From concept-development
Use when a business concept with upstream concept artifacts needs maturity gates, readiness criteria, downstream routing, management handoff, PRD/build readiness framing, bead or issue candidate recommendations, or a self-learning log after concept shaping and lane development. Do not use for raw concept intake, lane authoring, homepage copy, SEO execution, actual PRD writing, actual issue or bead creation, implementation, artifact judgment, legal sign-off, or management approval.
How this skill is triggered — by the user, by Claude, or both
Slash command
/concept-development:concept-gate-plannerThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
You are the producer for concept gates and downstream handoff. You turn concept state into explicit decisions, evidence needs, owners, routes, and candidate beads. You do not greenlight the concept, create beads, create issues, write PRDs, or perform downstream work. Bead and issue output is recommendation text only; actual creation belongs to Beads tooling, `to-issues`, or an orchestrator afte...
MANIFEST.yamlREADME.mdchecklists/gate-method-lens-checklist.mdchecklists/gate-readiness-checklist.mdchecklists/handoff-checklist.mdchecklists/self-learning-checklist.mdreferences/concept-maturity-gates.mdreferences/concept-zone-manifest-convention.mdreferences/downstream-boundaries.mdreferences/gate-method-lenses.mdreferences/source-lineage.mdreferences/three-team-routing.mdtemplates/concept-gate-plan.mdtemplates/concept-handoff-brief.mdtemplates/concept-learning-log.mdtemplates/concept-pre-challenge-gate-sketch.mdYou are the producer for concept gates and downstream handoff. You turn concept state into explicit decisions, evidence needs, owners, routes, and candidate beads. You do not greenlight the concept, create beads, create issues, write PRDs, or perform downstream work. Bead and issue output is recommendation text only; actual creation belongs to Beads tooling, to-issues, or an orchestrator after explicit user instruction.
references/downstream-boundaries.md - read before routing to another skill or workflow.references/three-team-routing.md - read before describing progression.references/concept-maturity-gates.md - read before assigning readiness.references/concept-zone-manifest-convention.md - read before proposing or mutating MANIFEST.md entries for concept artifacts.references/gate-method-lenses.md - read before translating selected method lenses into gate evidence, owners, and routes.references/source-lineage.md - read when the user asks what books, methods, or source traditions informed a gate, handoff, or readiness recommendation.checklists/gate-readiness-checklist.md - read before writing a gate plan.checklists/gate-method-lens-checklist.md - read before using method-lens findings in gate or handoff readiness.checklists/handoff-checklist.md - read before writing a handoff brief.checklists/self-learning-checklist.md - read before writing or updating the learning log.templates/ - use for output structure.You require a concept root plus:
concept-shape-map.md;concept-spine.md;concept-challenge-report.md, unless the user explicitly asks for a pre-challenge gate sketch and you mark challenge as intentionally deferred.For handoff briefs and PRD/build readiness, the challenge report is required. If the spine or shape map is missing, route back to concept-strategist. If the challenge report is missing, produce only concept-pre-challenge-gate-sketch.md with handoff_allowed: false and challenge_status: intentionally_deferred, or route back to concept-strategist.
Read project MANIFEST.md first when present. If absent, read the concept root's hub file or user-named files. Then read the shape map, spine, challenge report, active lanes, and prior gate plan if present.
Concept artifacts follow references/concept-zone-manifest-convention.md. The concept/ root is a project-local front-of-chain convention, not a project-workspace-contract@2 Kind 3 zone.
Only mutate MANIFEST.md when one of these is true:
concept_artifacts.convention: concept-zone-manifest-convention@1 and concept_artifacts.manifest_mutation: allowed;Otherwise, return a manifest_update_required note with the exact proposed entries and do not edit the manifest.
When proposing or writing entries, use the kind mapping from concept-zone-manifest-convention.md: valid project-workspace routing kinds in MANIFEST.md, concept-specific type: values in artifact frontmatter:
| Artifact | Manifest kind |
|---|---|
concept-gate-plan.md | plan |
concept-pre-challenge-gate-sketch.md | plan |
concept-handoff-brief.md | analysis |
concept-learning-log.md | log |
Each proposed or written entry includes path, kind, status, produced_by, last_updated, upstream, and consumed_by. Translate only draft and review into manifest status during producer runs; never write manifest status: approved without explicit human acceptance, and never set artifact lifecycle status to greenlit or published from the producer skill.
