Agent skill
planning
Planning workflows for clarifying ambiguous build requests, running spec/work-package delivery, and managing Linear lifecycle transitions.
Install this agent skill to your Project
npx add-skill https://github.com/bout3fiddy/agents/tree/main/skills/planning
Metadata
Additional technical details for this skill
- id
- planning.core
- version
- 1
- priority
- 85
- task types
-
[ "planning", "plan", "spec", "linear", "workpackage", "clarify" ] - load strategy
- progressive
- trigger phrases
-
[ "planning", "spec", "work package", "linear issue", "scope ambiguity", "requirements clarification", "project lifecycle", "workpackage", "Linear" ] - activation policy
- both
- workflow triggers
-
[ "linear_issue_context_detected", "workpackage_path_detected", "planning_request_detected" ] - operation contracts
-
{ "linear_transition": { "required_steps": [ "read_issue", "map_lifecycle_state", "apply_transition", "verify_write", "post_transition_comment" ], "forbidden_actions": [ "write_without_readback", "update_without_transition_reason" ], "required_output_fields": [ "state_change", "work_summary", "validation", "follow_ups", "owner_next_step" ] }, "clarification_gate": { "required_steps": [ "ask_minimum_questions", "confirm_assumptions", "restate_requirements" ], "forbidden_actions": [ "directional_implementation_without_constraints" ], "required_output_fields": [ "open_questions_or_assumptions", "agreed_scope", "success_criteria" ] }, "workpackage_execution": { "required_steps": [ "read_overview", "select_target_wp", "honor_local_directives", "sync_status_and_evidence" ], "forbidden_actions": [ "skip_overview", "ignore_approval_gate" ], "required_output_fields": [ "target_wp", "status_update", "proof_pointer", "next_action" ] } }
SKILL.md
Planning (Clarify + Spec + Track)
Use this skill when work is underspecified, needs a spec/work-package-first plan, or should be captured/tracked in Linear.
Scope & routing
- Use for planning/spec/clarification requests, work-package orchestration, or when the user explicitly asks for a plan.
- If the primary task is creating/updating a skill, prefer skill-creator; use planning only for a plan-only response.
- If the request shifts to implementation/build work, hand off to
codingafter clarifying scope and locking assumptions. - When opening references, use full repo paths like
skills/planning/references/...(notreferences/...). If a reference read fails, retry once with the full path. - If a trigger clearly matches, open the referenced file before drafting the plan/spec. If you need 1-2 clarifying questions first, ask them before opening the ref.
- If a word/length limit is given, keep it short and minimize extra reads.
- Treat all Linear status flow requests as planning work: load
skills/planning/references/linear-mcp-ops.md, map lifecycle semantics to team statuses, and capture rationale/comments for each transition.
Routing order (metadata-first)
- Workpackage execution or continuation (
docs/workpackages/...,docs/review/workpackages_*, or explicit workpackage execution directive). - Explicit Linear lifecycle or transition operation.
- Implementation intent with missing must-have scope/acceptance constraints.
- Spec-first iterative planning without explicit workpackage execution.
- Planning fallback to clarification.
Conflict rule: if workpackage and Linear cues appear together, run workpackage routing first; keep Linear context checks read-only unless transition actions are explicitly requested.
Routing note: trigger_phrases are lexical boosters only and must not be treated as literal match gates.
If workpackage hints are present, follow skills/planning/references/spec-driven-iterative-builder.md and keep docs/specs/* and related work-package files synchronized.
References
skills/planning/references/ask-questions-if-underspecified.md- minimal clarifying questions workflow with fast trigger testskills/planning/references/spec-driven-iterative-builder.md- spec-first iterative delivery with work-package integration modeskills/planning/references/linear-mcp-ops.md- Linear MCP operations and brainstorming capture
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
design
Frontend design curation skill for UI critique, motion storyboarding, and DialKit tuning. Use when the user asks for interface feedback, animation sequencing, or interactive design-control setup.
coding
Core engineering skill for implementation, bug fixes, refactors, and technical reviews with mandatory smell guardrails and targeted domain reference routing.
housekeeping
Repository housekeeping workflows for AGENTS/CLAUDE architecture, progressive disclosure, and migration of legacy monolithic instruction files.
skill-creator
Create, update, or install skills (including planning/specs and edits to skills/*) using our repo workflow (uv + skills-ref validation, lean SKILL.md, references/ for detail, and sync via bin/sync.sh).
edit-article
Edit and improve articles by restructuring sections, improving clarity, and tightening prose. Use when user wants to edit, revise, or improve an article draft.
handoff
Compact the current conversation into a handoff document for another agent to pick up.
Didn't find tool you were looking for?