@jenga-ai/agent 2.0.0 → 3.0.0

package/skills/{clearify → j-clearify}/SKILL.md

@@ -1,6 +1,6 @@
 ---
-name: j:clearify
-description: Clarifies ambiguous, dense, or under-specified prompts and conversation on request — inspects an attached prompt or falls back to the current conversation and surfaces plain-language clarifications with examples.
+name: j.clearify
+description: Polyfill alias of the clearify skill under a collision-safe directory name. Identical behavior to /clearify — Clarifies ambiguous, dense, or under-specified prompts and conversation on request — inspects an attached prompt or falls back to the current conversation and surfaces plain-language clarifications with examples. Use when the bare /clearify form is shadowed by another tool's own built-in command of the same name.
 keywords:
   - clarify this
   - clarify
@@ -9,16 +9,23 @@ keywords:
   - wtf
   - explain that again
   - can you simplify
+  - j-clearify
+  - polyfill
 examples:
   - "clarify this"
   - "clearify the last message"
   - "wtf does this mean"
   - "I don't understand what you're asking me to do here"
+  - "j-clearify"
 alias: wtf
 ---
 
 # Clearify — Ambiguity Clarification
 
+This skill is a literal-directory-name duplicate of `skills/clearify/`. It exists so that `/j-clearify` (and `j.j-clearify`) give a guaranteed-unshadowed way to reach the same flow as `/clearify`, even if a host tool's own built-in command of the same name would otherwise shadow or override the bare `/clearify` alias (Claude Code's native skill resolution is a literal-string, directory-name-based match — see `docs/skill-authoring.md`'s "Invocation Convention").
+
+This file is generated/synced by `scripts/generate-j-alias.sh clearify` from `skills/clearify/SKILL.md` — do not hand-edit it; re-run the generator instead to pick up source changes.
+
 > **Note on the `alias: wtf` frontmatter field:** this repo has no runtime mechanism that reads an `alias` key to route slash commands — no existing `SKILL.md` implements one, and `project/configs/workflow.json` has no alias registry. The field here documents the intended relationship only. `/wtf` is made invocable as a working alias by the companion skill folder at `skills/wtf/SKILL.md`, which delegates to these same instructions.
 
 ## Instructions

package/skills/{close-story → j-close-story}/SKILL.md

@@ -1,20 +1,27 @@
 ---
-name: j:close-story
-description: Close a story by verifying all tasks are in terminal state, extracting actual diff stats per task, computing scope divergence flags, and writing closure metadata to task frontmatter.
+name: j.close-story
+description: Polyfill alias of the close-story skill under a collision-safe directory name. Identical behavior to /close-story — Close a story by verifying all tasks are in terminal state, extracting actual diff stats per task, computing scope divergence flags, and writing closure metadata to task frontmatter. Use when the bare /close-story form is shadowed by another tool's own built-in command of the same name.
 keywords:
   - close story
   - close
   - finish story
   - complete story
   - story done
+  - j-close-story
+  - polyfill
 examples:
   - "close story E17_S06"
   - "/close-story E32_S06"
   - "mark story E12_S03 as done"
+  - "j-close-story"
 ---
 
 # close-story — Close a Story
 
+This skill is a literal-directory-name duplicate of `skills/close-story/`. It exists so that `/j-close-story` (and `j.j-close-story`) give a guaranteed-unshadowed way to reach the same flow as `/close-story`, even if a host tool's own built-in command of the same name would otherwise shadow or override the bare `/close-story` alias (Claude Code's native skill resolution is a literal-string, directory-name-based match — see `docs/skill-authoring.md`'s "Invocation Convention").
+
+This file is generated/synced by `scripts/generate-j-alias.sh close-story` from `skills/close-story/SKILL.md` — do not hand-edit it; re-run the generator instead to pick up source changes.
+
 ## Purpose
 
 `/close-story <story-id>` performs the final closure steps for a story:
@@ -38,7 +45,7 @@ examples:
 Run the guard script:
 
 ```bash
-bash skills/close-story/scripts/check-story-closeable.sh <story-id>
+bash skills/j-close-story/scripts/check-story-closeable.sh <story-id>
 ```
 
 - If it exits with code 0 and prints `CLOSEABLE`, continue.
@@ -65,7 +72,7 @@ For **each task ID** listed in the story's `tasks:` frontmatter array:
 
 3. **Run per-task diff stat extraction:**
    ```bash
-   bash skills/close-story/scripts/extract-task-diff-stats.sh <task-id>
+   bash skills/j-close-story/scripts/extract-task-diff-stats.sh <task-id>
    ```
    The script outputs:
    ```
@@ -76,11 +83,11 @@ For **each task ID** listed in the story's `tasks:` frontmatter array:
 
