Promote
Skill25 starsChanged 7 days agoMITView on GitHub
Promote conversation insights into durable vault notes, project updates, profiles, or doctrine. Use when saving an insight permanently or turning chat into a note.
17 other projects use a version of this.
Adopted by
Most recently taken up by
- anotherben/claude-harnesstheir own version, first seen Nov 8, 2026
- ArcticFox2029/chamnantheir own version, first seen Nov 5, 2026
- jbaruch/nanoclaw-hosttheir own version, first seen Oct 31, 2026
- anis-dr/skillstheir own version, first seen Oct 15, 2026
- dedalus-labs/wingmantheir own version, first seen Oct 8, 2026
- jdiazromeral/tarstheir own version, first seen Oct 3, 2026
Used with
Projects with it also use research.
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.
NVIDIASkillresearch
Before designing a feature, research how comparable libraries solve the problem, check best practices, known pitfalls, and upstream changes. Use when starting a new feature, investigating an unfamiliar area, or the user asks to research something.
Also in 3 projects that use this
Other versions17 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 17
- oliver-kriska/claude-elixir-phoenix★ 573same name
- dedalus-labs/wingman★ 181same name
- Hassaan146/claude-skills★ 18same name
- shahshrey/unclaw★ 17same name
- ArcticFox2029/chamnan★ 10same name
- nmhjklnm/yaohe★ 9same name
- anotherben/claude-harness★ 7same name
- anis-dr/skills★ 3same name
- Hussain-Elfalah/Agentic-Skills★ 2same name
- jbaruch/nanoclaw-host★ 2same name
7 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 repository71 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- docs/llms.txtllms.txt
- llms.txtllms.txt
- agent-fitnessSkill
- body-checkSkill
- briefSkill
- capsule-compactSkill
- closeSkill
- codex-adapterSkill
- cognitive-updateSkill
- comms-summarizeSkill
- compact-noteSkill
- context-capsuleSkill
- context-hygieneSkill
- critique-planSkill
- decideSkill
- deep-reconSkill
- DiagnoseSkill
- digestSkill
- dreamSkill
- EnvelopeSkill
- find-weaknessSkill
- First 10 MovesSkill
- first-winSkill
- frontend-slidesSkill
- Honesty CheckSkill
- humanize-docsSkill
- impeccableSkill
- learn-from-failureSkill
- LearnSkill
- memory-bridgeSkill
- meta-improveSkill
- meta-improve-vaultSkill
- nightly-close-paritySkill
- nightly-ledger-captureSkill
- nightlySkill
- openSkill
- operator-setupSkill
- orientSkill
- pauseSkill
- ponytailSkill
- port-specSkill
- reconcileSkill
- research-deepSkill
- resumeSkill
- Sandbox RoutingSkill
- scout-vaultSkill
- Self-ReviewSkill
- semantic-searchSkill
- setupSkill
- ship-adapterSkill
- Skill AuditSkill
- skill-huntSkill
- skill-recallSkill
- solution-huntSkill
- sprite-specSkill
- startSkill
- statusSkill
- StuckSkill
- supersedeSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
9 rules. 0 are common, 7 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 15 edited versions we read keep these.
7
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
- Distinctive: line 18
Use on prompts like: "/promote", "promote that", "make a note that", "save that insight", "elevate to doctrine", "capture this …
- Distinctive: line 24
Ask: which part of the conversation should become durable?
- Distinctive: line 26
If the principal points to specific turns ("the last 10 messages about X"), use those.
- Distinctive: line 27
Default to the last 5-10 turns AND any explicitly-referenced earlier exchanges
- Distinctive: line 28
If unclear, ask one focused question: "Promote the {topic A} discussion or the {topic B} discussion?"
- Distinctive: line 43
If the slice is about multiple categories, produce multiple artifacts.
- Very specific: line 60
Use the appropriate vault note structure (frontmatter with title/tags/created/aliases, then content).
- Distinctive: line 80
If the principal says yes, append a one-line entry to the appropriate MOC or to MEMORY.md.
- Very specific: line 84
If the promoted artifact reflects a decision (not just an insight), also append a one-line entry to vault/memory/DECISION_LOG.md:
“Common” is measured: kept by at least 6 in 10 of the 15 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
Promote
The conversation is a substrate. Most of what happens in it is ephemeral — task-specific, session-bound, useful in the moment and gone after. But some exchanges produce durable insights: a new architectural understanding, a person fact worth remembering, a doctrine pattern emerging, a decision that should be logged.
