@fernado03/zoo-flow 0.8.0 → 0.8.2

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@fernado03/zoo-flow",
   "description": "Workflow control plane for Zoo Code.",
-  "version": "0.8.0",
+  "version": "0.8.2",
   "type": "module",
   "bin": {
     "zoo-flow": "bin/zoo-flow.js"

package/templates/full/.roo/skills/engineering/commit-and-document/SKILL.md

@@ -134,6 +134,16 @@ On `yes` → suggest `/update-docs <area>`. On `skip` → continue.
 
 Report: commit hash + message, journal entry path, whether `.gitignore` was updated, and any issue actions taken. Close with: "All of `docs/` is gitignored, so this entry stays local."
 
+## Complete
+
+Call `attempt_completion` with:
+- commit hash (short)
+- journal entry path
+- status (complete / blocked with reason)
+- recommended next command
+
+Do NOT use `ask_followup_question` or write results as plain text without calling the tool.
+
 ## Context economy
 
 Before broad reads, locate relevant files/symbols with `list_files`, `search_files`, or `codebase_search`.

package/templates/full/.roo/skills/engineering/grill-with-docs/SKILL.md

@@ -38,3 +38,13 @@ Do not re-read unchanged files; use prior findings unless the file changed.
 - Update `CONTEXT.md` immediately for resolved terms.
 - Keep `CONTEXT.md` glossary-only; no impl/spec notes.
 - Offer ADR only when hard to reverse + surprising + real trade-off; use `ADR-FORMAT.md`.
+
+## Complete
+
+Call `attempt_completion` with:
+- questions resolved (count)
+- docs updated (CONTEXT.md, ADRs created/updated)
+- status (complete / blocked with reason)
+- recommended next command
+
+Do NOT use `ask_followup_question` or write results as plain text without calling the tool.

package/templates/full/.roo/skills/engineering/improve-codebase-architecture/SKILL.md

@@ -53,3 +53,13 @@ Use searches to identify dependency/call patterns before reading full modules. R
 3. If term sharpened, update `CONTEXT.md` immediately.
 4. Durable rejected reason useful later → offer ADR.
 5. Interface options requested → run interface-design workflow.
+
+## Complete
+
+Call `attempt_completion` with:
+- report location (`{tmpdir}/architecture-review-{timestamp}.html`)
+- candidates found (count)
+- status (complete / blocked with reason)
+- recommended next command
+
+Do NOT use `ask_followup_question` or write results as plain text without calling the tool.

package/templates/full/.roo/skills/engineering/prototype/SKILL.md

@@ -35,3 +35,13 @@ Do not re-read unchanged files; use prior findings unless the file changed.
 7. No polish: no tests, minimal errors, no abstractions.
 8. Surface full relevant state after each action/variant switch.
 9. Done → capture answer in commit/ADR/issue/`NOTES.md`; delete or fold into real code.
+
+## Complete
+
+Call `attempt_completion` with:
+- question answered
+- prototype location (`.scratch/prototypes/<slug>/` or real module path)
+- outcome (absorbed / discarded / needs decision)
+- recommended next command
+
+Do NOT use `ask_followup_question` or write results as plain text without calling the tool.

package/templates/full/.roo/skills/engineering/review/SKILL.md

@@ -97,9 +97,16 @@ End with exactly one result line:
 - `Review result: changes requested`
 - `Review result: blocked`
 
-## 6. Save
+## 6. Save and complete
 
-Write the full review (findings, axes, result) to `.scratch/reviews/<date>/review-<slug>.md`. Reference this file path in `attempt_completion` so the orchestrator can read and present it.
+Write the full review (findings, axes, result) to `.scratch/reviews/<date>/review-<slug>.md`.
+
+Call `attempt_completion` with:
+- file path where review was saved
+- brief result line (approve / approve with nits / changes requested / blocked)
+- recommended next command
+
+Do NOT use `ask_followup_question` or write results as plain text without calling the tool.
 
 ## Recommended next command
 

package/templates/full/.roo/skills/engineering/tdd/SKILL.md

@@ -52,6 +52,16 @@ Checklist per cycle:
 
 After green, suggest `/verify`, then `/review`, then `/commit-and-document` for non-trivial work. Do not auto-launch follow-up commands.
 
+## Complete
+
+Call `attempt_completion` with:
+- what was implemented (behaviours, interfaces)
+- tests written (count, pass/fail)
+- status (complete / blocked with reason)
+- recommended next command
+
+Do NOT use `ask_followup_question` or write results as plain text without calling the tool.
+
 ## Context economy
 
 Before broad reads, locate relevant files/symbols with `list_files`, `search_files`, or `codebase_search`.

package/templates/full/.roo/skills/engineering/to-issues/SKILL.md

@@ -43,3 +43,12 @@ Issue tracker + label vocabulary should exist; run `/setup-matt-pocock-skills` i
 ```
 
 If no blockers: `None - can start immediately`.
+
+## Complete
+
+Call `attempt_completion` with:
+- issues created (count, tracker URL or `.scratch/{feature-slug}/issues/`)
+- status (published / blocked with reason)
+- recommended next command
+
+Do NOT use `ask_followup_question` or write results as plain text without calling the tool.

package/templates/full/.roo/skills/engineering/to-prd/SKILL.md

@@ -55,3 +55,12 @@ RULE: Do not interview user. Synthesize current context.
 
 {other notes}
 ```
+
+## Complete
+
+Call `attempt_completion` with:
+- PRD location (issue tracker URL or `.scratch/{feature-slug}/PRD.md`)
+- status (published / blocked with reason)
+- recommended next command
+
+Do NOT use `ask_followup_question` or write results as plain text without calling the tool.