 4. **Write stats to task frontmatter:**
    ```bash
-   bash skills/close-story/scripts/update-task-frontmatter.sh \
+   bash skills/j-close-story/scripts/update-task-frontmatter.sh \
      "project/board/tasks/<task-id>_*.md" \
      actual_files_changed <N>
 
-   bash skills/close-story/scripts/update-task-frontmatter.sh \
+   bash skills/j-close-story/scripts/update-task-frontmatter.sh \
      "project/board/tasks/<task-id>_*.md" \
      actual_lines_delta <N>
    ```
@@ -97,13 +104,13 @@ For **each task ID** listed in the story's `tasks:` frontmatter array:
 
    Run the divergence computation:
    ```bash
-   DIVERGENCE_FLAG=$(bash skills/close-story/scripts/compute-scope-divergence.sh \
+   DIVERGENCE_FLAG=$(bash skills/j-close-story/scripts/compute-scope-divergence.sh \
      "<execution_scope>" <actual_files_changed> <actual_lines_delta>)
    ```
 
    Write the result to task frontmatter:
    ```bash
-   bash skills/close-story/scripts/update-task-frontmatter.sh \
+   bash skills/j-close-story/scripts/update-task-frontmatter.sh \
      "project/board/tasks/<task-id>_*.md" \
      scope_divergence_flag "$DIVERGENCE_FLAG"
    ```
@@ -120,7 +127,7 @@ For **each task ID** listed in the story's `tasks:` frontmatter array:
    frontmatter writes and divergence computation above, check whether this
    task's own work is permanently excluded from the public mirror:
    ```bash
-   bash skills/close-story/scripts/check-privatized.sh <task-id> "project/board/tasks/<task-id>_*.md"
+   bash skills/j-close-story/scripts/check-privatized.sh <task-id> "project/board/tasks/<task-id>_*.md"
    ```
    This is a **static** check (per `templates/SCRUM_BOARD_SCHEMA.md`'s "Static
    vs. Reactive Status Setting" section) — it derives the task's touched-file
@@ -170,7 +177,7 @@ against the story's own direct commits (E51_S03_T03) **before** deciding the
 story's terminal status:
 
 ```bash
-bash skills/close-story/scripts/check-privatized.sh <story-id> "project/board/stories/<story-id>_*.md"
+bash skills/j-close-story/scripts/check-privatized.sh <story-id> "project/board/stories/<story-id>_*.md"
 ```
 
 Passing the story id (`E##_S##`) rather than a task id makes the script's

package/skills/{close-story → j-close-story}/scripts/check-privatized.sh

@@ -1,6 +1,6 @@
 #!/usr/bin/env bash
 # ---------------------------------------------------------------------------
-# skills/close-story/scripts/check-privatized.sh
+# skills/j-close-story/scripts/check-privatized.sh
 #
 # Static (run-independent) `.publicignore` membership check for a single
 # board ticket, invoked by /close-story at both task granularity (Step 2's
@@ -142,7 +142,7 @@ PUBLICIGNORE="$REPO_ROOT/.publicignore"
 [ -f "$PUBLICIGNORE" ] || die ".publicignore not found at $PUBLICIGNORE"
 
 WITH_LOCK_SCRIPT="$REPO_ROOT/scripts/with-lock.sh"
-UPDATE_FRONTMATTER_SCRIPT="$REPO_ROOT/skills/close-story/scripts/update-task-frontmatter.sh"
+UPDATE_FRONTMATTER_SCRIPT="$REPO_ROOT/skills/j-close-story/scripts/update-task-frontmatter.sh"
 EVENTS_FILE="$REPO_ROOT/project/logs/events.json"
 
 [ -f "$WITH_LOCK_SCRIPT" ] || die "expected script not found: $WITH_LOCK_SCRIPT"

package/skills/{close-story → j-close-story}/scripts/check-story-closeable.sh

@@ -22,7 +22,7 @@ usage() {
 }
 
 # Locate the project root relative to this script's location.
-# Script lives at: skills/close-story/scripts/check-story-closeable.sh
+# Script lives at: skills/j-close-story/scripts/check-story-closeable.sh
 # Project root is three levels up (skills/ → repo root).
 SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
 PROJECT_ROOT="$(cd "$SCRIPT_DIR/../../.." && pwd)"

package/skills/{close-story → j-close-story}/scripts/extract-task-diff-stats.sh

@@ -12,7 +12,7 @@
 #
 # For bundle tasks (a single commit covers multiple task IDs), each task that
 # matches the commit receives the full bundle stats — this is the "full credit"
-# attribution model. See skills/close-story/SKILL.md for the rationale.
+# attribution model. See skills/j-close-story/SKILL.md for the rationale.
 #
 # Exit codes:
 #   0 — success (even when no commits are found; outputs 0 values)

