot tell "converging slowly" from "stuck", and three
+identical outputs cost the whole budget to learn what the second one already
+said. Report the block instead, naming what repeated.
+
+
 **ROLLBACK POLICY**: If implementation fatally fails (e.g. tests still failing after 3 attempts or unresolvable compilation errors), you MUST run `git reset --hard` to clean the worktree before reporting the failure in Phase 6, unless explicitly instructed to leave it dirty.
 
 **5.5 Re-commit fixes if any:**

package/src/gdskills/bundled/skills/orchestration/task-implementer/SKILL.zed.md

@@ -11,8 +11,8 @@ metadata:
   author: "MrCipherSmith"
   version: "1.0.0"
   category: "implementation"
+  compatible_harnesses: "cursor,codex,zed,opencode"
 license: "MIT"
-compatibility: "cursor,codex,zed,opencode"
 ---
 
 # Task Implementer
@@ -284,7 +284,25 @@ npm run build-storybook   # Verify stories compile
 | Test failures | Fix failing tests, re-commit |
 | Story build failure | Fix story code, re-commit |
 
-Maximum 3 self-fix attempts per verification step. 
+Maximum 3 self-fix attempts per verification step.
+
+Three, and it is the same three `job-orchestrator` and `flow-orchestrator`
+use: one round bound, not four. *"The first three to four repair iterations
+account for most achievable gains"*
+([arXiv:2607.05197](https://arxiv.org/abs/2607.05197)); correctness falls
+**0.820 -> 0.673** across two forced revisions while cumulative ever-correct is
+**0.847** ([arXiv:2607.24604](https://arxiv.org/abs/2607.24604)) — the agent
+finds the fix and then destroys it. Aider hardcodes `max_reflections = 3`;
+OpenHands' critic uses 3.
+
+**Stop earlier on repetition, whatever the count says.** If an attempt produces
+the same failure output as the previous attempt — the same failing test with the
+same message, the same type error at the same site — do NOT spend the remaining
+attempts. The counter cannot tell "converging slowly" from "stuck", and three
+identical outputs cost the whole budget to learn what the second one already
+said. Report the block instead, naming what repeated.
+
+
 **ROLLBACK POLICY**: If implementation fatally fails (e.g. tests still failing after 3 attempts or unresolvable compilation errors), you MUST run `git reset --hard` to clean the worktree before reporting the failure in Phase 6, unless explicitly instructed to leave it dirty.
 
 **5.5 Re-commit fixes if any:**

package/src/gdskills/bundled/skills/planning/autodoc-analyst/SKILL.md

@@ -5,7 +5,8 @@ description: >
   to extract purpose, structure, public API surface, patterns, and key dependencies.
   Use when: dispatched by autodoc-orchestrator Phase 2 (one instance per module).
   NOT for: direct user invocation.
-version: 1.0.0
+metadata:
+  version: 1.0.0
 ---
 
 # autodoc-analyst

package/src/gdskills/bundled/skills/planning/autodoc-architect/SKILL.md

@@ -1,12 +1,14 @@
 ---
 name: autodoc-architect
+model_tier: deep
 description: >
   Phase 3 subagent for autodoc-orchestrator. Synthesizes all module analyses
   into a system-level architecture description: layers, data flows, integration
   points, and cross-cutting concerns.
   Use when: dispatched by autodoc-orchestrator Phase 3.
   NOT for: direct user invocation.
-version: 1.0.0
+metadata:
+  version: 1.0.0
 ---
 
 # autodoc-architect

package/src/gdskills/bundled/skills/planning/autodoc-assembler/SKILL.md

@@ -5,7 +5,8 @@ description: >
   into a cohesive package: main README.md and navigation index.
   Use when: dispatched by autodoc-orchestrator Phase 5.
   NOT for: direct user invocation.
-version: 1.0.0
+metadata:
+  version: 1.0.0
 ---
 
 # autodoc-assembler

package/src/gdskills/bundled/skills/planning/autodoc-orchestrator/SKILL.md

@@ -10,7 +10,8 @@ description: >
   Trigger on: user provides a repo path, asks to document existing code, wants
   onboarding docs, API reference, or architecture overview generated automatically.
   NOT for: writing new PRDs or planning new features (use gproject-orchestrator).
-version: 1.0.0
+metadata:
+  version: 1.0.0
 ---
 
 <!-- SUBAGENT-STOP: If you are a subagent dispatched by another orchestrator, HALT.

package/src/gdskills/bundled/skills/planning/autodoc-scanner/SKILL.md

@@ -5,7 +5,8 @@ description: >
   detects stack, identifies module boundaries, entry points, and dependencies.
   Use when: dispatched by autodoc-orchestrator Phase 1.
   NOT for: direct user invocation.
-version: 1.0.0
+metadata:
+  version: 1.0.0
 ---
 
