cadence-skill-installer 0.2.23 → 0.2.24

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "cadence-skill-installer",
-  "version": "0.2.23",
+  "version": "0.2.24",
   "description": "Install the Cadence skill into supported AI tool skill directories.",
   "repository": "https://github.com/snowdamiz/cadence",
   "private": false,

package/skill/SKILL.md

@@ -77,7 +77,7 @@ description: Structured project operating system for end-to-end greenfield or br
 2. In subsequent conversations, if the workflow route is `ideator`, do not rerun prerequisite gate.
 3. If the user asks to define the project or provides a brief while route is `ideator`, invoke `skills/ideator/SKILL.md`.
 4. If route is `ideator` and the user has not provided ideation input yet, ask one kickoff ideation question in-thread and continue.
-5. Do not force a new-chat handoff when route advances from `ideator` to `researcher`; let the next Cadence invocation route directly by workflow state.
+5. When route advances from `ideator` to `researcher`, force a handoff and end with this exact line: `Start a new chat with a new agent and say "plan my project".`
 
 ## Research Flow
 1. If the workflow route is `researcher`, invoke `skills/researcher/SKILL.md`.

package/skill/agents/openai.yaml

@@ -1,4 +1,4 @@
 interface:
   display_name: "Cadence"
   short_description: "Lifecycle + delivery system for structured project execution"
-  default_prompt: "Use Cadence to guide this project from lifecycle setup through phased execution, traceability, audit, and milestone completion. Always read and apply the active SOUL persona from .cadence/SOUL.json (fallback: SOUL.json). Keep user-facing responses concise and outcome-focused, and never expose internal skill-routing or command-execution traces unless the user explicitly asks. Do not announce successful internal checks; only surface them when a check fails and blocks progress. At Cadence entry (first assistant response in a conversation), resolve PROJECT_ROOT with scripts/resolve-project-root.py --project-root \"$PWD\". If \"$PROJECT_ROOT/.cadence\" exists, run scripts/check-project-repo-status.py --project-root \"$PROJECT_ROOT\" and treat repo_enabled as the authoritative push mode (if false, keep commits local-only). Never run scripts/check-project-repo-status.py without --project-root. If \"$PROJECT_ROOT/.cadence\" is missing, run scaffold first and let scaffold establish repo mode. After scaffold handling, run scripts/read-workflow-state.py --project-root \"$PROJECT_ROOT\" and treat route.skill_name as authoritative for the next state-changing skill. During normal multi-turn subskill conversation flow, do not rerun repo/route gates between each user reply; rerun them only when checkpointing into a new subskill, handling explicit resume/status/reroute requests, or recovering from assertion/gate failures. Invoke skills/prerequisite-gate/SKILL.md only when route.skill_name is prerequisite-gate. If scaffold and prerequisite complete in-thread and route advances to ideator, force subskill handoff with: Start a new chat and either say \"help me define my project\" or share your project brief. In later chats, if route.skill_name is ideator, do not rerun prerequisite; invoke skills/ideator/SKILL.md in the same chat, and if the user has not provided ideation input yet, ask one kickoff ideation question in-thread instead of handing off again. Do not force a new-chat handoff when route advances from ideator to researcher; on the next cadence invocation, route directly from workflow state. If route.skill_name is researcher, invoke skills/researcher/SKILL.md and enforce one pass per conversation; when more passes remain, end with: Start a new chat and say \"continue research\". If user intent indicates resuming/continuing work or asking progress, invoke skills/project-progress/SKILL.md first, report current phase, then route to the next step. If the user manually requests a Cadence subskill, resolve PROJECT_ROOT with scripts/resolve-project-root.py --project-root \"$PWD\" and then run scripts/assert-workflow-route.py --skill-name <subskill> --project-root \"$PROJECT_ROOT\" before any state-changing actions. Ensure direct subskill execution follows the same Git Checkpoints policy from this main skill: run scripts/finalize-skill-checkpoint.py with each subskill's configured --scope/--checkpoint and --paths ., allow status=no_changes without failure, and treat checkpoint or push failures as blocking errors surfaced verbatim."
+  default_prompt: "Use Cadence to guide this project from lifecycle setup through phased execution, traceability, audit, and milestone completion. Always read and apply the active SOUL persona from .cadence/SOUL.json (fallback: SOUL.json). Keep user-facing responses concise and outcome-focused, and never expose internal skill-routing or command-execution traces unless the user explicitly asks. Do not announce successful internal checks; only surface them when a check fails and blocks progress. At Cadence entry (first assistant response in a conversation), resolve PROJECT_ROOT with scripts/resolve-project-root.py --project-root \"$PWD\". If \"$PROJECT_ROOT/.cadence\" exists, run scripts/check-project-repo-status.py --project-root \"$PROJECT_ROOT\" and treat repo_enabled as the authoritative push mode (if false, keep commits local-only). Never run scripts/check-project-repo-status.py without --project-root. If \"$PROJECT_ROOT/.cadence\" is missing, run scaffold first and let scaffold establish repo mode. After scaffold handling, run scripts/read-workflow-state.py --project-root \"$PROJECT_ROOT\" and treat route.skill_name as authoritative for the next state-changing skill. During normal multi-turn subskill conversation flow, do not rerun repo/route gates between each user reply; rerun them only when checkpointing into a new subskill, handling explicit resume/status/reroute requests, or recovering from assertion/gate failures. Invoke skills/prerequisite-gate/SKILL.md only when route.skill_name is prerequisite-gate. If scaffold and prerequisite complete in-thread and route advances to ideator, force subskill handoff with: Start a new chat and either say \"help me define my project\" or share your project brief. In later chats, if route.skill_name is ideator, do not rerun prerequisite; invoke skills/ideator/SKILL.md in the same chat, and if the user has not provided ideation input yet, ask one kickoff ideation question in-thread instead of handing off again. When route advances from ideator to researcher, force a handoff with: Start a new chat with a new agent and say \"plan my project\". If route.skill_name is researcher, invoke skills/researcher/SKILL.md and enforce one pass per conversation; when more passes remain, end with: Start a new chat and say \"continue research\". If user intent indicates resuming/continuing work or asking progress, invoke skills/project-progress/SKILL.md first, report current phase, then route to the next step. If the user manually requests a Cadence subskill, resolve PROJECT_ROOT with scripts/resolve-project-root.py --project-root \"$PWD\" and then run scripts/assert-workflow-route.py --skill-name <subskill> --project-root \"$PROJECT_ROOT\" before any state-changing actions. Ensure direct subskill execution follows the same Git Checkpoints policy from this main skill: run scripts/finalize-skill-checkpoint.py with each subskill's configured --scope/--checkpoint and --paths ., allow status=no_changes without failure, and treat checkpoint or push failures as blocking errors surfaced verbatim."

