Ejecuta cualquier Skill en Manus
con un clic

Ejecuta cualquier Skill en Manus con un clic

linear-issue-create

Estrellas3

Forks0

Actualizado22 de mayo de 2026 a las 14:34

Create a Linear issue for the Personal Agent project with the correct team, state, and label policy. Use when the user asks to create, file, open, or draft a Linear issue/ticket. Do not invoke for reading or updating existing issues.

Instalación

Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.

Ejecutar en Manus

Fuente

alextra-lab

alextra-lab/personal_agent

Abrir repositorio de GitHub Ver repositorios del creador

Descarga

Ejecutar en Manus

Ocupaciones relacionadasSOC

Basado en la clasificación ocupacional SOC

Desarrolladores de softwareOcupaciones informáticas y matemáticas·SOC 15-1252

SKILL.md

readonly

name	linear-issue-create
description	Create a Linear issue for the Personal Agent project with the correct team, state, and label policy. Use when the user asks to create, file, open, or draft a Linear issue/ticket. Do not invoke for reading or updating existing issues.
disable-model-invocation	true

linear-issue-create

Create a Linear issue that conforms to the Linear Implement Gate policy in .claude/CLAUDE.md:

New == Needs Approval. Implement == Approved.

Required Fields

Field	Value
Team	`FrenchForest`
State	`Needs Approval` (state — not a label)
Labels	`PersonalAgent` + exactly one tier label
Tier label (pick one)	`Tier-1:Opus` · `Tier-2:Sonnet` · `Tier-3:Haiku`

Tier Selection

Use the routing policy from .claude/MODEL_ROUTING_POLICY.md:

Tier-1:Opus — specs, plans, ADRs, complex debugging, architecture work
Tier-2:Sonnet — feature implementation from an approved plan, first-pass debugging
Tier-3:Haiku — Linear hygiene, git ops, linting, boilerplate, mechanical edits

Ask the user which tier if it isn't obvious from the description.

Workflow

Gather title and body from the user. Body should reference any specs/ADRs.
Determine tier (ask if ambiguous).
Find team/label IDs:
- mcp__claude_ai_Linear__list_teams → find FrenchForest
- mcp__claude_ai_Linear__list_issue_labels → find IDs for PersonalAgent + chosen tier label
- mcp__claude_ai_Linear__list_issue_statuses → find state ID for Needs Approval
Create via mcp__claude_ai_Linear__save_issue with team, state, label IDs, title, description.
Report the created issue URL and remind the user it's Needs Approval — implementation is blocked until they move it to Approved.

Never Do

Add a Needs Approval label (the policy uses state, not label).
Skip the tier label — every issue must have exactly one.
Move the issue to Approved yourself. Only the user does that.
Create the issue under any team other than FrenchForest.

Output Format

✅ Created FRE-XXX — <title>
   State: Needs Approval
   Labels: PersonalAgent, Tier-N:Model
   URL: https://linear.app/...

   Implementation is gated until you move it to Approved.

Más de este repositorio

mismo repositorio

master

alextra-lab/personal_agent

Use in the master session to integrate a ready PR — analyze (code-review + security-review), doc-drift check, merge, ask before deploy, verify live, close Linear, update MASTER_PLAN.

2026-07-113

prime-explore

alextra-lab/personal_agent

Use after /clear in the explore session (cc-explore) to rebuild full project situational awareness from durable sources — observer/strategist role, read-only, never actuate. All of master's vision, none of its hands; the deliberation seat where deep strategy/methodology thinking happens off master's context.

2026-07-113

adr

alextra-lab/personal_agent

Use in the adr session (Opus) to explore an idea with the owner and — if it earns it — produce a complete ADR. Discuss/explore first, write, iterate with codex review, open ADR PR, then file sequenced implementation tickets. An ADR is a possible outcome, not a mandate. Never touches src/ or merges.

2026-07-103

build

alextra-lab/personal_agent

Use in the build session to ship a Linear FRE ticket from Approved to a master-ready PR (CI green + any bounce resolved) — fresh-start reset, plan with risk-tiered codex review (reviewer, not co-author), TDD, docs, PR, then self-complete via watcher/master pokes. Never merges or deploys.

2026-07-103

prepare-reset

alextra-lab/personal_agent

Owner-invoked before resetting (/clear-ing) a session. Verifies a safe reset boundary, writes the session-delta artifact (LAST_SESSION.md) so the next session inherits this session's decisions, distills standing facts into memory, checkpoints MASTER_PLAN, and emits a go/no-go verdict. The safe wind-down bookend to prime-master.

2026-07-103

prime-master

alextra-lab/personal_agent

Use after /clear in the master session to rebuild the guardian snapshot from durable sources — current state (1-7) then target (8) then process (9). Never from prior conversation.

2026-07-103

linear-issue-create

Create a Linear issue that conforms to the Linear Implement Gate policy in .claude/CLAUDE.md:

New == Needs Approval. Implement == Approved.

Required Fields

Field

Value

Team

FrenchForest

State

Needs Approval (state — not a label)

Labels

PersonalAgent + exactly one tier label

Tier label (pick one)

Tier-1:Opus · Tier-2:Sonnet · Tier-3:Haiku

Tier Selection

Use the routing policy from .claude/MODEL_ROUTING_POLICY.md:

Tier-1:Opus — specs, plans, ADRs, complex debugging, architecture work

Tier-2:Sonnet — feature implementation from an approved plan, first-pass debugging

Tier-3:Haiku — Linear hygiene, git ops, linting, boilerplate, mechanical edits

Ask the user which tier if it isn't obvious from the description.

Workflow

Gather title and body from the user. Body should reference any specs/ADRs.

Determine tier (ask if ambiguous).

Find team/label IDs:

mcp__claude_ai_Linear__list_teams → find FrenchForest
mcp__claude_ai_Linear__list_issue_labels → find IDs for PersonalAgent + chosen tier label
mcp__claude_ai_Linear__list_issue_statuses → find state ID for Needs Approval

Create via mcp__claude_ai_Linear__save_issue with team, state, label IDs, title, description.

Report the created issue URL and remind the user it's Needs Approval — implementation is blocked until they move it to Approved.

Never Do

Add a Needs Approval label (the policy uses state, not label).

Skip the tier label — every issue must have exactly one.

Move the issue to Approved yourself. Only the user does that.

Create the issue under any team other than FrenchForest.

Output Format

✅ Created FRE-XXX — <title> State: Needs Approval Labels: PersonalAgent, Tier-N:Model URL: https://linear.app/... Implementation is gated until you move it to Approved.