package/skills/{commit → j-commit}/SKILL.md

@@ -1,19 +1,26 @@
 ---
-name: j:commit
-description: Commit implemented epic, story, or task work using the EST naming convention. Also handles user-action prerequisites and new-epic boundaries. Use after completing any EST work item.
+name: j.commit
+description: Polyfill alias of the commit skill under a collision-safe directory name. Identical behavior to /commit — Commit implemented epic, story, or task work using the EST naming convention. Also handles user-action prerequisites and new-epic boundaries. Use after completing any EST work item. Use when the bare /commit form is shadowed by another tool's own built-in command of the same name.
 keywords:
   - commit
   - save
   - git commit
   - done
   - push
+  - j-commit
+  - polyfill
 examples:
   - "commit this work"
   - "save my changes"
+  - "j-commit"
 ---
 
 # Commit — Commit Completed Work
 
+This skill is a literal-directory-name duplicate of `skills/commit/`. It exists so that `/j-commit` (and `j.j-commit`) give a guaranteed-unshadowed way to reach the same flow as `/commit`, even if a host tool's own built-in command of the same name would otherwise shadow or override the bare `/commit` alias (Claude Code's native skill resolution is a literal-string, directory-name-based match — see `docs/skill-authoring.md`'s "Invocation Convention").
+
+This file is generated/synced by `scripts/generate-j-alias.sh commit` from `skills/commit/SKILL.md` — do not hand-edit it; re-run the generator instead to pick up source changes.
+
 ## Inline Mode (called by /do for inline-scoped tasks)
 
 When invoked with the `--inline` flag OR when the environment variable `JENGA_COMMIT_INLINE=1` is set, execute inline mode:

package/skills/j-continue/SKILL.md

@@ -0,0 +1,36 @@
+---
+name: j.continue
+description: Polyfill alias of the continue skill under a collision-safe directory name. Identical behavior to /continue — Check project status across PROJECT_SUMMARY.md, epics, and stories to determine what should be done next. Reports "All done!" if everything is complete. Use when the bare /continue form is shadowed by another tool's own built-in command of the same name.
+keywords:
+  - continue
+  - next
+  - proceed
+  - what's next
+  - status
+  - j-continue
+  - polyfill
+examples:
+  - "what should I do next?"
+  - "continue with the project"
+  - "j-continue"
+---
+
+# Continue — Pick Up the Next Work Item
+
+This skill is a literal-directory-name duplicate of `skills/continue/`. It exists so that `/j-continue` (and `j.j-continue`) give a guaranteed-unshadowed way to reach the same flow as `/continue`, even if a host tool's own built-in command of the same name would otherwise shadow or override the bare `/continue` alias (Claude Code's native skill resolution is a literal-string, directory-name-based match — see `docs/skill-authoring.md`'s "Invocation Convention").
+
+This file is generated/synced by `scripts/generate-j-alias.sh continue` from `skills/continue/SKILL.md` — do not hand-edit it; re-run the generator instead to pick up source changes.
+
+## Instructions
+
+1. **Check `project/PROJECT_SUMMARY.md`** — Determine if there is outstanding work at the project level.
+
+2. **Check `project/epics/`** — If the project summary is done, check if any epics have remaining work.
+
+3. **Check `project/stories/`** — If epics are done, check if any stories have remaining work.
+
+   **Important:** Always check story status within an epic even if the epic itself is marked as done.
+
+4. **If everything is complete** — Respond with: "All done! 🎉"
+
+5. **Otherwise** — Begin work on the next incomplete item.

package/skills/{deep-dive → j-deep-dive}/SKILL.md

@@ -1,12 +1,6 @@
 ---
-name: j:deep-dive
-description: >
-  Multi-phase investigation workflow. The scrum-master orchestrates information
-  gathering, interactive brainstorming, critical scrutiny, and solution assessment
-  to produce a refined, well-considered output document. Use when a request needs
-  thorough analysis before committing to a plan. Triggers on phrases like
-  "deep dive", "investigate thoroughly", "think this through properly",
-  "analyze this in depth", or "I want a thorough analysis of".
+name: j.deep-dive
+description: Polyfill alias of the deep-dive skill under a collision-safe directory name. Identical behavior to /deep-dive — >. Use when the bare /deep-dive form is shadowed by another tool's own built-in command of the same name.
 metadata:
   prefered_agent: scrum_master
 keywords:
@@ -14,15 +8,22 @@ keywords:
   - "investigate"
   - "analyze thoroughly"
   - "think through"
+  - j-deep-dive
+  - polyfill
 examples:
   - "deep dive on this idea"
   - "let's think through this properly"
   - "I want a thorough analysis of this feature"
   - "investigate this proposal in depth"
+  - "j-deep-dive"
 ---
 
