Index of every page on this site: llms.txt
All skills
Run it yourself

Audit or design agent-facing product capabilities: action/context parity, discoverable contracts, safe mutations, verifiable outcomes, and recovery. Use for explicit agent-readiness reviews of apps, repos, CLIs, APIs, MCP/A2A integrations, or Agent Skills; not every general code or documentation task.

Use this Skill: https://skilld.dev/gh/tristanmanchester/agent-skills/agent-use

Nothing lands on disk. Nothing to clean up.

Fork this Skill

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

referencesweb-and-docs-readiness.md

≈625 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Web and discovery contracts

Publish only maintained surfaces a real consumer uses. Discovery conventions have different status; do not count every absent filename as a defect.

Surface Status and appropriate use
llms.txt, bounded Markdown documentation Optional documentation convention; neither permission to crawl nor a protocol requirement
robots/sitemap/canonical links Crawl/discovery signals; not authentication or proof of content completeness
/.well-known/api-catalog RFC 9727 API catalog using the specified Linkset representation; link to actual APIs
OAuth/OIDC metadata Use the exact current discovery/authorization contract for the protected resource and issuer
A2A /.well-known/agent-card.json A2A discovery card; its supported interface URL is the service, not the card itself
/.well-known/mcp.json A local example in this package, not a universal MCP discovery requirement
/.well-known/agent-skills/index.json A local index proposal, not required by the Agent Skills file format

For MCP, verify the selected specification/client/transport's actual discovery, initialisation, and authorization behaviour. Do not substitute a fabricated server card for protocol negotiation. Auth metadata is not authorization to obtain or use credentials. Validate issuer/resource relationships and redirect destinations before sending tokens; do not trust arbitrary links inside discovery documents.

Useful documentation exposes stable object IDs, bounded examples, field semantics, side effects, scopes, error/retry handling, dates/versioning, and result verification. Provide compact task-focused pages and a canonical source instead of copying an entire SDK catalogue into each skill. Keep dates and maintenance ownership visible.

Evaluate with real tasks: can the agent find the correct page, authenticate within its existing permission, choose the right operation, and verify the outcome? Measure failures, retries, corrections, and time/context cost. A heuristic discovery score is a lead for inspection, not that evaluation's result.

Sources reviewed 2026-09-13: Agent Skills specification, A2A discovery, RFC 9727. For MCP, read the applicable current official transport/authorization specification at implementation time; no single static well-known filename is assumed here.

Source: SKILL.md on GitHub

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.

1 warning1mo3 checks · Risk SAFE
  • Gen Agent Trust Hub1mo

    The skill 'agent-use' is a comprehensive toolkit for auditing and designing agent-ready systems. It includes documentation, templates, and Python scripts for scanning repositories and websites. Security analysis found no malicious intent; identified network and command execution patterns are aligned with the skill's primary purpose as an auditing tool.

  • Socket1mo

    1 alert: gptAnomaly

  • Snyk1mo

    Risk: LOW · No issues

Signed by skilld at 3323bc9. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 2 weeks ago.

Steadyupdated last month
metadata
{
  "version": "3.0.0",
  "reviewed": "2026-09-13"
}
Other metadata
compatibility
Local helper scripts require Python 3.10+; structural validation also requires PyYAML 6.0.3 or later in major 6. Network and execution checks need separately authorised tools and environments.

README badge

README badge for tristanmanchester/agent-skills/agent-use