package/templates/full/.roo/skills/engineering/triage/SKILL.md

@@ -77,3 +77,12 @@ Show counts + one-line summaries. Let maintainer pick.
 ```
 
 Rules: capture resolved info; ask specific/actionable questions; on resume, do not re-ask answered questions.
+
+## Complete
+
+Call `attempt_completion` with:
+- issues triaged (count, outcomes applied)
+- status (complete / blocked with reason)
+- recommended next command
+
+Do NOT use `ask_followup_question` or write results as plain text without calling the tool.

package/templates/full/.roo/skills/engineering/tweak/SKILL.md

@@ -17,6 +17,15 @@ Use for small known fixes.
 8. For R3+ risk, suggest `/verify` or `/review` before commit. Otherwise offer `/commit-and-document` only after user satisfied.
 9. Do not auto-launch follow-up commands.
 
+## Complete
+
+Call `attempt_completion` with:
+- what was changed (file paths, line ranges)
+- status (complete / blocked with reason)
+- recommended next command
+
+Do NOT use `ask_followup_question` or write results as plain text without calling the tool.
+
 ## Context economy
 
 Before broad reads, locate relevant files/symbols with `list_files`, `search_files`, or `codebase_search`.

package/templates/full/.roo/skills/engineering/update-docs/SKILL.md

@@ -64,3 +64,13 @@ Do not re-read unchanged files; use prior findings unless the file changed.
 ## 7. Recommend next step
 
 Recommend one: `/explore` (still unclear), `/feature` (plan emerged), `/refactor` (tangled-but-working code), `/fix` (bug found), `/commit-and-document` (done). Do not auto-run.
+
+## Complete
+
+Call `attempt_completion` with:
+- docs updated (file paths)
+- what changed (summary)
+- status (complete / blocked with reason)
+- recommended next command
+
+Do NOT use `ask_followup_question` or write results as plain text without calling the tool.

package/templates/full/.roo/skills/engineering/verify/SKILL.md

@@ -78,3 +78,14 @@ Reason: no verification command found
 ```
 
 Do not auto-launch any follow-up command.
+
+## 6. Complete
+
+Write the full verification report to `.scratch/verify/<date>/verify-<slug>.md`.
+
+Call `attempt_completion` with:
+- file path where report was saved
+- brief status (pass/fail/partial/blocked)
+- recommended next command
+
+Do NOT use `ask_followup_question` or write results as plain text without calling the tool.

package/templates/full/.roo/skills/productivity/grill-me/SKILL.md

@@ -11,3 +11,13 @@ description: Interview the user relentlessly about a plan or design until reachi
 4. Ask one question at a time.
 5. Include recommended answer.
 6. Inspect code instead of asking when code can answer.
+
+## Complete
+
+Call `attempt_completion` with:
+- decision tree branches resolved (count)
+- key decisions made (summary)
+- status (complete / blocked with reason)
+- recommended next command
+
+Do NOT use `ask_followup_question` or write results as plain text without calling the tool.

package/templates/full/.roo/skills/productivity/handoff/SKILL.md

@@ -12,3 +12,11 @@ argument-hint: "What will the next session be used for?"
 4. Include suggested skills section.
 5. Reference artifacts by path/URL; do not duplicate.
 6. Redact secrets/API keys/passwords/PII.
+
+## Complete
+
+Call `attempt_completion` with:
+- handoff file path (OS temp dir)
+- status (complete / blocked with reason)
+
+Do NOT use `ask_followup_question` or write results as plain text without calling the tool.

package/templates/full/.roo/skills/productivity/teach/SKILL.md

@@ -105,3 +105,15 @@ Default: attempt an answer, then route to a high-reputation community from `RESO
 ## `NOTES.md`
 
 The user will sometimes express preferences of how they want to be taught, or things you should keep in mind. This is the place to record those preferences, so you can refer back to them when designing lessons or working with the user.
+
+## Complete
+
+When the user ends the teaching session or says "done" / "stop teaching":
+
+Call `attempt_completion` with:
+- lessons created (count, paths)
+- mission status (created / updated)
+- learning records updated (count)
+- status (session complete / paused)
+
+Do NOT use `ask_followup_question` or write results as plain text without calling the tool.

package/templates/full/.roo/skills/productivity/write-a-skill/SKILL.md

@@ -50,3 +50,12 @@ Add when: deterministic op; repeated code; explicit error handling needed.
 - [ ] Terminology consistent.
 - [ ] Examples concrete.
 - [ ] References one level deep.
+
+## Complete
+
+Call `attempt_completion` with:
+- skill created (name, path)
+- files written (SKILL.md, references, scripts)
+- status (complete / blocked with reason)
+
+Do NOT use `ask_followup_question` or write results as plain text without calling the tool.