agentleFS
dmzoneilldmzoneill/skills/memory-view/SKILL.md

memory-view

Skill2 starsChanged 19 days agoApache-2.0View on GitHub

View and manage persistent memory - active issues, open MRs, follow-ups, environment health, recent sessions. Use when user says "view memory", "what's in memory?", or "show current work".

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    clear_old_sessions: Delete session files older than 7 days from memory/sessions/.

    line 32
  2. Very specific:

    Use memory_ask("What am I working on?") for quick context

    line 75

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Memory View - Inspect and Manage Memory

Shows current work state, learned patterns, follow-ups, and environment status. Supports optional actions.

Inputs

InputTypeDefaultPurpose
sectionstring"all"all, work, followups, environments, patterns, sessions
actionstring-clear_completed, add_followup, clear_old_sessions
followup_textstring-For add_followup action
followup_prioritystring"normal"high, medium, normal
slack_formatboolfalseUse <url|text> links

Workflow

1. Load Memory via MCP

  • memory_read("state/current_work") - active issues, open MRs, follow_ups
  • memory_read("state/environments") - environment health
  • memory_read("learned/patterns") - error patterns
  • memory_read("learned/runbooks") - runbooks
  • List memory/sessions/*.yaml - recent session logs (last 5 files)

2. Perform Action (if requested)

  • clear_completed: Filter active_issues (remove Done/Closed/Resolved), filter open_mrs (remove merged). Use memory_update or write back.
  • add_followup: Append to follow_ups with task, priority, created. Use memory_append("state/current_work", "follow_ups", item).
  • clear_old_sessions: Delete session files older than 7 days from memory/sessions/.

3. Format Output by Section

work: Active issues (key, summary, status, branch), Open MRs (id, title, url, needs_review, is_draft)

followups: List with priority emoji (🔴 high, 🟡 medium, ⚪ normal)

environments: Per-env status (healthy/issues/unknown), last_check, alerts, ephemeral namespaces

patterns: Error patterns with pattern + meaning/fix

sessions: Recent dates with last 5 actions each

4. Output Format

# 🧠 Memory View

## 📋 Current Work
### Active Issues (N)
- **AAP-XXXXX** - summary | Status: X | Branch: `branch`
### Open MRs (N)
- !1234 - title 👀📝

## 📌 Follow-ups
- 🔴/🟡/⚪ task

## 🌐 Environment Status
### ✅/⚠️/❓ stage/production/konflux

## 💡 Learned Patterns
## 📜 Recent Sessions

---
### Available Actions
- Clear completed: skill_run("memory_view", '{"action": "clear_completed"}')
- Add follow-up: skill_run("memory_view", '{"action": "add_followup", "followup_text": "..."}')

Key Details

  • Chains to: memory_edit, memory_cleanup
  • Use memory_ask("What am I working on?") for quick context
  • Linkify Jira keys and MR IDs in output

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.