 # /deep-dive — Deep Investigation Workflow
 
+This skill is a literal-directory-name duplicate of `skills/deep-dive/`. It exists so that `/j-deep-dive` (and `j.j-deep-dive`) give a guaranteed-unshadowed way to reach the same flow as `/deep-dive`, even if a host tool's own built-in command of the same name would otherwise shadow or override the bare `/deep-dive` alias (Claude Code's native skill resolution is a literal-string, directory-name-based match — see `docs/skill-authoring.md`'s "Invocation Convention").
+
+This file is generated/synced by `scripts/generate-j-alias.sh deep-dive` from `skills/deep-dive/SKILL.md` — do not hand-edit it; re-run the generator instead to pick up source changes.
+
 ## Overview
 
 A multi-phase workflow that takes a user's request through structured investigation,

package/skills/{dev-done → j-dev-done}/SKILL.md

@@ -1,18 +1,25 @@
 ---
-name: j:dev-done
-description: Commit the current work and immediately sync it into the .claude/ and .agents/ mirrors. Shortcut that chains /commit followed by /self-sync.
+name: j.dev-done
+description: Polyfill alias of the dev-done skill under a collision-safe directory name. Identical behavior to /dev-done — Commit the current work and immediately sync it into the .claude/ and .agents/ mirrors. Shortcut that chains /commit followed by /self-sync. Use when the bare /dev-done form is shadowed by another tool's own built-in command of the same name.
 keywords:
   - dev done
   - commit and sync
   - commit and mirror
   - done syncing
+  - j-dev-done
+  - polyfill
 examples:
   - "dev-done E42_S04_T01"
   - "commit this and sync the mirrors"
+  - "j-dev-done"
 ---
 
 # Dev-Done — Commit, then Sync the Mirrors
 
+This skill is a literal-directory-name duplicate of `skills/dev-done/`. It exists so that `/j-dev-done` (and `j.j-dev-done`) give a guaranteed-unshadowed way to reach the same flow as `/dev-done`, even if a host tool's own built-in command of the same name would otherwise shadow or override the bare `/dev-done` alias (Claude Code's native skill resolution is a literal-string, directory-name-based match — see `docs/skill-authoring.md`'s "Invocation Convention").
+
+This file is generated/synced by `scripts/generate-j-alias.sh dev-done` from `skills/dev-done/SKILL.md` — do not hand-edit it; re-run the generator instead to pick up source changes.
+
 Chains `/commit <scope-id>` and `/self-sync`, the same "convenience shortcut" pattern `skills/lgtm/SKILL.md`
 uses for `/commit` + `/continue` — applied here to the commit -> mirror-sync sequence instead of the
 commit -> next-task sequence. Useful right after implementing a root-level framework change
@@ -20,7 +27,7 @@ commit -> next-task sequence. Useful right after implementing a root-level frame
 `.agents/` mirrors never sit stale waiting on a manual `/self-sync` call.
 
 The deterministic decision of whether `/commit` halted early (nothing to commit) or completed
-normally lives in `skills/dev-done/scripts/classify-commit-outcome.sh`, not inline here — see that
+normally lives in `skills/j-dev-done/scripts/classify-commit-outcome.sh`, not inline here — see that
 script's header for the exact contract.
 
 ## Instructions
@@ -32,7 +39,7 @@ script's header for the exact contract.
 
 2. Pass the captured output to the classifier script:
    ```
-   skills/dev-done/scripts/classify-commit-outcome.sh <<< "$COMMIT_OUTPUT"
+   skills/j-dev-done/scripts/classify-commit-outcome.sh <<< "$COMMIT_OUTPUT"
    ```
 
 3. If the script exits `1` (HALT): print its stdout — the exact message `No implementation to

package/skills/{dev-done → j-dev-done}/scripts/classify-commit-outcome.sh

@@ -1,6 +1,6 @@
 #!/usr/bin/env bash
 # ---------------------------------------------------------------------------
-# skills/dev-done/scripts/classify-commit-outcome.sh
+# skills/j-dev-done/scripts/classify-commit-outcome.sh
 #
 # Deterministic classifier backing `/dev-done` (story E42_S04, task
 # E42_S04_T01). `/dev-done` chains `/commit <scope-id>` then `/self-sync`,
@@ -8,7 +8,7 @@
 # there was nothing to commit. Per CLAUDE.md's "Skill Implementation
 # Principle — Scripts Over Inline Logic", that halt-vs-proceed check is a
 # deterministic, repeatable text match — it does not belong as inline
-# conditional logic in `skills/dev-done/SKILL.md`, so it lives here instead,
+# conditional logic in `skills/j-dev-done/SKILL.md`, so it lives here instead,
 # the same way `skills/self-sync/SKILL.md` delegates its own filesystem work
 # to `skills/self-sync/scripts/run.js` rather than inlining it.
 #
@@ -39,8 +39,8 @@
 # The text `/commit` produced is passed either as the single argument, or
 # (when no argument is given) read from stdin in full, e.g.:
 #
-#   skills/dev-done/scripts/classify-commit-outcome.sh <<< "$COMMIT_OUTPUT"
-#   printf '%s' "$COMMIT_OUTPUT" | skills/dev-done/scripts/classify-commit-outcome.sh
+#   skills/j-dev-done/scripts/classify-commit-outcome.sh <<< "$COMMIT_OUTPUT"
+#   printf '%s' "$COMMIT_OUTPUT" | skills/j-dev-done/scripts/classify-commit-outcome.sh
 #
 # ---------------------------------------------------------------------------
 # OUTPUT CONTRACT (stdout, single line, nothing else)

