learn
Skill64 starsChanged 7 months agoApache-2.0View on GitHub
Save a marketing diagnosis insight to the pro-diagnosis knowledge base so it is applied in future operations across all platforms. Use when the user runs /learn, explicitly teaches the agent a marketing insight, corrects the agent's analysis, or asks to remember/record an operational learning for next time. Also use when the user asks in Japanese (この学びを記録して / 次回から反映して / 運用の気づきを覚えておいて).
195 other projects use a version of this.
Adopted by
Most recently taken up by
- Doist/todoist-aitheir own version, first seen Nov 9, 2026
- Doist/todoist-clitheir own version, first seen Nov 8, 2026
- HughYau/AcademicForgetheir own version, first seen Nov 8, 2026
- dimsedra/skillstheir own version, first seen Nov 8, 2026
- rajanrx/skillstheir own version, first seen Nov 8, 2026
- edwinidrus/dragonhoardtheir own version, first seen Nov 8, 2026
Used with
Projects with it also use add-anydoc, add-clidash and 10 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.
TomGranotSkilladd-anydoc
Add local office-document-to-Markdown conversion to NanoClaw agent containers with the pinned Firecrawl AnyDoc CLI. Use when agents need to read attached Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, CSV, or text-based PDF files without uploading them to a hosted parser.
Also in 5 projects that use this
TomGranotSkilladd-clidash
Add clidash — a zero-dependency, read-only web dashboard that derives its tabs and tables at runtime from any CLI that lists resources as JSON. Ships pre-wired for NanoClaw's ncl CLI (agent groups, sessions, channels, users, roles), plus message-activity charts, a log tail, and a read-only file viewer for group skills/CLAUDE.md/profiles.
Also in 5 projects that use this
seek888Skillopen-gstack-browser
Launch GStack Browser — AI-controlled Chromium with the sidebar extension baked in. Opens a visible browser window where you can watch every action in real time. The sidebar shows a live activity feed and chat. Anti-bot stealth built in. Use when asked to "open gstack browser", "launch browser", "connect chrome", "open chrome", "real browser", "launch chrome", "side panel", or "control my browser". Voice triggers (speech-to-text aliases): "show me the browser".
Also in 11 projects that use this
Saqlain-811Skillios-sync
Regenerate the iOS debug bridge against the latest upstream gstack templates. (gstack)
Also in 6 projects that use this
MicrosoftSkilladd-codex
Use Codex (CLI + AppServer) as the full agent provider — planning, tool orchestration, native compaction, MCP tools, session resume — in place of the Claude Agent SDK. ChatGPT subscription or OPENAI_API_KEY. Per-group via agent_provider. Distinct from using OpenAI as an MCP tool (where Claude remains the planner).
Also in 6 projects that use this
MicrosoftSkilladd-deltachat
Add DeltaChat channel integration via @deltachat/stdio-rpc-server. Native adapter — no Chat SDK bridge. Email-based messaging with end-to-end encryption.
Also in 6 projects that use this
- +5 more from TomGranot
- +1 more from microsoft
Other versions195 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 195
- garrytan/gstack★ 141ksame name
- rohitg00/ai-engineering-from-scratch★ 78ksame name
- gavrielc/nanoclaw★ 31ksame name
- nanocoai/nanoclaw★ 31ksame name
- qwibitai/nanoclaw★ 31ksame name
- tigerless-labs/autoharness★ 11ksame name
- tw93/claude-health★ 7.5ksame name
- tw93/Waza★ 7.5ksame name
- nykooi1/vibe-wise★ 3.5ksame name
- HughYau/AcademicForge★ 2.6ksame name
185 more not listed
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 repository30 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- ad-fatigue-checkSkill
- audience-reviewSkill
- budget-pacingSkill
- budget-rebalanceSkill
- competitive-scanSkill
- creative-generateSkill
- creative-refreshSkill
- daily-checkSkill
- experimentSkill
- goal-reviewSkill
- incident-postmortemSkill
- lead-form-createSkill
- monthly-reportSkill
- _mureo-amazon-adsSkill
- _mureo-google-adsSkill
- _mureo-learningSkill
- _mureo-meta-adsSkill
- _mureo-pro-diagnosisSkill
- _mureo-report-persistSkill
- _mureo-sharedSkill
- _mureo-state-schemaSkill
- _mureo-strategySkill
- onboardSkill
- rescueSkill
- search-term-cleanupSkill
- sync-stateSkill
- tracking-healthSkill
- weekly-reportSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 170 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 42
Identify the insight: If the user passed an insight as the argument, use it.