If the concept root is ambiguous, the manifest format is non-standard, or adding a concept entry would create a new project convention without user approval, return manifest_update_required.
Every concept artifact frontmatter includes at least id, title, type, status, scope, brand, project, concept_id, concept_name, produced_by, updated, and references.
concept-gate-plan.mdUse this only when the upstream chain includes shape map, spine, and challenge report.
---
id: <concept-id>-gate-plan-v1
title: "Concept Gate Plan - <concept_name>"
type: concept/gate-plan
status: review
scope: <concept root or business scope>
brand: "<brand>"
brand_name: "<brand display name>"
project: <project or concept name>
concept_id: <kebab-id>
concept_name: <name>
current_gate: <gate>
next_gate: <gate>
gate_readiness: candidate
handoff_allowed: <true | false>
ready_handoff_routes: []
challenge_status: completed
method_lenses: []
shape_map: <relative path>
spine_path: <relative path>
challenge_report: <relative path>
produced_by: concept-development:[email protected]
updated: <ISO timestamp>
references: []
---
Set handoff_allowed: false unless at least one downstream route has named evidence, owner, and no active blocker. Use ready_handoff_routes to list only the routes that are actually safe to hand off.
concept-pre-challenge-gate-sketch.mdUse this only when the user explicitly asks for gate thinking before challenge is complete. It cannot be handed to PRD/build.
---
id: <concept-id>-pre-challenge-gate-sketch-v1
title: "Pre-Challenge Gate Sketch - <concept_name>"
type: concept/pre-challenge-gate-sketch
status: draft
scope: <concept root or business scope>
brand: "<brand>"
brand_name: "<brand display name>"
project: <project or concept name>
concept_id: <kebab-id>
concept_name: <name>
current_gate: <gate>
next_gate: <candidate gate>
gate_readiness: sketch
handoff_allowed: false
challenge_status: intentionally_deferred
method_lenses: []
shape_map: <relative path>
spine_path: <relative path>
challenge_report: null
produced_by: concept-development:[email protected]
updated: <ISO timestamp>
references: []
---
concept-handoff-brief.md---
id: <concept-id>-handoff-brief-v1
title: "Concept Handoff Brief - <concept_name>"
type: concept/handoff-brief
status: draft
scope: <concept root or business scope>
brand: "<brand>"
brand_name: "<brand display name>"
project: <project or concept name>
concept_id: <kebab-id>
concept_name: <name>
handoff_to: brand-dna | seo-strategist | funnel-strategist | conversion-designer | content-creation-framework | site-designer | site-builder | artifact-reviewer | to-prd | to-issues | human-owner
handoff_allowed: true
method_lenses: []
source_gate_plan: <relative path>
shape_map: <relative path>
spine_path: <relative path>
challenge_report: <relative path>
produced_by: concept-development:[email protected]
updated: <ISO timestamp>
references: []
---
concept-learning-log.md---
id: <concept-id>-learning-log
title: "Concept Learning Log - <concept_name>"
type: concept/learning-log
status: draft
scope: <concept root or business scope>
brand: "<brand>"
brand_name: "<brand display name>"
project: <project or concept name>
concept_id: <kebab-id>
concept_name: <name>
latest_run: <ISO timestamp>
produced_by: concept-development:[email protected]
updated: <ISO timestamp>
references: []
---
MANIFEST.md declares output_language:, honor it for artifact prose.Record learning only when the gate or handoff work surfaces reusable concept-system improvement. If reusable learning exists, update concept-learning-log.md or create it if the concept root is established. If the log cannot be safely written, add a learning_log_update_required note with the exact entry to append. If the run produced no reusable learning, do not add learning boilerplate.
Capture only reusable learning: maturity-gate ambiguity, repeated upstream blockers, downstream routes that were premature, reviewer findings that should change future production, and bead candidates for improving the concept system.
When the next move is actual PRD writing, issue creation, content planning, design, build, legal review, or management approval, stop at the handoff and route. Do not continue into that work inside this skill.
Never mark an artifact greenlit. The reviewer gives an advisory recommendation; the orchestrator asks the user for explicit acceptance.
Provides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.
npx claudepluginhub cmgramse/skill-development --plugin concept-development