package/skills/{distribute → j-distribute}/SKILL.md

@@ -1,6 +1,6 @@
 ---
-name: j:distribute
-description: Distribute Jenga AI framework files from this private monorepo to one or more consuming projects via the local filesystem. Manages release type selection, version bumping, dry-run preview, per-target file copy, and a post-distribution git commit.
+name: j.distribute
+description: Polyfill alias of the distribute skill under a collision-safe directory name. Identical behavior to /distribute — Distribute Jenga AI framework files from this private monorepo to one or more consuming projects via the local filesystem. Manages release type selection, version bumping, dry-run preview, per-target file copy, and a post-distribution git commit. Use when the bare /distribute form is shadowed by another tool's own built-in command of the same name.
 keywords:
   - distribute
   - private distribution
@@ -8,14 +8,21 @@ keywords:
   - framework update
   - version bump
   - distribute to projects
+  - j-distribute
+  - polyfill
 examples:
   - "/distribute"
   - "/distribute /path/to/consuming-project"
   - "/distribute --dry-run"
+  - "j-distribute"
 ---
 
 # Distribute
 
+This skill is a literal-directory-name duplicate of `skills/distribute/`. It exists so that `/j-distribute` (and `j.j-distribute`) give a guaranteed-unshadowed way to reach the same flow as `/distribute`, even if a host tool's own built-in command of the same name would otherwise shadow or override the bare `/distribute` alias (Claude Code's native skill resolution is a literal-string, directory-name-based match — see `docs/skill-authoring.md`'s "Invocation Convention").
+
+This file is generated/synced by `scripts/generate-j-alias.sh distribute` from `skills/distribute/SKILL.md` — do not hand-edit it; re-run the generator instead to pick up source changes.
+
 Copies Jenga AI framework files from this monorepo to all active consuming projects registered in `distribute.config.json`. Manages the full version lifecycle: release type selection, `package.json` version bump, dry-run preview, per-target file copy, and a final git commit of the version bump.
 
 Distinct from `/self-sync` (which mirrors root → in-repo `.claude/.agents/`) and `/mirror-public` (which syncs to the public GitHub repo). Do not call either of those skills from within this flow.
@@ -60,7 +67,7 @@ Read `distribute.config.json`.
 For each entry in `targets`:
 - If `active` is `false`: print `Skipping <name> — inactive.` Do not include it in the distribution run.
 - If the `path` does not exist on disk: print `Skipping <name> — path not found: <path>.` Do not include it in the distribution run.
-- If release type is `amend`: run `bash skills/distribute/scripts/check-version.sh <path>`.
+- If release type is `amend`: run `bash skills/j-distribute/scripts/check-version.sh <path>`.
   - Exit 0 → include the target.
   - Exit 1 → print `Skipping <name> — already up to date.` Do not include it in the distribution run (record it in the final report as "already up to date").
   - Exit 2 → print `Skipping <name> — invalid path or config.` Do not include it.
@@ -87,7 +94,7 @@ On success, read the new version from `package.json` and print: `Version bumped
 For each eligible target (from Step 3), run:
 
 ```bash
-bash skills/distribute/scripts/distribute-changes.sh <project_path> --dry-run
+bash skills/j-distribute/scripts/distribute-changes.sh <project_path> --dry-run
 ```
 
 Display the full output for each target. Then ask the user:
@@ -101,7 +108,7 @@ Wait for confirmation. If the user does not confirm, halt without making any cha
 For each eligible target in sequence:
 
 ```bash
-bash skills/distribute/scripts/distribute-changes.sh <project_path>
+bash skills/j-distribute/scripts/distribute-changes.sh <project_path>
 ```
 
 Record the exit code and any output. If a target fails (non-zero exit), record the failure and continue to the next target. Do not abort the run on partial failure.
@@ -129,7 +136,7 @@ Skip this step for `amend`. Skip this step if no targets succeeded in Step 6.
 Call:
 
 ```bash
-bash skills/distribute/scripts/commit-version-bump.sh
+bash skills/j-distribute/scripts/commit-version-bump.sh
 ```
 
