grinrus/tasks-new
skills/tasks-new/SKILL.md
Derives or refines tasklist items from PRD and plan artifacts. Use when tasklist stage prepares implementation-ready work items. Do not use when the request is plan authoring in `plan-new` or loop execution in `implement`.
$ install --global
skillsauthnpx skillsauth add grinrus/ai_driven_dev tasks-newInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 22, 2026, 8:38 PM189.2s3 files scanned
SKILL.md
- name:
- tasks-new
- description:
- Derives or refines tasklist items from PRD and plan artifacts. Use when tasklist stage prepares implementation-ready work items. Do not use when the request is plan authoring in `plan-new` or loop execution in `implement`.
- argument-hint:
- $1 [note...]
- lang:
- en
- prompt_version:
- 1.1.25
- source_version:
- 1.1.25
- model:
- inherit
- disable-model-invocation:
- true
- user-invocable:
- true
Follow feature-dev-aidd:aidd-core.
Steps
- Inputs: resolve active feature and verify PRD/plan artifacts needed for tasklist generation.
- Preflight: set active stage
tasklistand active feature. - Orchestration is bounded: run
python3 ${CLAUDE_PLUGIN_ROOT}/skills/tasks-new/runtime/tasks_new.py --ticket <ticket>, then gate PRD readiness withpython3 ${CLAUDE_PLUGIN_ROOT}/skills/aidd-flow-state/runtime/prd_check.py. - Use the existing rolling context pack as input evidence; do not invoke standalone context-pack builder scripts from this stage.
- Run subagent
feature-dev-aidd:tasklist-refineronly when upstream prerequisites are already present and the current failure mode is repairable tasklist structure. First action: read the rolling context pack. - Postflight: validate via
python3 ${CLAUDE_PLUGIN_ROOT}/skills/aidd-flow-state/runtime/tasklist_check.py. - Retry policy: allow at most one bounded retry, and only when validator issues are categorized as
repairable_structure. Do not retry forupstream_blocker, env/policy errors, or truth/advisory warnings. - Forbidden recovery paths in this stage: creating missing upstream artifacts, launching ad hoc repair interviews, reading runtime source files for self-diagnosis, or looping
tasks_new.py -> tasklist_check.py -> manual editswithout new evidence. - Ready path: return
/feature-dev-aidd:implement <ticket>only whentasklist_check.pypasses and the next iteration is implementation-ready. - Pending or blocked path: return the output contract with structured tasklist gaps and a canonical next action on
review-specortasks-new; stop after the bounded retry budget is exhausted.
Command contracts
python3 ${CLAUDE_PLUGIN_ROOT}/skills/tasks-new/runtime/tasks_new.py
- When to run: as canonical tasklist stage entrypoint before implement phase.
- Inputs:
--ticket <ticket>and current PRD/plan artifacts. - Outputs: normalized tasklist structure and structured validator issue set.
- Failure mode: non-zero exit when upstream blockers exist or tasklist contract checks fail.
- Next action: rerun only after fixing upstream readiness blockers, or do one bounded retry for
repairable_structure.
Notes
- Planning stage:
AIDD:ACTIONS_LOG: n/a.
Additional resources
- Tasklist template source: templates/tasklist.template.md (when: generating or normalizing tasklist sections; why: keep iteration/handoff structure aligned with canonical template).
Related Skills
grinrus/status
testing
VerifiedTrustedCommunity
Generates consolidated ticket status summary and key artifact pointers. Use when checking current stage state or handoff readiness. Do not use when the request is diagnostics/inventory from `aidd-observability` or flow-state mutation via `aidd-flow-state`.
5SKILL.mdUpdated Apr 5, 2026
grinrus/spec-interview
testing
VerifiedTrustedCommunity
Collects missing spec inputs and synchronizes answers into `spec.yaml`. Use when review-spec leaves unresolved specification fields. Do not use when the request is readiness gating in `review-spec` or task derivation in `tasks-new`.
5SKILL.mdUpdated Apr 5, 2026
grinrus/review
testing
VerifiedTrustedCommunity
Runs review-stage validation for scope changes, findings, and follow-up task derivation. Use when review stage needs verdict and handoff tasks. Do not use when the request is direct implementation execution in `implement` or QA validation in `qa`.
5SKILL.mdUpdated Apr 5, 2026
grinrus/review-spec
tools
VerifiedTrustedCommunity
Reviews plan and PRD, then gates readiness for task derivation. Use when plan and PRD artifacts are ready for downstream planning readiness. Do not use when the request is plan authoring in `plan-new` or task derivation in `tasks-new`.
5SKILL.mdUpdated Apr 5, 2026