Pearl1531Pearl1531/Archetype-talk/.claude/skills/source-sync/SKILL.md

source-sync

Skill2 starsChanged 47 days agoMITView on GitHub

Connect read-only research sources beyond Dovetail — voice memos (Grain, Fireflies, Otter, tl;dv, Zoom), Notion, Confluence, Capacities, Maze, UserTesting, Lookback. Use when importing research from a tool without a dedicated skill.

1 other project uses a version of this.

Adopted by

Most recently taken up by

thiagofinch/mega-braintheir own version, first seen Oct 8, 2026

Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
thiagofinch/mega-brain★ 95same 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 repository31 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- affinitySkill
- ai-personaSkill
- analytics-syncSkill
- backlogSkill
- catalogSkill
- cold-startSkill
- contradictionsSkill
- demo-dataSkill
- dovetail-syncSkill
- exportSkill
- extract-findingsSkill
- feature-panelSkill
- forget-participantSkill
- graph-lintSkill
- interview-guideSkill
- journey-mapSkill
- opportunity-treeSkill
- persona-avatarSkill
- persona-querySkill
- persona-talkSkill
- persona-voiceSkill
- persona-workshopSkill
- prdSkill
- prioritizeSkill
- researcherSkill
- retentionSkill
- subject-accessSkill
- welcomeSkill

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Very specific:
Read-only: Only search_* / get_* / list_*-shaped tools.
line 36
Distinctive:
No fabrication: Import only what the source returns.
line 38

≈ “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

source-sync — Generic read-only research source connector

One pattern, many sources. dovetail-sync proved the shape: external tool = read-only source, our graph = canonical. This skill applies the same shape to everything else, so adding a new source means writing one mapping reference, not a new skill.

External tool (source)  ──read-only──▶  our graph (canonical)

Trigger

/source-sync                    ← list supported sources, ask which to connect
/source-sync <source>           ← e.g. /source-sync grain, /source-sync notion
/source-sync --setup <source>   ← connection walkthrough only

Supported source families (one reference each — load only the relevant one)

Family	Tools	Maps to	Reference
Voice memos & call recordings	Grain, Fireflies, Otter, tl;dv, Zoom; raw voice memo files	`Inbox/` → `Transcripts/`	references/voice-memos.md
Docs & wikis	Notion, Confluence	`Transcripts/` or `Evidence/` (per item)	references/docs-wikis.md
PKM apps	Capacities (Markdown export or API)	`Inbox/` → `Transcripts/` or `Evidence/`	references/capacities.md
Usability testing	Maze, UserTesting, Lookback	`Signals/` + `Evidence/`	references/usability-tools.md

Analytics tools (Mixpanel, GA4, Amplitude) have their own skill — /analytics-sync. Dovetail keeps its dedicated skill — /dovetail-sync.

Universal rules (inherited from dovetail-sync — apply to every source)

Never handle secrets in chat. Prefer OAuth/browser sign-in via the tool's official MCP server; tokens live in the MCP client's own config, never in files or chat. MCP servers and their auth flows drift — check the tool's live docs at setup time instead of assuming.
Read-only. Only search_* / get_* / list_*-shaped tools. Never call anything that writes to the source.
Confirm before writing our files. Show a mapping plan (source item → target file → type), get a yes.
No fabrication. Import only what the source returns; thin items import thin.
Provenance always: source: <tool>, a stable source id, and a deep link where one exists — so items are traceable and re-syncable (match by id on re-sync, update in place, never duplicate).
The Signal/Evidence line holds: an observation from OUR OWN session (whatever tool recorded it) → Transcripts/ then /extract-findings → Signals. Someone else's published/aggregated data → Evidence/. When ambiguous, ask — never guess an item into Signal status.
Our schema is canonical. Map into our types; if something doesn't fit, ask — don't bend the folder structure to mirror the tool.

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.

Check your setup, free