 Report the resulting commit SHA to the user.
@@ -144,15 +151,15 @@ Do not invoke `/self-sync` or `/mirror-public` at any point in this flow. They a
 
 | Script | Purpose |
 |--------|---------|
-| `skills/distribute/scripts/distribute-changes.sh <path> [--dry-run]` | Copy framework files to a single consuming project |
-| `skills/distribute/scripts/commit-version-bump.sh` | Commit the `package.json` version bump |
-| `skills/distribute/scripts/check-version.sh <path>` | Amend mode: exits 0 if target needs update, 1 if up to date, 2 if invalid |
+| `skills/j-distribute/scripts/distribute-changes.sh <path> [--dry-run]` | Copy framework files to a single consuming project |
+| `skills/j-distribute/scripts/commit-version-bump.sh` | Commit the `package.json` version bump |
+| `skills/j-distribute/scripts/check-version.sh <path>` | Amend mode: exits 0 if target needs update, 1 if up to date, 2 if invalid |
 
 ## Config
 
 `distribute.config.json` at the repo root is the registry of consuming projects.
 
-Schema reference: `skills/distribute/CONFIG_SCHEMA.md`
+Schema reference: `skills/j-distribute/CONFIG_SCHEMA.md`
 
 Each target entry:
 

package/skills/{distribute → j-distribute}/scripts/distribute-changes.sh

@@ -45,7 +45,7 @@ dry_run() { echo "[DRY RUN] $*"; }
 
 # ---------------------------------------------------------------------------
 # Resolve monorepo root from this script's location.
-# Script lives at: skills/distribute/scripts/distribute-changes.sh
+# Script lives at: skills/j-distribute/scripts/distribute-changes.sh
 # Repo root is three levels up.
 # ---------------------------------------------------------------------------
 

package/skills/{do → j-do}/SKILL.md

@@ -1,21 +1,28 @@
 ---
-name: j:do
-description: Execute tasks from the scrum board. Reads from project/todo.md, resolves each entry to its full scrum board context, and drives the developer agent through implementation with the correct sender object and communication contract. Loops until all selected tasks are done or the user exits.
+name: j.do
+description: Polyfill alias of the do skill under a collision-safe directory name. Identical behavior to /do — Execute tasks from the scrum board. Reads from project/todo.md, resolves each entry to its full scrum board context, and drives the developer agent through implementation with the correct sender object and communication contract. Loops until all selected tasks are done or the user exits. Use when the bare /do form is shadowed by another tool's own built-in command of the same name.
 keywords:
   - do
   - execute
   - implement
   - work on
   - build
+  - j-do
+  - polyfill
 examples:
   - "implement the login feature"
   - "work on the API endpoint"
+  - "j-do"
 metadata: 
   prefered_agent: developer
 ---
 
 # Do — Execute Scrum Board Tasks
 
+This skill is a literal-directory-name duplicate of `skills/do/`. It exists so that `/j-do` (and `j.j-do`) give a guaranteed-unshadowed way to reach the same flow as `/do`, even if a host tool's own built-in command of the same name would otherwise shadow or override the bare `/do` alias (Claude Code's native skill resolution is a literal-string, directory-name-based match — see `docs/skill-authoring.md`'s "Invocation Convention").
+
+This file is generated/synced by `scripts/generate-j-alias.sh do` from `skills/do/SKILL.md` — do not hand-edit it; re-run the generator instead to pick up source changes.
+
 ## `--trivial` Flag
 
 **Syntax:** `/do <id> --trivial` — a dispatch-time override, distinct from `/todo --trivial` (a creation-time flag documented in `skills/todo/SKILL.md`). Where `/todo --trivial` writes a brand-new task straight to `execution_scope: inline`, `/do <id> --trivial` overrides an **already-existing** task's `execution_scope` — whatever it currently is, including absent (legacy tasks with no execution-scope fields at all) — to `inline` at the moment it's dispatched. See `### 4.1.5. \`--trivial\` Dispatch-Time Override` below for the full mechanics.
@@ -174,7 +181,7 @@ After acquiring the epic lock and before writing the bundle manifest, scan all o
 
       1. **Extract expected files** from the task's frontmatter field `scope_rationale` and from the task's `## Description` section. Use a best-effort prose heuristic: split the text on whitespace and punctuation, then retain any token that either (a) contains a `/` character or (b) matches the pattern `*.*` (a dot surrounded by non-dot characters on both sides, e.g. `SKILL.md`, `foo.json`). Collect all retained tokens into a set called `expected_files`. This is intentionally permissive — false positives (expected files that were never actually changed) are acceptable and produce no report.
 