 # autodoc-scanner

package/src/gdskills/bundled/skills/planning/autodoc-writer/SKILL.md

@@ -5,7 +5,8 @@ description: >
   from analysis artifacts. Dispatched in parallel — one instance per section.
   Use when: dispatched by autodoc-orchestrator Phase 4.
   NOT for: direct user invocation.
-version: 1.0.0
+metadata:
+  version: 1.0.0
 ---
 
 # autodoc-writer

package/src/gdskills/bundled/skills/planning/brainstorm/SKILL.codex.md

@@ -12,8 +12,8 @@ metadata:
   author: "MrCipherSmith"
   version: "1.0.0"
   category: "ideation"
+  compatible_harnesses: "cursor,codex,zed,opencode,claude"
 license: "MIT"
-compatibility: "cursor,codex,zed,opencode,claude"
 ---
 
 # Brainstorm

package/src/gdskills/bundled/skills/planning/brainstorm/SKILL.cursor.md

@@ -12,8 +12,8 @@ metadata:
   author: "MrCipherSmith"
   version: "1.0.0"
   category: "ideation"
+  compatible_harnesses: "cursor,codex,zed,opencode,claude"
 license: "MIT"
-compatibility: "cursor,codex,zed,opencode,claude"
 ---
 
 # Brainstorm

package/src/gdskills/bundled/skills/planning/brainstorm/SKILL.md

@@ -12,8 +12,8 @@ metadata:
   author: "MrCipherSmith"
   version: "1.0.0"
   category: "ideation"
+  compatible_harnesses: "cursor,codex,zed,opencode,claude"
 license: "MIT"
-compatibility: "cursor,codex,zed,opencode,claude"
 ---
 
 # Brainstorm

package/src/gdskills/bundled/skills/planning/consistency-checker/SKILL.codex.md

@@ -8,8 +8,8 @@ metadata:
   author: "MrCipherSmith"
   version: "1.0.0"
   category: "planning"
+  compatible_harnesses: "cursor,codex,zed,opencode"
 license: "MIT"
-compatibility: "cursor,codex,zed,opencode"
 ---
 
 

package/src/gdskills/bundled/skills/planning/consistency-checker/SKILL.cursor.md

@@ -8,8 +8,8 @@ metadata:
   author: "MrCipherSmith"
   version: "1.0.0"
   category: "planning"
+  compatible_harnesses: "cursor,codex,zed,opencode"
 license: "MIT"
-compatibility: "cursor,codex,zed,opencode"
 ---
 
 

package/src/gdskills/bundled/skills/planning/consistency-checker/SKILL.md

@@ -5,7 +5,8 @@ description: >
   and best practices constraints. Catches contradictions, gaps, and violations.
   Use when: dispatched by gproject-orchestrator Phase 5.
   NOT for: direct user invocation.
-version: 1.0.0
+metadata:
+  version: 1.0.0
 ---
 
 # gproject-consistency-checker

package/src/gdskills/bundled/skills/planning/docpack-orchestrator/SKILL.md

@@ -12,8 +12,8 @@ metadata:
   author: "MrCipherSmith"
   version: "1.0.0"
   category: "planning"
+  compatible_harnesses: "cursor,codex,zed,opencode,claude"
 license: "MIT"
-compatibility: "cursor,codex,zed,opencode,claude"
 ---
 
 # docpack-orchestrator

package/src/gdskills/bundled/skills/planning/docpack-review/SKILL.md

@@ -11,8 +11,8 @@ metadata:
   author: "MrCipherSmith"
   version: "1.0.0"
   category: "planning"
+  compatible_harnesses: "cursor,codex,zed,opencode,claude"
 license: "MIT"
-compatibility: "cursor,codex,zed,opencode,claude"
 ---
 
 # docpack-review

package/src/gdskills/bundled/skills/planning/interview/SKILL.codex.md

@@ -12,8 +12,8 @@ metadata:
   author: "MrCipherSmith"
   version: "1.0.0"
   category: "analysis"
+  compatible_harnesses: "cursor,codex,zed,opencode,claude"
 license: "MIT"
-compatibility: "cursor,codex,zed,opencode,claude"
 ---
 
 # Interview

package/src/gdskills/bundled/skills/planning/interview/SKILL.cursor.md

@@ -12,8 +12,8 @@ metadata:
   author: "MrCipherSmith"
   version: "1.0.0"
   category: "analysis"
+  compatible_harnesses: "cursor,codex,zed,opencode,claude"
 license: "MIT"
-compatibility: "cursor,codex,zed,opencode,claude"
 ---
 
 # Interview

package/src/gdskills/bundled/skills/planning/interview/SKILL.md

@@ -12,8 +12,8 @@ metadata:
   author: "MrCipherSmith"
   version: "1.0.0"
   category: "analysis"
+  compatible_harnesses: "cursor,codex,zed,opencode,claude"
 license: "MIT"
-compatibility: "cursor,codex,zed,opencode,claude"
 ---
 
