Index of every page on this site: llms.txt
All skills
agricidaniel avatar

/ads-validate

@fc3908e
by Agrici Danielagricidaniel/claude-ads11k stars
1,609
Run it yourself

Validate Claude Ads contracts, scoring inputs, run bundles, capabilities, source freshness, safety, installation, uninstall, or release readiness. Use for ads validate, ads status, ads next, maturity checks, ownership-manifest uninstall, preserving unrelated ads-* skills, checksum verification, preflight, QA, or release audits.

Use this Skill: https://skilld.dev/gh/agricidaniel/claude-ads/ads-validate

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈86 tokens for metadata: the name and description. ≈443 when used: this file.

Description uses 4.3% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈344 characters, or 4.3%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

Validate Claude Ads

Choose the narrowest validation target:

  • Contract or bundle: use the deterministic core validator.
  • Scores: validate controls, findings, category weights, and coverage.
  • Run: verify manifest completeness, source lineage, privacy, worker status, and render artifacts.
  • Capability: require implementation, fixtures, tests, sources, and truthful mode.
  • Repository: run deterministic, routing, security, installer, rendering, evidence, packaging, and freshness gates.
  • Release: dispatch a fresh-context release verifier.

Return machine-readable pass/fail results, the highest-priority blocker, exact evidence, and recovery steps. Never promote maturity because documentation is polished or a prior release passed. Stale evidence and skipped remote CI demote readiness.

Reverify-or-demote decisions belong to ads-research. If an expired claim cannot be reverified because source or filesystem access is unavailable, return a failed current-evidence check, demote that claim for the current run, and block dependent release-current assertions before asking for the missing access.

Install and uninstall validation

An uninstall may remove only exact paths in the matching Claude Ads ownership manifest. Validate the entire manifest and configured root boundaries before any deletion. If the manifest is absent, invalid, mismatched, or unsafe, stop before deleting anything and require manual review. Never discover targets with an ads-* glob; unrelated skills such as ads-weather must remain untouched.

Reject pipe-to-shell install instructions. A safe install uses the host's native installer or a locally inspected checkout/archive; archives require a SHA-256 checksum verified against a trusted release channel before execution.

Source: SKILL.md on GitHub

No rule matched.

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No alerts1mo3 checks · Risk SAFE
  • Gen Agent Trust Hub1mo

    This skill provides instructions for an agent to validate Claude Ads artifacts such as contracts, manifests, and installation bundles. It emphasizes security best practices, including checksum verification for archives, manifest-based boundaries for file operations, and the rejection of insecure installation methods. No malicious patterns were detected.

  • Socket1mo

    No alerts

  • Snyk1mo

    Risk: LOW · No issues

Signed by skilld at fc3908e. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub last month.

Activeupdated last month

README badge

README badge for agricidaniel/claude-ads/ads-validate