How do I install the Vestige Show skill?

Run npx skillmds@latest add conorluddy/vestige-show in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

What does the Vestige Show skill do?

Expand a Vestige memory at higher fidelity once you have its handle (a `mem_ ` string). Use this skill after `vestige-recall` returns a card whose `one_liner` isn't enough, when the user says "show me memory ", "expand ", "what does say in full?", "read me memory ", or whenever you need the *body*, *rationale*, or *source content* of a memory rather than the compact handle. Depth ladder — one_liner → summary → compressed → full. Default is summary; pass `--depth full` to read the entire body. It is listed under Coding & Dev Tools on SkillMD.

Is Vestige Show safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Vestige Show?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Vestige Show free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Vestige Show?

conorluddy (@conorluddy) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Vestige Show by conorluddy — Agent Skill

Name: Vestige Show
Author: conorluddy

Vestige Show

Expand a Vestige memory at higher fidelity once you have its handle (a `mem_<ULID>` string). Use this skill after `vestige-recall` returns a card whose `one_liner` isn't enough, when the user says "show me memory <id>", "expand <id>", "what does <id> say in full?", "read me memory <id>", or whenever you need the *body*, *rationale*, or *source content* of a memory rather than the compact handle. Depth ladder — one_liner → summary → compressed → full. Default is summary; pass `--depth full` to read the entire body.

conorluddy Updated Sep 17, 2026

File contents

Expand a memory by handle

Read a memory at the depth you actually need. Vestige stores memories as a depth ladder (PRD §11.3): one_liner (≤ 60 chars), summary (a sentence), compressed (a paragraph), full (the whole body). vestige-recall returns the compact card — this skill drills in.

When to fire

vestige-recall just returned a card whose one-liner sounds relevant but you need to read the actual decision/rationale to apply it.
The user said "show me mem_…" or "what does mem_… say".
You're about to cite a memory and want to confirm the wording.

If you don't have a handle yet, run vestige-recall first.

How to invoke

vestige show <mem_id> --depth summary --json

<mem_id> (positional, required): the mem_<ULID> handle from a recall hit or a context pack.
--depth (optional, default summary): one of one_liner, summary, compressed, full. Use full only when you need everything; summary is usually enough to apply a decision.
--sources (optional): include attached source rows in the response.
--json (recommended): structured envelope with id, type, depth, content, sources[].

After invocation

Read content at the depth you requested. The depth ladder exists precisely to keep agent context lean — don't reach for --depth full reflexively. If summary was enough, stop there.

When citing the memory, include the handle so the user can verify.

Idempotence & dedup

Read-only — re-running is safe but wastes tokens. Skip if:

You only need the one-liner the recall already returned.
You want a list of memories, not one. Use vestige-recall with --limit.

---name: vestige-showdescription: Expand a Vestige memory at higher fidelity once you have its handle (a `mem_<ULID>` string). Use this skill after `vestige-recall` returns a card whose `one_liner` isn't enough, when the user says "show me memory <id>", "expand <id>", "what does <id> say in full?", "read me memory <id>", or whenever you need the *body*, *rationale*, or *source content* of a memory rather than the compact handle. Depth ladder — one_liner → summary → compressed → full. Default is summary; pass `--depth full` to read the entire body.---# Expand a memory by handleRead a memory at the depth you actually need. Vestige stores memories as a depth ladder (PRD §11.3): `one_liner` (≤ 60 chars), `summary` (a sentence), `compressed` (a paragraph), `full` (the whole body). `vestige-recall` returns the compact card — this skill drills in.## When to fire- `vestige-recall` just returned a card whose one-liner sounds relevant but you need to read the actual decision/rationale to apply it.- The user said "show me `mem_…`" or "what does `mem_…` say".- You're about to cite a memory and want to confirm the wording.If you don't have a handle yet, run `vestige-recall` first.## How to invoke```bashvestige show <mem_id> --depth summary --json```- **`<mem_id>`** (positional, required): the `mem_<ULID>` handle from a recall hit or a context pack.- **`--depth`** (optional, default `summary`): one of `one_liner`, `summary`, `compressed`, `full`. Use `full` only when you need everything; `summary` is usually enough to apply a decision.- **`--sources`** (optional): include attached source rows in the response.- **`--json`** (recommended): structured envelope with `id`, `type`, `depth`, `content`, `sources[]`.## After invocationRead `content` at the depth you requested. The depth ladder exists precisely to keep agent context lean — don't reach for `--depth full` reflexively. If `summary` was enough, stop there.When citing the memory, include the handle so the user can verify.## Idempotence & dedupRead-only — re-running is safe but wastes tokens. Skip if:- You only need the one-liner the recall already returned.- You want a *list* of memories, not one. Use `vestige-recall` with `--limit`.

Frequently asked questions