 <SUBAGENT-STOP>

package/src/gdskills/bundled/skills/planning/interviewer/SKILL.codex.md

@@ -11,8 +11,8 @@ metadata:
   author: "MrCipherSmith"
   version: "1.0.0"
   category: "meta"
+  compatible_harnesses: "cursor,codex,zed,opencode,claude"
 license: "MIT"
-compatibility: "cursor,codex,zed,opencode,claude"
 ---
 
 # Interviewer

package/src/gdskills/bundled/skills/planning/interviewer/SKILL.cursor.md

@@ -11,8 +11,8 @@ metadata:
   author: "MrCipherSmith"
   version: "1.0.0"
   category: "meta"
+  compatible_harnesses: "cursor,codex,zed,opencode,claude"
 license: "MIT"
-compatibility: "cursor,codex,zed,opencode,claude"
 ---
 
 # Interviewer

package/src/gdskills/bundled/skills/planning/interviewer/SKILL.md

@@ -11,8 +11,8 @@ metadata:
   author: "MrCipherSmith"
   version: "1.0.0"
   category: "meta"
+  compatible_harnesses: "cursor,codex,zed,opencode,claude"
 license: "MIT"
-compatibility: "cursor,codex,zed,opencode,claude"
 ---
 
 <SUBAGENT-STOP>

package/src/gdskills/bundled/skills/planning/patterns-researcher/SKILL.codex.md

@@ -8,8 +8,8 @@ metadata:
   author: "MrCipherSmith"
   version: "1.0.0"
   category: "planning"
+  compatible_harnesses: "cursor,codex,zed,opencode"
 license: "MIT"
-compatibility: "cursor,codex,zed,opencode"
 ---
 
 

package/src/gdskills/bundled/skills/planning/patterns-researcher/SKILL.cursor.md

@@ -8,8 +8,8 @@ metadata:
   author: "MrCipherSmith"
   version: "1.0.0"
   category: "planning"
+  compatible_harnesses: "cursor,codex,zed,opencode"
 license: "MIT"
-compatibility: "cursor,codex,zed,opencode"
 ---
 
 

package/src/gdskills/bundled/skills/planning/patterns-researcher/SKILL.md

@@ -5,7 +5,8 @@ description: >
   application architecture patterns. Produces constraints that PRD must follow.
   Use when: dispatched by gproject-orchestrator Phase 3.
   NOT for: direct user invocation.
-version: 1.0.0
+metadata:
+  version: 1.0.0
 ---
 
 # gproject-patterns-researcher

package/src/gdskills/bundled/skills/planning/planner/SKILL.codex.md

@@ -8,8 +8,8 @@ metadata:
   author: "MrCipherSmith"
   version: "1.0.0"
   category: "planning"
+  compatible_harnesses: "cursor,codex,zed,opencode"
 license: "MIT"
-compatibility: "cursor,codex,zed,opencode"
 ---
 
 

package/src/gdskills/bundled/skills/planning/planner/SKILL.cursor.md

@@ -8,8 +8,8 @@ metadata:
   author: "MrCipherSmith"
   version: "1.0.0"
   category: "planning"
+  compatible_harnesses: "cursor,codex,zed,opencode"
 license: "MIT"
-compatibility: "cursor,codex,zed,opencode"
 ---
 
 

package/src/gdskills/bundled/skills/planning/planner/SKILL.md

@@ -4,7 +4,8 @@ description: >
   Generates roadmap, milestones, task breakdown, and dependency graph from PRD.
   Use when: dispatched by gproject-orchestrator Phase 6.
   NOT for: direct user invocation.
-version: 1.0.0
+metadata:
+  version: 1.0.0
 ---
 
 # gproject-planner

package/src/gdskills/bundled/skills/planning/prd-creator/SKILL.codex.md

@@ -11,8 +11,8 @@ metadata:
   author: "MrCipherSmith"
   version: "1.0.0"
   category: "planning"
+  compatible_harnesses: "cursor,codex,zed,opencode"
 license: "MIT"
-compatibility: "cursor,codex,zed,opencode"
 ---
 
 # PRD-Creator Sub-Agent

package/src/gdskills/bundled/skills/planning/prd-creator/SKILL.cursor.md

@@ -11,8 +11,8 @@ metadata:
   author: "MrCipherSmith"
   version: "1.0.0"
   category: "planning"
+  compatible_harnesses: "cursor,codex,zed,opencode"
 license: "MIT"
-compatibility: "cursor,codex,zed,opencode"
 ---
 
