session-awareness

Project state awareness and session recovery for GSD-managed projects. Use this skill whenever: starting a new work session, resuming after a break, the user asks "where did we leave off" or "what's the current state", before making substantial code changes (to check for existing plans), the user seems disoriented about project status, or when something seems off and STATE.md might have relevant context. Also activates when the user references .planning/ files, milestones, phases, or project progress.

Ir a la instalación Revisar archivos

Repositorio: Tibsfox/gsd-skill-creator
Última actividad en el origen: 25 de abril de 2026 a las 21:14
Idioma detectado de SKILL.md: inglés
Estrellas: 70
Forks: 9

Opciones de instalación

De forma predeterminada está seleccionado el prompt que primero revisa el origen. Puedes cambiar a un comando directo o descargar una copia local.

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.

Un comando directo omite el prompt de revisión. Revisa el origen antes de ejecutarlo.

npx skills add https://github.com/Tibsfox/gsd-skill-creator --skill session-awareness

El comando permanece en una sola línea. Desplázate horizontalmente para revisarlo antes de copiarlo.

¿Prefieres una copia local? Descarga los archivos que SkillsMP tiene disponibles ahora.

Revisa los archivos de origen

Lee SKILL.md y los archivos complementarios que muestra SkillsMP antes de decidir si quieres instalarlo.

SKILL.md

Instrucciones de origen · Vista previa de solo lectura

name: session-awareness
description: Project state awareness and session recovery for GSD-managed projects. Use this skill whenever: starting a new work session, resuming after a break, the user asks "where did we leave off" or "what's the current state", before making substantial code changes (to check for existing plans), the user seems disoriented about project status, or when something seems off and STATE.md might have relevant context. Also activates when the user references .planning/ files, milestones, phases, or project progress.
user-invocable: true
version: 1.0.0
format: 2025-10-02T00:00:00.000Z
triggers: ["the user references"]
updated: 2026-04-25T00:00:00.000Z
status: ACTIVE

# Session Awareness ## GSD Artifact Map | File | Purpose | When to Read | |---|---|---| | `.planning/PROJECT.md` | Vision, constraints, decisions | Understanding project context | | `.planning/REQUIREMENTS.md` | What we're building (REQ-IDs) | Scoping work | | `.planning/ROADMAP.md` | Phase structure and status | Finding current position | | `.planning/STATE.md` | Session memory, blockers, decisions | **Always on resume** | | `.planning/config.json` | Workflow preferences | Checking mode (yolo/interactive) | | `.planning/phases/XX-name/XX-YY-PLAN.md` | Detailed task plans | Executing work | | `.planning/phases/XX-name/XX-YY-SUMMARY.md` | What was built | Reviewing completed work | ### skill-creator Artifacts | File | Purpose | When to Read | |---|---|---| | `.planning/patterns/sessions.jsonl` | Session observations | Pattern detection input | | `.claude/commands/*.md` | Project-level skills | Before GSD phase execution | | `.claude/agents/*.md` | Composed agents | Agent selection | | `~/.claude/commands/*.md` | User-level skills | Fallback when no project skill matches | ## Response Pattern: Before Substantial Work ``` Let me check the current project state... [Read ROADMAP.md, STATE.md] This falls under Phase X. There's already a plan at `.planning/phases/...`. Should I execute that plan, or are you looking to do something different? ``` ## Response Pattern: Fresh Session Recovery ``` /gsd:progress (or) /gsd:resume-work ``` ## Response Pattern: No GSD Structure ``` This project doesn't have GSD initialized yet. Want me to run `/gsd:new-project` to set up the planning structure? ``` ## Response Pattern: Work Conflicts with Plans ``` Heads up — this would modify files that Phase N is planning to create. Options: 1. Execute Phase N first (recommended) 2. Update the Phase N plan to account for this 3. Proceed anyway and reconcile later ``` ## Core Rule **Always check STATE.md** when resuming or when something seems off — it is the project's memory.

Ver en GitHub

Volver a la búsqueda Volver a la instalación

goal-ambiguity-gate

Use the moment a request is underspecified and you are about to act on an ASSUMED goal. Enumerate the candidate goals the request could mean, project the action or artifact each one implies, and check whether they diverge: if two or more plausible goals lead to materially different actions or artifacts, ask exactly ONE targeted clarifying question; otherwise proceed on the most-likely goal and state the assumption in one line. Clarification is an evidence-producing action, not a delay — but one question, never an interrogation. Distinct from gsd-spec-phase (GSD-phase-bound, emits a heavy SPEC.md) and intent-router (fetch strategy, not goal disambiguation). Backed by agent goal-state inference (arxiv 2606.16813v1). Triggers on acting under an assumed goal when the request admits more than one materially different reading.

2026-07-19

memory-hubness-gate

Use at write time to vector/embedding memory — Grove content-addressed insertion, chroma/pgvector upserts, memory-consolidation promoting session traces to MEMORY.md, or embedding externally-ingested content. Scores each candidate record against a fixed panel of sentinel queries and quarantines any record that would become the nearest neighbor of too many unrelated queries — a hub — whether from adversarial poisoning or accidental over-generality. This is the memory-record-side sibling of skill-injection-guardian (file-side) and the write-side complement of memory-use-warrant (read-side). Quarantine, never silently drop; a human reviews. Backed by the admission-time hubness gate (arxiv 2606.19692v1). Triggers on inserting into vector memory, consolidating memory, and embedding stranger content.

2026-07-19

memory-use-warrant

Run this appropriateness check the moment you are about to integrate a retrieved long-term memory — a Grove content-addressed hit, a chroma/pgvector neighbour, a memory-consolidation digest, or a MEMORY.md line — into a response, especially anything touching private origins, Fox Companies IP, credentials, or Center Camp / consent-governed content. It answers a question intent-router never asks: not WHAT to fetch or HOW, but WHETHER a correctly-retrieved item should reach output. Relevance is not appropriateness — a perfect similarity match can still be a boundary violation. Default is FAIL-CLOSED: if in-context authorization is uncertain, the memory may inform behaviour but must not be surfaced. Backed by RBI-Eval (arxiv 2606.06055v1). Triggers on surfacing recalled sensitive memory into a response.

2026-07-19

Ver todos los de este repositorio

session-awareness

Datos de origen

Opciones de instalación

Revisa los archivos de origen

Más de este repositorio

Más de este repositorio