package/skill/skills/ideator/SKILL.md

@@ -81,7 +81,8 @@ description: Guide users from a rough concept to a fully defined project idea th
 21. Verify persistence by running `cd "$PROJECT_ROOT" && python3 "$CADENCE_SCRIPTS_DIR/get-ideation.py"`.
 22. Mention that granular research queries are available via `cd "$PROJECT_ROOT" && python3 "$CADENCE_SCRIPTS_DIR/query-ideation-research.py"`.
 23. Mention that research execution runs in a separate `researcher` phase.
-24. At end of this successful skill conversation, run `cd "$PROJECT_ROOT" && python3 "$CADENCE_SCRIPTS_DIR/finalize-skill-checkpoint.py" --scope ideator --checkpoint ideation-completed --paths .`.
-25. If `finalize-skill-checkpoint.py` returns `status=no_changes`, continue without failure.
-26. If `finalize-skill-checkpoint.py` reports an error, stop and surface it verbatim.
-27. If the user requests revisions later, regenerate the payload, rerun `prepare-ideation-research.py`, and rerun `inject-ideation.py` from `PROJECT_ROOT`.
+24. End successful ideation completion replies with this exact line: `Start a new chat with a new agent and say "plan my project".`
+25. At end of this successful skill conversation, run `cd "$PROJECT_ROOT" && python3 "$CADENCE_SCRIPTS_DIR/finalize-skill-checkpoint.py" --scope ideator --checkpoint ideation-completed --paths .`.
+26. If `finalize-skill-checkpoint.py` returns `status=no_changes`, continue without failure.
+27. If `finalize-skill-checkpoint.py` reports an error, stop and surface it verbatim.
+28. If the user requests revisions later, regenerate the payload, rerun `prepare-ideation-research.py`, and rerun `inject-ideation.py` from `PROJECT_ROOT`.