 # PRD-Creator Sub-Agent

package/src/gdskills/bundled/skills/planning/prd-creator/SKILL.md

@@ -11,8 +11,8 @@ metadata:
   author: "MrCipherSmith"
   version: "1.0.0"
   category: "planning"
+  compatible_harnesses: "cursor,codex,zed,opencode"
 license: "MIT"
-compatibility: "cursor,codex,zed,opencode"
 ---
 
 # PRD-Creator Sub-Agent

package/src/gdskills/bundled/skills/planning/prd-creator/SKILL.opencode.md

@@ -11,8 +11,8 @@ metadata:
   author: "MrCipherSmith"
   version: "1.0.0"
   category: "planning"
+  compatible_harnesses: "cursor,codex,zed,opencode"
 license: "MIT"
-compatibility: "cursor,codex,zed,opencode"
 ---
 
 # PRD-Creator Sub-Agent

package/src/gdskills/bundled/skills/planning/prd-creator/SKILL.zed.md

@@ -11,8 +11,8 @@ metadata:
   author: "MrCipherSmith"
   version: "1.0.0"
   category: "planning"
+  compatible_harnesses: "cursor,codex,zed,opencode"
 license: "MIT"
-compatibility: "cursor,codex,zed,opencode"
 ---
 
 # PRD-Creator Sub-Agent

package/src/gdskills/bundled/skills/planning/problem-definer/SKILL.codex.md

@@ -8,8 +8,8 @@ metadata:
   author: "MrCipherSmith"
   version: "1.0.0"
   category: "planning"
+  compatible_harnesses: "cursor,codex,zed,opencode"
 license: "MIT"
-compatibility: "cursor,codex,zed,opencode"
 ---
 
 

package/src/gdskills/bundled/skills/planning/problem-definer/SKILL.cursor.md

@@ -8,8 +8,8 @@ metadata:
   author: "MrCipherSmith"
   version: "1.0.0"
   category: "planning"
+  compatible_harnesses: "cursor,codex,zed,opencode"
 license: "MIT"
-compatibility: "cursor,codex,zed,opencode"
 ---
 
 

package/src/gdskills/bundled/skills/planning/problem-definer/SKILL.md

@@ -4,7 +4,8 @@ description: >
   Defines core problems, goals, non-goals, and success metrics from discovery data.
   Use when: dispatched by gproject-orchestrator Phase 1.
   NOT for: direct user invocation.
-version: 1.0.0
+metadata:
+  version: 1.0.0
 ---
 
 # gproject-problem-definer

package/src/gdskills/bundled/skills/planning/project-discovery/SKILL.codex.md

@@ -8,8 +8,8 @@ metadata:
   author: "MrCipherSmith"
   version: "1.0.0"
   category: "planning"
+  compatible_harnesses: "cursor,codex,zed,opencode"
 license: "MIT"
-compatibility: "cursor,codex,zed,opencode"
 ---
 
 

package/src/gdskills/bundled/skills/planning/project-discovery/SKILL.cursor.md

@@ -8,8 +8,8 @@ metadata:
   author: "MrCipherSmith"
   version: "1.0.0"
   category: "planning"
+  compatible_harnesses: "cursor,codex,zed,opencode"
 license: "MIT"
-compatibility: "cursor,codex,zed,opencode"
 ---
 
 

package/src/gdskills/bundled/skills/planning/project-discovery/SKILL.md

@@ -4,7 +4,8 @@ description: >
   Collects and structures initial project information from multiple sources.
   Use when: dispatched by gproject-orchestrator Phase 0.
   NOT for: direct user invocation — always called through orchestrator.
-version: 1.0.0
+metadata:
+  version: 1.0.0
 ---
 
 # gproject-discovery

package/src/gdskills/bundled/skills/planning/spec-writer/SKILL.codex.md

@@ -8,8 +8,8 @@ metadata:
   author: "MrCipherSmith"
   version: "1.0.0"
   category: "planning"
+  compatible_harnesses: "cursor,codex,zed,opencode"
 license: "MIT"
-compatibility: "cursor,codex,zed,opencode"
 ---
 
 

package/src/gdskills/bundled/skills/planning/spec-writer/SKILL.cursor.md

@@ -8,8 +8,8 @@ metadata:
   author: "MrCipherSmith"
   version: "1.0.0"
   category: "planning"
+  compatible_harnesses: "cursor,codex,zed,opencode"
 license: "MIT"
-compatibility: "cursor,codex,zed,opencode"
 ---
 
 

package/src/gdskills/bundled/skills/planning/spec-writer/SKILL.md

@@ -5,7 +5,8 @@ description: >
   architecture doc, and best practices. Does NOT invent new architectural decisions.
   Use when: dispatched by gproject-orchestrator Phase 4.
   NOT for: direct user invocation.
-version: 1.0.0
+metadata:
+  version: 1.0.0
 ---
 
 # gproject-spec-writer