- Distinctive: line 65
Choose the scope: Before saving, detect which knowledge tiers this installation exposes.
“Common” is measured: kept by at least 6 in 10 of the 170 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
Learn
PREREQUISITE: Read
../_mureo-shared/SKILL.mdfor auth, security rules, output format, and Tool Selection (Read/Write on Code,mureo_strategy_*/mureo_state_*MCP on Desktop / Cowork).
Save a marketing diagnosis insight to the pro-diagnosis knowledge base.
Saved insights are loaded at the start of future sessions and applied
across /daily-check, /rescue, /budget-rebalance, and the other
diagnostic workflows.
The skill persists insights by shelling out to mureo learn add,
which routes the write through the KnowledgeStore Protocol. The
default backend writes to
~/.claude/skills/_mureo-pro-diagnosis/SKILL.md (preserving the
prior file layout); an alternate backend registered via the
mureo.runtime_context_factory entry-point group can redirect or
split the write without changing this skill.
The knowledge base has two tiers — an operator tier shared across
every workspace, and an optional workspace tier scoped to the
current one. Use mureo learn tiers to find out which are available
before deciding where an insight belongs (step 4).
When to use
- The user runs
/learnfollowed by an insight, e.g.:/learn CV少ないサイトではマイクロCVを活用すべき(sites with few conversions should use micro-conversions)<!-- ja-literal -->/learn 予算5000円/日で広告グループ8個は多すぎる(eight ad groups is too many on a ¥5,000/day budget)<!-- ja-literal -->/learn Target CPA を下げすぎると逆に CV が減る(lowering Target CPA too far reduces conversions)<!-- ja-literal -->
- The user runs
/learnwith no argument — review the current conversation for corrections or marketing expertise the user shared and propose those as insights.
Steps
- Identify the insight. If the user passed an insight as the argument, use it. Otherwise review the current conversation for moments where the user corrected the agent's analysis or supplied marketing expertise, and select the most reusable one(s).
Structure the insight using this template:
### [Short descriptive title] **Situation:** [When this insight applies] **Wrong assumption:** [What an inexperienced agent might think] **Correct approach:** [The right way to handle this situation] **Why:** [The reasoning behind the correct approach] Date learned: YYYY-MM-DD- Present for approval. Show the formatted insight to the user and ask for explicit confirmation before saving. Capture the generalized lesson only — never record account IDs, credentials, access tokens, or personal data in the knowledge base.
Choose the scope. Before saving, detect which knowledge tiers this installation exposes. The command is read-only — it creates and modifies nothing:
mureo learn tiersIt prints one line per tier, e.g.:
operator: configured workspace: configuredworkspace: configured— ask the user which tier to save to, and present workspace as the recommended default. Most insights worth recording are account-specific: product quirks, measurement and conversion-tracking quirks, seasonality, campaign history, what has already been tried on this account. Those are true here and often false elsewhere, so writing them to the operator tier makes every other account inherit them and the agent will confidently misapply them. Reserve the operator tier for genuinely generalizable cross-account know-how — platform mechanics, statistical reasoning, structural rules of thumb.workspace: absent— no workspace tier is installed on this machine. Save to the operator tier without asking the user.
Save by invoking the CLI. Pass the approved insight verbatim (including its leading blank line and trailing newline), with the scope from step 4 stated explicitly:
# Run ONE of these — the scope you settled on in step 4. mureo learn add "$INSIGHT_MARKDOWN" --scope workspace mureo learn add "$INSIGHT_MARKDOWN" --scope operator--scope operatorwrites the cross-workspace tier read by every diagnostic skill.--scope workspacewrites the workspace-scoped tier, so the insight stays with the active account and never leaks to other workspaces. The command exits with a helpful message when no workspace tier is configured — step 4 rules that case out.
Both tiers are handed to diagnostic workflows by
mureo_learning_insights_get; when the two conflict, workspace-tier insights take precedence over operator-tier insights.- Confirm. Tell the user the insight was saved, which tier it went
to, and that it will be applied in future
/daily-check,/rescue,/budget-rebalance, and other diagnostic workflows.
IMPORTANT: Always save through mureo learn add, never by writing the
file path manually. Going through the CLI keeps the skill compatible
with alternate KnowledgeStore backends and avoids the agent having to
know about the scaffold/file layout. Never save to Claude Code memory;
the on-disk knowledge base persists across sessions, Claude memory
does not.
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.