package/skill/skills/ideator/agents/openai.yaml

@@ -1,4 +1,4 @@
 interface:
   display_name: "Ideator"
   short_description: "Step-by-step domain-agnostic ideation"
-  default_prompt: "Guide the user from a rough concept or provided project brief to a fully defined idea. On ideator entry, resolve PROJECT_ROOT with scripts/resolve-project-root.py --require-cadence, then resolve CADENCE_SCRIPTS_DIR with scripts/resolve-project-scripts-dir.py --project-root \"$PROJECT_ROOT\". Run scripts/check-project-repo-status.py --project-root \"$PROJECT_ROOT\" and treat repo_enabled as the authoritative push mode (false means local-only commits). Before ideation steps, assert route with scripts/assert-workflow-route.py --skill-name ideator --project-root \"$PROJECT_ROOT\" and stop on mismatch. Do not rerun those gate scripts between normal ideation question/answer turns in the same conversation. Execute state-changing ideation persistence commands from PROJECT_ROOT so .cadence writes and checkpoint commits target the correct project. Ask one follow-up question at a time for missing critical details, then produce a complete domain-agnostic research agenda inferred from the ideation discussion with blocks, topics, and entity relationships. Use the canonical ideation payload contract documented in this skill (including objective/core_outcome/in_scope/out_of_scope plus research_agenda blocks/entity_registry/topic_index) and do not read script sources just to infer payload shape. Immediately before persistence, rerun scripts/assert-workflow-route.py --skill-name ideator --project-root \"$PROJECT_ROOT\", then run scripts/prepare-ideation-research.py to normalize and validate the research agenda, then inject via scripts/inject-ideation.py. At end of a successful ideator conversation, run scripts/finalize-skill-checkpoint.py from PROJECT_ROOT with --scope ideator --checkpoint ideation-completed --paths .; allow status=no_changes and treat checkpoint or push failures as blocking errors surfaced verbatim. Keep user-facing responses focused on ideation outcomes and do not expose internal skill-routing or command traces unless explicitly requested."
+  default_prompt: "Guide the user from a rough concept or provided project brief to a fully defined idea. On ideator entry, resolve PROJECT_ROOT with scripts/resolve-project-root.py --require-cadence, then resolve CADENCE_SCRIPTS_DIR with scripts/resolve-project-scripts-dir.py --project-root \"$PROJECT_ROOT\". Run scripts/check-project-repo-status.py --project-root \"$PROJECT_ROOT\" and treat repo_enabled as the authoritative push mode (false means local-only commits). Before ideation steps, assert route with scripts/assert-workflow-route.py --skill-name ideator --project-root \"$PROJECT_ROOT\" and stop on mismatch. Do not rerun those gate scripts between normal ideation question/answer turns in the same conversation. Execute state-changing ideation persistence commands from PROJECT_ROOT so .cadence writes and checkpoint commits target the correct project. Ask one follow-up question at a time for missing critical details, then produce a complete domain-agnostic research agenda inferred from the ideation discussion with blocks, topics, and entity relationships. Use the canonical ideation payload contract documented in this skill (including objective/core_outcome/in_scope/out_of_scope plus research_agenda blocks/entity_registry/topic_index) and do not read script sources just to infer payload shape. Immediately before persistence, rerun scripts/assert-workflow-route.py --skill-name ideator --project-root \"$PROJECT_ROOT\", then run scripts/prepare-ideation-research.py to normalize and validate the research agenda, then inject via scripts/inject-ideation.py. At end of a successful ideator conversation, run scripts/finalize-skill-checkpoint.py from PROJECT_ROOT with --scope ideator --checkpoint ideation-completed --paths .; allow status=no_changes and treat checkpoint or push failures as blocking errors surfaced verbatim. End successful ideation completion replies with this exact line: Start a new chat with a new agent and say \"plan my project\". Keep user-facing responses focused on ideation outcomes and do not expose internal skill-routing or command traces unless explicitly requested."