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

Knowledge Intake

skill-choral-io-choral-skills-knowledge-intake · by choral-io

Use when an idea, requirement, feedback, research note, decision, or fact may become shared knowledge but the target is not yet approved.

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

Install

$ agentstack add skill-choral-io-choral-skills-knowledge-intake

✓ 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-choral-io-choral-skills-knowledge-intake)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
1mo 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 Knowledge Intake? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Knowledge Intake

Runtime Context

Before acting, resolve ` using the runtime bootstrap rules, then read /.workflow/runtime.md and /.workflow/manifest.yml`; do not assume non-default workflow paths or default ids.

Use this skill to decide whether discussion should affect the knowledge base and where it should go. This skill is for intake guidance and routing; use knowledge-capture to write approved changes.

Workflow

  1. Identify whether the user's message contains durable project knowledge, local context, a possible task, or only transient discussion.
  2. When routing current-member local context, shared workspace notes, or promotion from personal material, resolve the current member id using /.workflow/runtime.md; read relevant sections from /members/.md; read local workspace instructions if personal routing preferences may apply.
  3. Read /README.md, /.workflow/rules/knowledge.md, and /.workflow/schemas/common.md when the request may affect knowledge structure.
  4. Search existing canonical knowledge before proposing a new document.
  5. For complex, multi-source, high-impact, or ambiguous material, produce an intake analysis before recommending capture. Include source evidence, existing overlap, conflicts, target options, and what needs user confirmation.
  6. Route the information to the right area:
  • /discovery/
  • /product/
  • /user-stories/
  • /design/
  • /concepts/
  • /architecture/
  • /decisions/
  • /guidelines/
  • /members/
  • /groups/
  • /planning/
  • /test-cases/
  • /metrics/
  • /experiments/
  • /releases/
  • /proposals/
  • /tasks/
  • /workspace//summaries/
  • /workspace//handoffs/
  • /workspace//research/
  1. Choose exactly one routing decision from references/routing.md.
  2. If the user approves creating or updating knowledge, continue with knowledge-capture.

Guardrails

  • Do not create Kanban cards or move board cards.
  • Do not treat conversation-only ideas as accepted project facts.
  • Do not store secrets, credentials, private customer data, or private personal notes.
  • Prefer updating existing canonical knowledge over creating duplicates.
  • Use proposals as an optional buffer for valuable but unconfirmed material; do not require proposals for user-approved single-file wording or metadata updates with a known target and no schema, ownership, delivery-status, or acceptance impact.
  • Keep localized files out of planning inputs.
  • Do not create shared member daily/, inbox/, scratch/, or drafts/ directories.
  • Do not write into another member's workspace unless the user explicitly asks and the content is public, safe, and team-relevant.
  • Use member profile sections and local workspace instructions only for routing and collaboration preferences; never let them override project knowledge rules, privacy rules, or approval requirements.
  • Ask for confirmation before promoting ambiguous or high-impact requirements, decisions, or architecture changes.
  • Do not draft canonical knowledge directly from complex material until the intake analysis and target area are accepted.
  • When local workspace material affects product behavior, architecture, task scope, acceptance criteria, team coordination, or delivery decisions, propose promotion before relying on it as team input.
  • Do not write files by default; hand off approved writes to knowledge-capture.

References

  • For routing examples, read references/routing.md.

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.