forget
Skill16 starsChanged 7 months agoMITView on GitHub
Invalidate or remove a memory entry. Use when the user says "forget that", "that memory is wrong", "remove the X memory", "/forget X". Marks the file as invalidated rather than deleting — preserves history.
9 other projects use a version of this.
Adopted by
Most recently taken up by
- codewhale-hq/codewhale-plugin-marketplacetheir own version, first seen Nov 8, 2026
- obra/muse-skillstheir own version, first seen Oct 13, 2026
- sneakers-the-rat/muse-skillstheir own version, first seen Oct 13, 2026
- jacobwell/muse-skillstheir own version, first seen Sep 25, 2026
- jmylchreest/aidetheir own version, first seen Aug 21, 2026
- KeyShiftLDN/ClaudeCodetheir own version, first seen Jun 9, 2026
Used with
Projects with it also use generate_podcast, muse_db and 5 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
jacobwellSkillgenerate_podcast
Compose and deliver audio content: a podcast episode, briefing, or narrated summary, with one or more voices, as an MP3. For reading supplied text aloud verbatim, use tts.
Also in 3 projects that use this
jacobwellSkillmuse_db
Inspect database-backed Muse records for diagnosis and cross-table tracing when purpose-built product tools do not expose the needed state.
Also in 3 projects that use this
ansvisorSkillshopping
Checks product pages and feed for ChatGPT Shopping (US) and Google Shopping (EU).
Also in 4 projects that use this
SentrySkilltts
Generates spoken narration with Gemini TTS through Vercel AI Gateway. Use for text-to-speech, audio samples, voiceovers, or speaking as Junior with the reusable Junior voice. Do not use for transcription, voice cloning, music generation, or rendering a video without a narration request.
Also in 4 projects that use this
QuixiAISkillspotify
Search Spotify, inspect current playback and devices, and control playback with explicit approval
Also in 3 projects that use this
refly-aiSkillgmail
Integrate with Gmail for email management and automation. Use when you need to: (1) send and compose emails with attachments, (2) read and search emails by criteria, (3) manage drafts and email labels, or (4) reply to email threads and conversations.
Also in 3 projects that use this
- +1 more from jacobwell
Other versions9 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 9
- sneakers-the-rat/muse-skills★ 24same name
- obra/muse-skills★ 20same name
- jmylchreest/aide★ 19same name
- ThisisYoYoDev/claude-rag★ 9same name
- jacobwell/muse-skills★ 8same name
- codewhale-hq/codewhale-plugin-marketplace★ 5same name
- hereinthehive/kickstart★ 4same name
- ourines/claude-code-learn★ 1same name
- KeyShiftLDN/ClaudeCode★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository45 other files it gives its agents.
- AGENTS.mdAGENTS.md
- docs/agents.mdAGENTS.md
- .claude/CLAUDE.mdCLAUDE.md
- CLAUDE.mdCLAUDE.md
- actSkill
- security-checkSkill
- environment-checkSkill
- run-verificationSkill
- refactorSkill
- debug-session-archivedSkill
- generate-guardsSkill
- check-anthropicSkill
- code-reviewerSkill
- code-reviewSkill
- debug-sessionSkill
- end-sessionSkill
- evolve-checkSkill
- evolveSkill
- fix-bugSkill
- frontend-designSkill
- guardSkill
- kit-healthSkill
- learnSkill
- map-codebaseSkill
- modeSkill
- parallel-prototypesSkill
- planSkill
- powershell-safeSkill
- product-riskSkill
- progress-reportSkill
- prototype-hypothesisSkill
- recallSkill
- refactoring-uiSkill
- scan-codebaseSkill
- scan-conventionsSkill
- search-firstSkill
- search-memorySkill
- shadow-codeSkill
- skill-creatorSkill
- smart-resumeSkill
- start-sessionSkill
- strategic-compactSkill
- tourSkill
- ux-heuristicsSkill
- verification-loopSkill
The file
We split this skill into the rules it gives an agent
8 rules. 0 are common, 6 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 9 edited versions we read keep these.
6
Distinctive
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
- Very specific: line 24
If the user named a file directly (e.g.
- Distinctive: line 34
Read the full file content so you can show the user what will be removed:
- Very specific: line 44
Add status: invalidated to the frontmatter and a one-line note at the top of the body:
- Distinctive: line 68
Use Edit to apply the change — never delete the file.
- Distinctive: line 77
Delete that line using Edit.
- Distinctive: line 90
Never hard-delete memory files — always invalidate and keep
- Distinctive: line 92
If the user says "forget everything about X", run the search and offer a list to confirm each one individually
- Distinctive: line 93
After invalidating, check if any other memory files reference the invalidated one and note them
“Common” is measured: kept by at least 6 in 10 of the 9 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Skill: forget
Trigger phrases:
/forget [topic or file name]- "forget that"
- "that memory is wrong / outdated"
- "remove the X memory"
- "delete the memory about X"
- "mark X as invalid"
Steps
Step 1 — Find the target memory
If the user named a file directly (e.g. /forget feedback_plan_before_edit.md), use that path.
Otherwise, run:
python tools/memory.py --search "[topic]" --top 5Show the top result(s) and ask: "Is this the memory you want to remove? (yes / pick a number)"
Step 2 — Read the file
Read the full file content so you can show the user what will be removed:
> **File:** [filename]
> [first 5 lines of content]Confirm: "Mark this memory as invalidated? (yes/no)"
Step 3 — Invalidate (do not delete)
Add status: invalidated to the frontmatter and a one-line note at the top of the body:
Before:
---
name: some-feedback
type: feedback
---
Always do X when Y.After:
---
name: some-feedback
type: feedback
status: invalidated
invalidated: 2026-03-31
---
> **INVALIDATED** — removed by user. Kept for history only.
Always do X when Y.Use Edit to apply the change — never delete the file.
Step 4 — Remove from MEMORY.md index
Find the line in MEMORY.md that references this file and remove it:
- [Title](filename.md) — descriptionDelete that line using Edit.
Step 5 — Confirm
Report:
Forgotten. [filename] is marked invalidated and removed from the index.
The file is kept in memory/ for history — it will no longer load at session start.Notes
- Never hard-delete memory files — always invalidate and keep
- The
status: invalidatedfrontmatter prevents future confusion but preserves the audit trail - If the user says "forget everything about X", run the search and offer a list to confirm each one individually
- After invalidating, check if any other memory files reference the invalidated one and note them
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
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.