Without /promote, those insights live in the conversation transcript and decay. With /promote, the principal can elevate them to vault content the framework will surface in future sessions.
When to use
- The conversation produced an insight that should outlive this session
- The principal said "we should remember that" or "make a note that…"
- A doctrine pattern is starting to emerge from the discussion
- A new person, project, or concept came up that needs a vault entry
- Use on prompts like: "/promote", "promote that", "make a note that", "save that insight", "elevate to doctrine", "capture this conversation", "remember that we decided", "this should be a vault note"
How to execute
Step 1 — Identify the slice to promote
Ask: which part of the conversation should become durable?
If the principal points to specific turns ("the last 10 messages about X"), use those. Otherwise:
- Default to the last 5-10 turns AND any explicitly-referenced earlier exchanges
- If unclear, ask one focused question: "Promote the {topic A} discussion or the {topic B} discussion?"
Step 2 — Categorize the artifact
Map the slice to a vault category:
| If the slice is about... | Promote to... |
| A new concept, doctrine, or pattern | vault/concepts/{slug}.md |
| A person (collaborator, advisor, contact) | vault/people/{name}.md |
| A project (current or new) | vault/projects/{slug}.md |
| A decision with reasoning | append entry to vault/memory/DECISION_LOG.md |
| A learning sweep on a tool/framework | vault/concepts/learning/{slug}.md (use /learn instead) |
| A person/process rejection with reasoning | append entry to vault/concepts/What I Am Not Building.md |
If the slice is about multiple categories, produce multiple artifacts. Don't bundle.
Step 3 — Extract the durable content
From the conversation slice, extract:
- The insight or fact (the load-bearing claim)
- The reasoning that led to it (why this is true / matters)
- The context (what triggered the conversation)
- Open questions (what's NOT yet resolved)
Drop:
- Conversational noise ("good point", "right", "that makes sense")
- Tool calls and intermediate exploration that doesn't matter to the conclusion
- Prior context that's already in other vault notes (link to those instead)
Step 4 — Write the artifact
Use the appropriate vault note structure (frontmatter with title/tags/created/aliases, then content). Cross-link to existing notes that the slice references.
Step 5 — Confirm and link
Output:
✅ Promoted to vault/{path}.md
Cross-references added:
- [[Existing Note 1]]
- [[Existing Note 2]]
Open questions captured:
- {question 1}
- {question 2}
Update [[MOC]] or [[MEMORY]] if this is high-signal? (y/n)If the principal says yes, append a one-line entry to the appropriate MOC or to MEMORY.md.
Step 6 — Optional: append to DECISION_LOG
If the promoted artifact reflects a decision (not just an insight), also append a one-line entry to vault/memory/DECISION_LOG.md:
- 2026-04-27: {decision summary} → see [[promoted-artifact]]This will trigger the decision-aging loop ([[Cost of Confidence]] sister doctrine) and surface 30/60/90-day check-ins via /open.
What this skill is NOT
- Not a transcript saver. The daily note (
/closeartifact) handles that./promoteis for selective elevation. - Not a summarizer.
/promoteextracts insights; it doesn't condense a long conversation. If the slice doesn't have a durable insight, don't promote — just let it stay in the transcript. - Not automatic. The principal decides what graduates. Auto-promotion would dilute the vault.
Anti-patterns this prevents
- Insights captured in chat transcripts that nobody reads later
- The principal saying "we already discussed this" but not knowing where
- Decisions made in conversation that don't make it to DECISION_LOG → lost reasoning
- Doctrine emerging in real-time but never crystallizing into a vault note → never applied
Connects to
/close— writes the daily note (transient outcome record)/learn— sister skill for tool/framework evaluations specifically/decision-log(forthcoming) — sister skill for decisions specifically- [[Self-Improving CLAUDE.md]] — the broader pattern of converting conversation to durable rules
- [[Legibility Thesis]] — the meta-doctrine that demands ephemera become legible artifacts
vault/memory/MEMORY.md— the index that gets updated when promoted artifacts are high-signal
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.

