AgentStack
SKILL verified ISC Self-run

Source Grounding

skill-danielleit241-my-skills-source-grounding · by danielleit241

>

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

Install

$ agentstack add skill-danielleit241-my-skills-source-grounding

✓ 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.

Are you the author of Source Grounding? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Source Grounding

Use sources when correctness depends on current or version-specific behavior. Local code is the primary source for this repo; official docs are the primary source for external APIs and frameworks.

Process

  1. Detect the version and surface:
  • package lock, config, imports, CLI output, SDK version
  • runtime, framework, database, provider, or protocol
  1. Choose source tier:
  • repo source and tests for local behavior
  • official docs or API reference for external behavior
  • release notes or migration guides for version changes
  • source code/types when docs are incomplete
  1. Record a source note:
  • claim
  • source path or URL
  • version/date if available
  • confidence
  • what remains unverified
  1. Apply the finding narrowly:
  • update the plan, phase brief, implementation, or review package
  • do not paste long docs into artifacts
  • mark any unsourced assumption explicitly

Source Note

## Source Grounding

Claim: {behavior or API decision}
Source: {repo path, official docs URL, type definition, release note}
Version: {detected version or unknown}
Confidence: {high | medium | low}
Unverified: {none or remaining uncertainty}

Red Flags

  • Using remembered API syntax for a library version not checked locally.
  • Treating blog posts or examples as authoritative over official docs.
  • Ignoring local wrappers or project conventions.
  • Updating code from docs without checking installed version.
  • "Probably works" appears in a plan, review, or completion claim.

Verification

  • [ ] Version or local source was checked when relevant.
  • [ ] External claims use official or primary sources.
  • [ ] Unverified assumptions are labeled.
  • [ ] The final artifact cites the source note briefly.

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.