-      2. **Compute unexpected files**: let `actual_files` = the array stored at `task_changed_files[<task_id>]` in the bundle manifest (from step c.1). Compute `unexpected = actual_files − expected_files` (set difference: files in `actual_files` that have no match in `expected_files`). Matching is case-sensitive and exact against the relative path or the basename of the path — a token like `SKILL.md` matches any actual file whose basename is `SKILL.md` (e.g. `skills/do/SKILL.md`).
+      2. **Compute unexpected files**: let `actual_files` = the array stored at `task_changed_files[<task_id>]` in the bundle manifest (from step c.1). Compute `unexpected = actual_files − expected_files` (set difference: files in `actual_files` that have no match in `expected_files`). Matching is case-sensitive and exact against the relative path or the basename of the path — a token like `SKILL.md` matches any actual file whose basename is `SKILL.md` (e.g. `skills/j-do/SKILL.md`).
 
       3. **If `unexpected` is non-empty**:
          a. Write a Markdown conflict report to `project/queue/conflict-<task_id>.md` with the following structure:
@@ -485,7 +492,7 @@ After the developer agent returns (or after inline execution completes), run the
 
 2. Run `git diff --name-only HEAD~1` to retrieve the list of changed file names (relative paths, one per line).
 
-3. Read the prompt template from `skills/do/assets/intent-vs-diff-prompt.md`. Extract the prompt block (the content between the triple backticks under `## Prompt`).
+3. Read the prompt template from `skills/j-do/assets/intent-vs-diff-prompt.md`. Extract the prompt block (the content between the triple backticks under `## Prompt`).
 
 4. Substitute the placeholders:
    - `{description}` — full text of the task's `## Description` section
@@ -507,7 +514,7 @@ After the developer agent returns (or after inline execution completes), run the
 
 **This check is non-blocking.** It does not change the task's Passed/Failed outcome. It only writes `divergence_flag: true` and emits a warning for human review. Execution continues regardless of the check result.
 
-**Prompt calibration:** The prompt in `skills/do/assets/intent-vs-diff-prompt.md` is tuned to flag only files with zero plausible connection to the stated task. Test files, documentation files, lock files, and clearly implied files are excluded from flagging. See the `## False-Positive Tuning Rationale` section in the prompt template for full details.
+**Prompt calibration:** The prompt in `skills/j-do/assets/intent-vs-diff-prompt.md` is tuned to flag only files with zero plausible connection to the stated task. Test files, documentation files, lock files, and clearly implied files are excluded from flagging. See the `## False-Positive Tuning Rationale` section in the prompt template for full details.
 
 ### 6. Verify documentation
 After the developer completes the task, confirm the following documentation was written:

package/skills/{doc → j-doc}/README.md

@@ -10,7 +10,7 @@
 /doc
 ```
 
-When no target is provided, `/doc` resolves the default target from `skills/doc/assets/path-objectives.yaml`. Today that default is `README.md`.
+When no target is provided, `/doc` resolves the default target from `skills/j-doc/assets/path-objectives.yaml`. Today that default is `README.md`.
 
 Expected flow:
 1. Resolve `README.md`
@@ -32,11 +32,11 @@ Accepted convenience form:
 /doc update: docs/API.md
 ```
 
-Both forms resolve `docs/API.md`, then apply the matching rule from `skills/doc/assets/path-objectives.yaml`.
+Both forms resolve `docs/API.md`, then apply the matching rule from `skills/j-doc/assets/path-objectives.yaml`.
 
 ## Target Resolution and Objective Rules
 
-`skills/doc/assets/path-objectives.yaml` is the source of truth for:
+`skills/j-doc/assets/path-objectives.yaml` is the source of truth for:
 - the default target
 - known target paths
 - each path's documentation objective
@@ -97,7 +97,7 @@ Typical failure modes:
 
 ## Ambiguity Gate
 
-If the resolved target path is not present in `skills/doc/assets/path-objectives.yaml`, `/doc` must not guess.
+If the resolved target path is not present in `skills/j-doc/assets/path-objectives.yaml`, `/doc` must not guess.
 
