← All skills
capture
Use when the user dumps a chaotic stream of thoughts, tasks, or ideas and wants it turned into a structured, actionable summary with nothing dropped.
About this skill
Use when the user dumps a chaotic stream of thoughts, tasks, or ideas and wants it turned into a structured, actionable summary with nothing dropped.
SKILL.md
capture.SKILL.mdPlace it in your Syntic skills folder. For Syntic Code, install in your local skills directory, review the contents and run it in a controlled environment first.
---
name: capture
description: Use when the user dumps a chaotic stream of thoughts, tasks, or ideas and wants it turned into a structured, actionable summary with nothing dropped.
category: Productivity
version: 1.0.0
tools: []
---
# Capture — Brain-Dump Organizer
Transform unstructured streams of mixed thoughts, tasks, and ideas into a clean four-section actionable system with zero information loss. Fast-to-action by design — no upfront intake.
## Invocation Triggers
**Explicit phrases:** "brain dump," "capture this," "let me dump some ideas," "I've got a bunch of thoughts," "here's everything on my mind," "idea dump," "let me just get this out of my head," "I need to organize my thoughts," "here's what I'm thinking."
**Implicit signals (no phrase needed):** the user pastes or dictates a long unstructured block of mixed ideas, tasks, plans; multiple unrelated thoughts in one message without organizing framing; a wall of bullet-y text covering 3+ unrelated topics.
When you detect an implicit trigger, run the skill directly. Do NOT ask "do you want me to organize this?" first — the dump itself IS the request.
## Operating Principles (All Five Apply Always)
1. **Capture everything.** Zero loss. Trivial items go in; the user prunes later. Never silently drop something because it "seemed unimportant."
2. **Preserve voice.** If the user said "build something crazy with AI," do NOT restate as "Explore innovative AI-driven solutions." Keep the energy and the casual register.
3. **Match output complexity to input.** A 5-task dump does NOT get forced into 4 elaborate sections — use the Compressed Output Pattern below.
4. **Be honest about ambiguity.** If you're unsure what something means, flag it. Don't guess silently.
5. **No action without approval.** The ONLY immediate action is the organization itself. Every offer in Section 4 waits for the user's explicit pick.
## Grill-Me Mid-Organization Clarifier
No upfront intake — the dump is enough to start organizing immediately. The grill-me discipline applies as a **single mid-organization clarifying question**, asked **only when** one item in the dump is genuinely ambiguous between *task* and *project*, and the misclassification would meaningfully change the output:
> **Quick clarification — one item in your dump could go either way. Is [X] a one-shot task or a multi-step project?**
> *Why I'm asking:* If I guess wrong on a borderline item I either bury a project as a task or inflate a task into a project that doesn't need the structure.
**Stop condition:** max 1 clarifying question per dump. If the dump is unambiguous, skip the clarifier entirely. Asking 3+ questions up front breaks the dump-and-organize flow that makes capture useful.
## Section 1: Projects & Ideas
Cluster related items into themed projects when natural clustering exists. This section also holds standalone creative sparks, half-formed concepts, "what if" thoughts, and embedded decisions (`Decide: X or Y`) and open questions (`Q: ...`) kept WITHIN the relevant project — not extracted into a separate top-level category.
```
### {Project name in user's voice}
- {component / sub-idea}
- Q: {open question this project needs answered}
- Decide: {decision this project requires}
```
Use the user's words for the project name. If the user wrote "ai dating app for ferrets," do NOT rename it to "AI-Powered Pet Companion Platform."
## Section 2: Tasks
Flat, scannable, action-oriented: explicit todos, decisions framed as `Decide: ...`, open questions framed as `Resolve: ...`. If a task belongs to a project from Section 1, append `[Project: X]` to link it without repeating the project's context.
## Section 3: Connections
This is where the skill earns its keep — and where **fabrication is forbidden**.
1. **Inventory what's available** — search the Knowledge Base for content matching dump keywords and themes.
2. **Match dump items to existing content** — prior thinking, in-progress work, overlapping material.
3. **Surface dependencies within the dump** — items that affect each other, themes, ordering implications.
4. **Be honest about inaccessibility** — if there's nothing to search against, say so explicitly. Do NOT make up plausible-sounding connections.
**Hard rule:** NEVER fabricate connections. Only surface ones actually found by search. If none exist: "**Connections:** No connections found." If nothing is searchable: "**Connections:** Nothing accessible to cross-reference here — want to share more context or @mention a teammate who'd know?"
## Section 4: How I Can Help
**Concrete offers, not abstract possibilities.** Every offer specifies what would be produced and how it would be delivered.
Right pattern: "I can research integration options and give you 3 choices, delivered here in chat." Wrong pattern: "You might want to look into integration approaches."
End with the directive question: **Which of these should I tackle?**
## Compressed Output Pattern
When the dump has **5 or fewer items** and items are **unrelated** (no natural clustering), drop the 4-section format:
```
## What I heard
- {item}
- {item}
## How I can help
- {concrete offer with what + how delivered}
Which should I tackle?
```
Use judgment on when a dump is small/simple enough for this format versus the full four sections.
## Approval Gate
After the sections are delivered, wait for the user's explicit pick before doing anything else. If the user says "go" without picking a specific offer, honor it, but explicitly note any items you weren't 100% sure about so they can correct. The organization itself is the only auto-action — every Section 4 offer requires a green light.
## Error Handling
| Situation | Behavior |
|---|---|
| Nothing to cross-reference | State this; skip Section 3 or note nothing accessible |
| Dump is very short (3-5 items) | Use compressed output; don't force 4 sections |
| Items are highly ambiguous | Flag in output, ask up to 1 clarifier (or surface ambiguity in delivery) |
| Dump contains sensitive info | Acknowledge but don't echo verbatim unless organization requires it |
| Conflicting items in the dump | Surface the conflict explicitly (`Conflict: X says A, Y says B`) |
| User says "go" before approval | Honor it, but explicitly note items you weren't sure about |
## Anti-Patterns To Reject
- Fabricating connections that weren't actually verified
- Dropping items deemed "trivial" — capture everything, let the user prune
- Corporate-ifying the user's casual language
- Forcing 4-section structure when input is small
- Acting on Section-4 offers immediately without approval
- Splitting decisions/questions into a separate top-level category instead of embedding them in the relevant project
- Vague Section-4 offers ("you might want to consider…")
- Asking 3+ clarifying questions up front (breaks fast-to-action)
Install
Syntic App
- 1Create a dedicated folder for this skill in your local skills library.
- 2Place SKILL.md into that folder.
- 3Restart Syntic and invoke this skill on matching tasks.
Syntic Code (CLI)
- 1Save SKILL.md in your local Syntic Code skills directory.
- 2Keep related files in the same skill folder.
- 3Run in a safe environment and validate outputs.