Working Memory

Maintain a project's mid-term working memory — a WORKING.md file in the repo holding the current stage's state (decision log, what was tried and failed, what's next) so it survives context compaction and new sessions. Use to set up WORKING.md in a project, to read it at the start of a session, to checkpoint progress into it after a meaningful step or before /compact, and to consolidate settled conclusions into long-term assistant memory (then reset WORKING.md) when a stage completes. Triggers: "set up working memory", "checkpoint", "save state", "resume where we left off", "consolidate memory"

3 starsProductivity & Notes

Install

skills CLI (Claude Code, Cursor, Codex and more)

npx skills add ikotelkin/claude-skills --skill working-memory

Manual install

git clone --depth 1 https://github.com/ikotelkin/claude-skills.git /tmp/claude-skills
mkdir -p ~/.claude/skills
cp -r /tmp/claude-skills/skills/working-memory ~/.claude/skills/working-memory

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Working Memory

## Why

A long session runs out of context and gets **compacted** — the transcript is squeezed into a summary, and the details drop out: decisions, edge-cases, what was already tried and failed. Work quality falls, and the next session starts blind — the user feels "didn't we already do this?".

Root cause: the important state lived **only in the conversation** — volatile memory that dies on compaction and never crosses into a new session. The fix is to stage that state onto a medium that survives: a `WORKING.md` file in the repo.

## The three levels

| Level | Medium | Lifespan |
|---|---|---|
| **Short-term** | session context | hours — dies on compaction |
| **Mid-term** | `WORKING.md` in the repo | days–weeks — while a stage runs |
| **Long-term** | the assistant's memory (e.g. Claude Code memory files) | months — survives everything |

This skill owns the mid-term level and the bridge up to long-term. Flow: **context → WORKING.md → (distill at stage end) → long-term memory.** WORKING.md is a *staging area* for memory, not a parallel store.

## The file

`WORKING.md` lives at the repo root (a working thread in a subfolder may have its own, e.g. `docs/research/WORKING.md`). Four sections:

- **Current stage** — one or two lines: where we are right now.
- **Decision log** — datestamped entries (absolute dates), newest-relevant on top: what was decided/done and *why*.
- **Tried / didn't work** — dead ends, so they aren't re-attempted.

Read the full skill on GitHub

Details

Skill name: working-memory
Repository: ikotelkin/claude-skills
Path: skills/working-memory/SKILL.md
License: MIT
Repo updated: 7 September 2026
Listed in: karanb192/awesome-claude-skills

FAQ

What does the Working Memory skill do?

How do I install the Working Memory skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add ikotelkin/claude-skills --skill working-memory. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Working Memory popular?

It lives in ikotelkin/claude-skills, which has 3 GitHub stars and 0 forks, and is included in 1 curated skill list.

Related skills

Dialog Tree

ikotelkin/claude-skills

Maintain a visual "dialog tree" — a data file plus a self-contained HTML viewer in the project repo that map the branches of a long conversation (user questions → the steps/variants of the answers) as an interactive tree with resolve/delete marks and a "built up to" marker for incremental updates. Use whenever the user asks to "create/set up a dialog tree", "update the tree", "add this to the tree", "show open branches", or mentions dialog-tree.html — and proactively offer it when a deep-dive discussion branches enough that the user risks losing track of unexplored side-threads.

Git & Code ReviewIn 1 list

Cline Pilot

gongdear/cline-pilot

Proxy Cline CLI tasks: dispatch, monitor, relay decisions.

Productivity & NotesIn 1 list

Cera Project Memory

miketepUR/cera-reasoning-harness

CERA Project Memory v1.01 — two-tier persistent learning and collaborative reasoning across sessions. Use ONLY inside a project. When active: read CERA Index and/or session maps at conversation start, engage CERA Layer 0 behavioral protocol, produce session maps at checkpoints. CERA Index is created and managed exclusively by a dedicated integrator conversation.

Productivity & NotesIn 1 list

Puzzle Activity Planner

fruitwyatt/puzzle-activity-planner

Plan engaging puzzle-based activities for classrooms, parties, team-building, and events. Generates structured activity plans with printable puzzle recommendations, timing, difficulty levels, and direct links to free puzzle generators. Use when planning educational activities, party games, team events, or any occasion that could benefit from puzzles.

Productivity & NotesIn 1 list

Workplace English Wingman

Rorogogogo/workplace-english-wingman

Improve, rewrite, and explain workplace English for an English-as-a-second-language professional in Australia. Use when the user asks to polish, fix, rewrite, improve, or check work emails, Slack or Teams messages, follow-ups, replies to managers or stakeholders, technical explanations, status updates, polite chasing messages, questions, pushback, issue explanations, or similar workplace communication for Australian companies. Ask targeted clarifying questions before rewriting when the intended meaning, recipient, action, deadline, blame, commitment, or technical conclusion is unclear.

Productivity & Notes

Align

ggrigo/align

Epistemic feedback loop. Generate an interactive HTML form where the user rates LLM-produced claims as correct, wrong, almost, needs-nuance, can't-verify, or skipped — plus add notes and flag missing items. Submit downloads an align.md that Claude reads back to apply corrections to TASKS.md, smart-memory (guarded), and the per-session archive. Source-agnostic by design: any producer (rhythm, digest, briefing, todo, code review, financial recon, anything) that emits claims matching the claim shape can be aligned. Trigger words: "/align", "align", "give feedback", "correct the rhythm", "that's n

Productivity & NotesIn 1 list

Browse the most popular Claude skills, all productivity & notes skills, or write your own with the skills generator.