 It should stop and ask exactly:
 
@@ -149,7 +149,7 @@ Avoid annotations when the work has no documentation impact.
 ## Maintainer Checklist
 
 Before relying on `/doc`, confirm that:
-1. the target path exists in `skills/doc/assets/path-objectives.yaml`, or you are prepared to answer the ambiguity prompt
+1. the target path exists in `skills/j-doc/assets/path-objectives.yaml`, or you are prepared to answer the ambiguity prompt
 2. relevant board items include accurate `docs: [...]` annotations
 3. higher-priority evidence sources are up to date
 4. any existing target file content that should survive regeneration is genuinely still valid

package/skills/{doc → j-doc}/SKILL.md

@@ -1,6 +1,6 @@
 ---
-name: j:doc
-description: Generate or update a documentation file by resolving a target path to a clear documentation objective before writing.
+name: j.doc
+description: Polyfill alias of the doc skill under a collision-safe directory name. Identical behavior to /doc — Generate or update a documentation file by resolving a target path to a clear documentation objective before writing. Use when the bare /doc form is shadowed by another tool's own built-in command of the same name.
 metadata:
   prefered_agent: developer
 keywords:
@@ -9,16 +9,23 @@ keywords:
   - write docs
   - generate docs
   - update docs
+  - j-doc
+  - polyfill
 examples:
   - "/doc"
   - "/doc docs/API.md"
   - "/doc update: docs/API.md"
   - "generate documentation for the CLI"
   - "update the contributing guide"
+  - "j-doc"
 ---
 
 # Doc — Documentation Synthesis and Regeneration
 
+This skill is a literal-directory-name duplicate of `skills/doc/`. It exists so that `/j-doc` (and `j.j-doc`) give a guaranteed-unshadowed way to reach the same flow as `/doc`, even if a host tool's own built-in command of the same name would otherwise shadow or override the bare `/doc` alias (Claude Code's native skill resolution is a literal-string, directory-name-based match — see `docs/skill-authoring.md`'s "Invocation Convention").
+
+This file is generated/synced by `scripts/generate-j-alias.sh doc` from `skills/doc/SKILL.md` — do not hand-edit it; re-run the generator instead to pick up source changes.
+
 ## Input Format
 
 ```text
@@ -32,9 +39,9 @@ examples:
 
 ## Reference Asset
 
-Load `skills/doc/assets/path-objectives.yaml` before resolving the documentation objective. Treat it as the source of truth for the `default_target`, known target paths, and their structural requirements.
+Load `skills/j-doc/assets/path-objectives.yaml` before resolving the documentation objective. Treat it as the source of truth for the `default_target`, known target paths, and their structural requirements.
 
-For extended usage guidance, provenance notes, and board-author tips, see `skills/doc/README.md`.
+For extended usage guidance, provenance notes, and board-author tips, see `skills/j-doc/README.md`.
 
 ## Synthesis Context Contract
 
@@ -73,7 +80,7 @@ If the shared collector from E24_S03 is not yet merged, construct a temporary co
 
 ### 1. Parse the target path
 
-1. Read `default_target` from `skills/doc/assets/path-objectives.yaml`. If it is missing, fall back to `README.md`.
+1. Read `default_target` from `skills/j-doc/assets/path-objectives.yaml`. If it is missing, fall back to `README.md`.
 2. Remove the `/doc` command token from the invocation.
 3. Trim the remaining text.
 4. If the trimmed remainder starts with the exact prefix `update:`, remove that prefix and trim the remainder again.
@@ -88,7 +95,7 @@ Examples:
 
 ### 2. Resolve the objective from the rule table
 
-1. Read `skills/doc/assets/path-objectives.yaml`.
+1. Read `skills/j-doc/assets/path-objectives.yaml`.
 2. Find an entry whose `path` exactly matches `target_path`.
 3. If a match exists, set:
    - `objective` to the entry's `objective`
@@ -113,7 +120,7 @@ If the matched rule includes section guidance, carry it forward as constraints f
 
 ### 4. Ambiguity gate for unknown targets
 
-If `target_path` is not present in `skills/doc/assets/path-objectives.yaml`:
+If `target_path` is not present in `skills/j-doc/assets/path-objectives.yaml`:
 
 - Ask the user exactly: `What should <target_path> document? Please describe the objective.`
 - Do **not** guess the objective.
@@ -145,7 +152,7 @@ If the target file does not exist, keep `existing_intent = null`.
 
 ### 7. Resolve `last_update` provenance before writing
 
-1. Run `python3 skills/doc/scripts/resolve_last_update.py <target_path>` from the repository root.
+1. Run `python3 skills/j-doc/scripts/resolve_last_update.py <target_path>` from the repository root.
 2. The resolver must scan `project/board/epics/`, `project/board/stories/`, and `project/board/tasks/`.
 3. Treat a board item as provenance only when all of the following are true:
    - `status` is exactly `Done` or `Passed`

package/skills/{doc → j-doc}/authoring-notes.md

@@ -4,7 +4,7 @@
 
 `/doc` writes a `last_update` frontmatter field at the top of generated documentation files. That value is derived from completed scrum-board items that explicitly declare they affected the target document.
 
-The resolver is `skills/doc/scripts/resolve_last_update.py`. It scans:
+The resolver is `skills/j-doc/scripts/resolve_last_update.py`. It scans:
 
 - `project/board/epics/`
 - `project/board/stories/`