williamthorsen · williamthorsen · Mar 23, 2026 · Mar 23, 2026
diff --git a/packages/agents/content/skills/_data/case-conventions.md b/packages/agents/content/skills/_data/case-conventions.md
diff --git a/packages/agents/content/skills/code-patterns/SKILL.md b/packages/agents/content/skills/code-patterns/SKILL.md
@@ -36,7 +36,7 @@ Rules for how code is structured, organized, and documented.
 
 ## Naming
 
-Follow the naming rules in `_data/naming-conventions.md`: no abbreviations, unit-of-measure suffixes on numerics, verb-led function names, boolean prefixes (`is`, `has`, `should`, `does`).
+Follow the naming rules in [naming-conventions.md](../_data/naming-conventions.md): no abbreviations, unit-of-measure suffixes on numerics, verb-led function names, boolean prefixes (`is`, `has`, `should`, `does`).
 
 ## Testing patterns
 

diff --git a/packages/agents/content/skills/condense-branch/SKILL.md b/packages/agents/content/skills/condense-branch/SKILL.md
@@ -44,7 +44,7 @@ Use `summarize-change` to compose a good commit message. Save the description pe
 
 ## Commit format
 
-Follow `_data/commit-format.md`:
+Follow [commit-format.md](../_data/commit-format.md):
 
 ```
 {workspace}|{WORK_TYPE}: {title}

diff --git a/packages/agents/content/skills/create-devlog/SKILL.md b/packages/agents/content/skills/create-devlog/SKILL.md
@@ -52,7 +52,7 @@ Resolve artifact directory using `get-session-context` to obtain `artifact_base_
 
 Full path: `{artifact_base_dir}/projects/{project_slug}/{devlogs_path}/`
 
-Follow [artifact conventions](_data/artifact-conventions.md).
+Follow [artifact conventions](../_data/artifact-conventions.md).
 
 Artifact type: `devlog`. Filename format:
 

diff --git a/packages/agents/content/skills/design-and-plan/SKILL.md b/packages/agents/content/skills/design-and-plan/SKILL.md
@@ -196,7 +196,7 @@ Present the plan to the user. Revise until approved.
 
    If `baseSha` could not be resolved, omit the `baseSha` line entirely.
 
-4. Report paths and present next steps. The plan is unreviewed — use this as recommendation context when applying the rules in [next-steps-after-plan](_data/next-steps-after-plan.md). Include both `{ticket_path}` and `{plan_path}` in each skill-invoking option line.
+4. Report paths and present next steps. The plan is unreviewed — use this as recommendation context when applying the rules in [next-steps-after-plan](../_data/next-steps-after-plan.md). Include both `{ticket_path}` and `{plan_path}` in each skill-invoking option line.
 
 ```
 Design and plan complete:

diff --git a/packages/agents/content/skills/ex-post-facto/SKILL.md b/packages/agents/content/skills/ex-post-facto/SKILL.md
@@ -65,7 +65,7 @@ git diff $DEFAULT_BRANCH...HEAD
 
 Use `get-session-context` to obtain `artifact_base_dir`, `project_slug`, and `ticket_id`.
 
-Follow [artifact conventions](_data/artifact-conventions.md).
+Follow [artifact conventions](../_data/artifact-conventions.md).
 
 Ticket directory: `{artifact_base_dir}/projects/{project_slug}/tickets/{ticket_id}/`
 

diff --git a/packages/agents/content/skills/plan/SKILL.md b/packages/agents/content/skills/plan/SKILL.md
@@ -69,7 +69,7 @@ If inside an active run (`run-index.json` exists in a parent directory):
 2. Save as ticket-level artifact: `{artifact_base_dir}/projects/{project_slug}/tickets/{ticket_id}/{timestamp}_{slug}_plan.md`
 3. Slug derived from the plan's descriptive title (kebab-case, max 60 chars).
 
