Name: AIM Refresh
Author: Skills Guide Bot

Automated summary

Manually re-runs the freshness evaluation for code-patterns memories by executing the refresh.py script from the ai-memory system.

Strengths

Reuses the existing freshness scan pipeline (SPEC-013) instead of reimplementing it.
Supports an optional project filter (group_id) to narrow the scan scope.
Outputs a per-tier table (Fresh / Aging / Stale / Expired / Unknown) plus an actionable count.
Always goes through run-with-env.sh, ensuring the installed ai-memory virtualenv and local service defaults are used.

Limitations

The --topic option is a no-op in v2.1: a full scan still runs even when a topic filter is given.
Requires a local ai-memory installation with its virtualenv and run-with-env.sh script.
Only covers code-patterns memories, not other memory types.

When to use it

Use it when you want to force a freshness re-evaluation of code-patterns memories without waiting for the automatic scan, optionally limited to a single project.

When not to use it

Don't use it to view, edit, or delete memory contents, or when you expect a topic filter to actually take effect.

Security analysis

Caution

Quality score82/100

The skill is a thin wrapper around a local maintenance script. Bash execution is legitimate here but powerful; the main risk is trusting the installed ai-memory scripts and the environment-controlled install directory.

Findings

•Executes a local script via Bash through run-with-env.sh, running whatever code is present at the resolved install path.
•The install path is controlled by AI_MEMORY_INSTALL_DIR, so it could point at a different or untrusted ai-memory installation.
•No destructive commands, secret exfiltration, network calls, or obfuscated payloads are shown.

How this analysis is made

Examples

Full freshness scan

/aim-refresh — re-scan all code-patterns memories and show the freshness tier table.

Project-scoped refresh

Run the aim-refresh skill but limit the freshness scan to the my-project group_id.

Topic filter (v2.1)

Use aim-refresh with --topic "authentication" to re-evaluate memories about authentication.

name: aim-refresh description: "Manually re-evaluate freshness for code-patterns memories" trigger: "/aim-refresh" allowed-tools: Bash

Manually re-evaluates freshness for code-patterns memories. Reuses the freshness scan pipeline from SPEC-013 with optional scope filters.

Canonical Execution

Always run the real script through run-with-env.sh so the skill uses the installed ai-memory virtualenv and the standard local service defaults.

"${AI_MEMORY_INSTALL_DIR:-$HOME/.ai-memory}/scripts/memory/run-with-env.sh" refresh.py

Examples

# Scan all code-patterns memories
"${AI_MEMORY_INSTALL_DIR:-$HOME/.ai-memory}/scripts/memory/run-with-env.sh" refresh.py

# Limit to a specific project group_id
"${AI_MEMORY_INSTALL_DIR:-$HOME/.ai-memory}/scripts/memory/run-with-env.sh" refresh.py my-project

# Topic filter (v2.1 — currently runs full scan with project filter)
"${AI_MEMORY_INSTALL_DIR:-$HOME/.ai-memory}/scripts/memory/run-with-env.sh" refresh.py --topic "authentication"

Implementation

Script: scripts/memory/refresh.py
Interpreter: run-with-env.sh (imports memory.*, requires venv)
Args: [project] (optional positional group_id filter), --topic (v2.1, no-op today)
Output: tier table (Fresh / Aging / Stale / Expired / Unknown) + actionable count

From the file to a first result

The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.

View the source and supporting files

This download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.

1. Download the file

Download SKILL.md

From the root of a test project, save the file as .skill-downloads/aim-refresh-ms2s7bt3/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.

Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.

mkdir -p '.skill-downloads/aim-refresh-ms2s7bt3' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/aim-refresh-ms2s7bt3/download' --output '.skill-downloads/aim-refresh-ms2s7bt3/SKILL.md.part' && mv '.skill-downloads/aim-refresh-ms2s7bt3/SKILL.md.part' '.skill-downloads/aim-refresh-ms2s7bt3/SKILL.md'

2. Check prerequisites

Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.

Tools declared by the author (check availability in your agent): Bash

No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.

The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.

3. Load the skill

After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.

Claude Code

test -f '.skill-downloads/aim-refresh-ms2s7bt3/SKILL.md' && test -s '.skill-downloads/aim-refresh-ms2s7bt3/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/aim-refresh' && cp -R '.skill-downloads/aim-refresh-ms2s7bt3' '.claude/skills/aim-refresh'

OpenSkills

OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.

Official OpenSkills installation

openskills install './.skill-downloads/aim-refresh-ms2s7bt3'

openskills read 'aim-refresh-ms2s7bt3'

Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.

For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.

openskills sync

Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.

4. Try a first task

Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:

Read .skill-downloads/aim-refresh-ms2s7bt3/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.

Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.

Related skills

Create Interactive Maps with kepler.gl

Data & AI

Create interactive map visualizations and export standalone HTML using the keplergl Python package. Use to plot geospatial data from DataFrames, GeoJSON, or CSV.

Claude CodeCursorCodexintermediateSafe 11,995

Skills Guide Bot