AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Ideas

skill-kriscard-skills-ideas · by kriscard

>-

No reviews yet
0 installs
49 views
0.0% view→install

Install

$ agentstack add skill-kriscard-skills-ideas

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-kriscard-skills-ideas)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
3mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Ideas? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Ideas Capture

Get ideas out of your head and into the vault immediately. Low friction is the whole point — capture first, organize later. The Inbox is the landing zone.

Quick Capture (single idea)

Write to inbox immediately, no questions:

obsidian create path="0 - Inbox/idea-$(date +%Y%m%d-%H%M).md" content="..."

Frontmatter to add:

---
type: idea
captured: YYYY-MM-DD HH:MM
context: 
tags: [idea]
---

After capturing, ask ONE optional follow-up:

> "This looks like a [project / area / resource] idea — want a full project note now, or just inbox > for later?"

Only ask if the answer isn't already obvious. If they say "just capture it", stop there.

Idea Extraction from Conversation

When the conversation contains multiple ideas scattered through the discussion:

  1. Identify all distinct ideas — don't lump unrelated things together
  2. Group related ideas into clusters (same problem space, same project, same technology)
  3. Write one note per cluster — related ideas together, unrelated ideas separately
# One note per distinct cluster
obsidian create path="0 - Inbox/idea-$(date +%Y%m%d-%H%M)-.md" content="..."

Present the clusters to the user before writing, in case grouping is wrong.

When to Suggest a Project Note Instead

If the idea clearly has:

  • A concrete outcome ("build X", "ship Y", "learn Z")
  • An implicit deadline or urgency

...ask: "This sounds like more than an idea — want me to set up a project note in 1 - Projects/?" Then hand off to the project skill if yes.

Naming Convention

  • Single idea: idea-YYYYMMDD-HHMM.md
  • Named idea: idea-YYYYMMDD-HHMM-.md
  • Extracted cluster: idea-YYYYMMDD-HHMM-.md

Keep slugs short (2–3 words max). The timestamp is the primary identifier.

Promote Mode — Graduate Daily Note Ideas

When the user wants to promote ideas from daily notes to permanent notes:

Step 1 — Scan the last 14 days of daily notes

obsidian read path="2 - Areas/Daily Ops/YYYY/YYYY-MM-DD.md"  # repeat for each day

Explicit signals: #idea, #expand, "I should write about", named concepts, unresolved [[links]]

Implicit signals: high-energy paragraphs (longer, stronger language), original frameworks, recurring themes across 3+ days, questions that keep reappearing

Not candidates: tasks, meeting logistics, things with existing standalone notes

Step 2 — Cross-reference existing vault

For each candidate:

obsidian search query="" format=json

Categorize: New concept (no note exists) / Underdeveloped (thin note) / Already covered (skip) / Recurring unresolved [[link]] (high priority)

Step 3 — Present candidates table

| # | Idea | Source | Days Mentioned | Status | Recommendation | | --- | ---- | ------ | -------------- | ------ | -------------- |

Include for each: 1–2 sentence summary, exact quote from daily note, what it connects to in vault.

Step 4 — Graduate selected ideas

Always ask before creating or modifying files.

For new notes: place in 3 - Resources/ (concept), 1 - Projects/ (actionable + deadline), 2 - Areas/ (ongoing interest). Write as mini-essay (3–8 paragraphs) with core claim, context from daily notes, [[backlinks]], open questions. Go back and add [[links]] in source daily notes.

For enriching existing: read note, add dated section, add backlinks, update source daily note links.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.