-Follow [artifact conventions](_data/artifact-conventions.md).
+Follow [artifact conventions](../_data/artifact-conventions.md).
 
 `mkdir -p` the target directory before writing.
 

diff --git a/packages/agents/content/skills/prepare-pr/SKILL.md b/packages/agents/content/skills/prepare-pr/SKILL.md
@@ -33,7 +33,7 @@ git rev-parse --short HEAD
 
 Use `get-session-context` to obtain `artifact_base_dir`, `project_slug`, and `ticket_id`.
 
-Follow [artifact conventions](_data/artifact-conventions.md).
+Follow [artifact conventions](../_data/artifact-conventions.md).
 
 Ticket directory: `{artifact_base_dir}/projects/{project_slug}/tickets/{ticket_id}/`
 

diff --git a/packages/agents/content/skills/refine-plan/SKILL.md b/packages/agents/content/skills/refine-plan/SKILL.md
@@ -75,7 +75,7 @@ Parse the return block:
 
 Evaluate the finding counts:
 
-- **0 total findings** (AutoResolvable = 0 AND UserQuestions = 0): skip the reviser entirely. Report that the plan needs no refinement, then present next steps. The plan was just reviewed with no issues — use this as recommendation context when applying the rules in [next-steps-after-plan](_data/next-steps-after-plan.md). Use `{plan_path}` (the original plan argument, not `{revision_output_path}` — no revised plan exists on this path) and `{ticket_source}` in each skill-invoking option line.
+- **0 total findings** (AutoResolvable = 0 AND UserQuestions = 0): skip the reviser entirely. Report that the plan needs no refinement, then present next steps. The plan was just reviewed with no issues — use this as recommendation context when applying the rules in [next-steps-after-plan](../_data/next-steps-after-plan.md). Use `{plan_path}` (the original plan argument, not `{revision_output_path}` — no revised plan exists on this path) and `{ticket_source}` in each skill-invoking option line.
 
   ```
   Plan reviewed -- no findings. The plan is ready for implementation.
@@ -211,7 +211,7 @@ Plan refined:
   Revised: {revision_output_path}
 ```
 
-After reporting, present next steps. The plan was just reviewed. If the review surfaced significant scope changes or unresolved questions that led to a dramatic revision, the plan may warrant another refinement round; otherwise, orchestration is the typical recommendation. Use this as recommendation context when applying the rules in [next-steps-after-plan](_data/next-steps-after-plan.md). Include both `{revision_output_path}` (as the plan path) and `{ticket_source}` in each skill-invoking option line.
+After reporting, present next steps. The plan was just reviewed. If the review surfaced significant scope changes or unresolved questions that led to a dramatic revision, the plan may warrant another refinement round; otherwise, orchestration is the typical recommendation. Use this as recommendation context when applying the rules in [next-steps-after-plan](../_data/next-steps-after-plan.md). Include both `{revision_output_path}` (as the plan path) and `{ticket_source}` in each skill-invoking option line.
 
 ```
 Next steps:

diff --git a/packages/agents/content/skills/respond-to-review/SKILL.md b/packages/agents/content/skills/respond-to-review/SKILL.md
@@ -22,7 +22,7 @@ This skill bridges the gap between receiving a code review and implementing fixe
 1. **Get context** using `get-session-context` to obtain `ticket_id`, `project_slug`, and `artifact_base_dir`
 2. **Locate the review** per the [Locating the review](#locating-the-review) section
 3. **Read prior artifacts** in the run directory chronologically for full context
-4. **Parse findings**: extract all numbered findings (F{n}, W{n}, T{n}, R{n}, S{n}, L{n}). See [finding scheme](_data/artifact-conventions.md#finding-scheme-fwtrsl) for category definitions.
+4. **Parse findings**: extract all numbered findings (F{n}, W{n}, T{n}, R{n}, S{n}, L{n}). See [finding scheme](../_data/artifact-conventions.md#finding-scheme-fwtrsl) for category definitions.
 5. **Evaluate each finding** following the evaluation protocol below
 6. **Write response** per the output format
 7. **Save** per the [Saving](#saving) section
@@ -70,7 +70,7 @@ This is distinct from the **post-implementation** vocabulary used by the orchest
 
 ## Disposition scope
 
-Per [artifact conventions](_data/artifact-conventions.md#disposition-rules):
+Per [artifact conventions](../_data/artifact-conventions.md#disposition-rules):
 
 | Role     | Can disposition                                              | Cannot disposition                                       |
 | -------- | ------------------------------------------------------------ | -------------------------------------------------------- |
@@ -163,7 +163,7 @@ Author: {Agent name} (model: {model})
 
 Use `get-session-context` to obtain `artifact_base_dir` and `project_slug`.
 
-Follow [artifact conventions](_data/artifact-conventions.md).
+Follow [artifact conventions](../_data/artifact-conventions.md).
 
 ### Run directory
 

diff --git a/packages/agents/content/skills/review-change/SKILL.md b/packages/agents/content/skills/review-change/SKILL.md
@@ -44,7 +44,7 @@ For GitHub: `gh issue view --json number,title,body,labels {number}`
 5. **Review thoroughly** following the guidelines below
 6. **Assign a score** out of 10
 7. **Save the review** per the [Saving](#saving) section
-8. **Present next steps** _(branch scope only)_ — after saving, present a next-steps prompt following [next-steps-after-review](_data/next-steps-after-review.md). Supply recommendation context: finding counts and categories from the review, and whether ticket compliance gaps or unplanned work were identified. The next-steps prompt is interactive output only and is not saved in the review artifact.
+8. **Present next steps** _(branch scope only)_ — after saving, present a next-steps prompt following [next-steps-after-review](../_data/next-steps-after-review.md). Supply recommendation context: finding counts and categories from the review, and whether ticket compliance gaps or unplanned work were identified. The next-steps prompt is interactive output only and is not saved in the review artifact.
 
 ## Review guidelines
 
@@ -65,7 +65,7 @@ Read and apply the `review-criteria` skill (`../review-criteria/SKILL.md`). Addi
 
 ## Issue numbering
 
-Uniquely number all issues for easy reference. See [finding scheme](_data/artifact-conventions.md#finding-scheme-fwtrsl) for full category criteria and criticality mapping.
+Uniquely number all issues for easy reference. See [finding scheme](../_data/artifact-conventions.md#finding-scheme-fwtrsl) for full category criteria and criticality mapping.
 
 - FIXMEs: `F{n}` — critical, must fix before merge
 - Warnings: `W{n}` — questionable decisions, may block merge
@@ -221,7 +221,7 @@ Score: X/10
 
 Use `get-session-context` to obtain `artifact_base_dir`, `project_slug`, and `ticket_id`.
 
-Follow [artifact conventions](_data/artifact-conventions.md).
+Follow [artifact conventions](../_data/artifact-conventions.md).
 
 ### Branch scope
 

diff --git a/packages/agents/content/skills/save-artifact/SKILL.md b/packages/agents/content/skills/save-artifact/SKILL.md
@@ -40,8 +40,8 @@ Save AI-generated files with standardized naming conventions.
 
 **Common fields (both formats):**
 
-- **role**: Kebab-case identifier; hyphens are free within the name, underscores are reserved as structural separators. Each role has a `roleType` (one of: `orchestrator`, `analyst`, `planner`, `author`, `reviewer`). See [artifact-conventions.md](_data/artifact-conventions.md#run-artifacts-review-workflow) for the current role list and [roleType taxonomy](_data/artifact-conventions.md#roletype-taxonomy).
-- **artifact**: Kebab-case identifier following the same naming conventions. See [artifact-conventions.md](_data/artifact-conventions.md#artifact-types) for the complete artifact type list.
+- **role**: Kebab-case identifier; hyphens are free within the name, underscores are reserved as structural separators. Each role has a `roleType` (one of: `orchestrator`, `analyst`, `planner`, `author`, `reviewer`). See [artifact-conventions.md](../_data/artifact-conventions.md#run-artifacts-review-workflow) for the current role list and [roleType taxonomy](../_data/artifact-conventions.md#roletype-taxonomy).
+- **artifact**: Kebab-case identifier following the same naming conventions. See [artifact-conventions.md](../_data/artifact-conventions.md#artifact-types) for the complete artifact type list.
 
 Run artifacts are saved by the skills that produce them (`review-change`, `respond-to-review`). They handle run directory discovery and creation.
 
@@ -91,7 +91,7 @@ Create the directory if needed.
 
 Read `artifact_paths` from the `get-session-context` manifest for category paths (chats, devlogs, plans). These are relative to the project directory: `{artifact_base_dir}/projects/{project_slug}/{category}/`.
 
-Follow [artifact conventions](_data/artifact-conventions.md).
+Follow [artifact conventions](../_data/artifact-conventions.md).
 
 ## Slug generation
 

diff --git a/packages/agents/content/skills/save-plan/SKILL.md b/packages/agents/content/skills/save-plan/SKILL.md
@@ -45,13 +45,13 @@ Save the plan from the current conversation as a ticket-scoped artifact. Useful
 
    Include `baseSha` only if resolved successfully.
 
-Follow [artifact conventions](_data/artifact-conventions.md).
+Follow [artifact conventions](../_data/artifact-conventions.md).
 
 ## Completion
 
 Report the file path, then present a ticket prompt and next steps together in a single message. Do not wait for the user's reply before showing next steps.
 
-The plan source is unknown (could be plan mode, third-party tool, or manual) — treat it as unreviewed. Use this as recommendation context when applying the rules in [next-steps-after-plan](_data/next-steps-after-plan.md). Omit the ticket path from option lines — no ticket path is available at completion time.
+The plan source is unknown (could be plan mode, third-party tool, or manual) — treat it as unreviewed. Use this as recommendation context when applying the rules in [next-steps-after-plan](../_data/next-steps-after-plan.md). Omit the ticket path from option lines — no ticket path is available at completion time.
 
 ```
 Plan saved: {plan_path}

diff --git a/packages/agents/content/skills/summarize-change/SKILL.md b/packages/agents/content/skills/summarize-change/SKILL.md
@@ -11,7 +11,7 @@ Analyze the current branch's changes since diverging from the default branch.
 ## Process
 
 1. **Gather context**:
-   - Use `get-session-context` to obtain `default_branch` and `ticket_id`; consult `_data/work-types.md`.
+   - Use `get-session-context` to obtain `default_branch` and `ticket_id`; consult [work-types.md](../_data/work-types.md).
    - Determine workspace from commit subjects: parse `{workspace}|{type}:` prefixes, collect unique values. Single → use it. Multiple → use `*`. None → omit.
 
 2. **Analyze changes**:
@@ -100,7 +100,7 @@ When the original ticket is accessible:
 
 Use `get-session-context` to obtain `artifact_base_dir`, `project_slug`, and `ticket_id`.
 
-Follow [artifact conventions](_data/artifact-conventions.md).
+Follow [artifact conventions](../_data/artifact-conventions.md).
 
 Ticket directory: `{artifact_base_dir}/projects/{project_slug}/tickets/{ticket_id}/`
 

diff --git a/packages/agents/content/skills/summarize-chat/SKILL.md b/packages/agents/content/skills/summarize-chat/SKILL.md
@@ -71,7 +71,7 @@ Resolve artifact directory using `get-session-context` to obtain `artifact_base_
 
 Full path: `{artifact_base_dir}/projects/{project_slug}/{chats_path}/`
 
-Follow [artifact conventions](_data/artifact-conventions.md).
+Follow [artifact conventions](../_data/artifact-conventions.md).
 
 Artifact type: `chat-summary`. Filename format: