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

/agent-use

@3323bc9
by Tristan Manchestertristanmanchester/agent-skills3 stars
2
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.

CHANGELOG.md

≈561 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Changelog

2.0.0 — 2026-06-29

  • Added web discovery following from Link headers and RFC 9727 Linkset JSON so linked OpenAPI/OAuth/API catalog surfaces count even across origins.
  • Added docs/API/tool web profiles and stopped recommending MCP/A2A cards unless the scanned surface is actually a tool/agent surface.
  • Added evidence provenance and confidence to local repo audits so scanner internals, templates, generated reports, and reference prose no longer count as implementation evidence.
  • Added scanner regression tests for linked web discovery, docs/API profile inference, and keyword-only repo false positives.
  • Fixed stale script references and restored working v2 command names plus v1 compatibility entry points.
  • Fixed validation from the current directory by resolving the skill directory before comparing the frontmatter name.
  • Added Python compilation and script --help validation, JSON resource validation, trigger-query checks, and output-directory creation.
  • Fixed generated-report recursion so self-audits, validation reports, and generated llms.txt drafts are skipped by default by the local audit scanner.
  • Fixed hidden-directory scanning so .well-known and .github are not accidentally missed.
  • Fixed the API catalog template to use RFC-style Linkset JSON rather than an ad-hoc list.
  • Added /.well-known/mcp.json as the primary MCP discovery path while keeping the legacy alternate check.
  • Added profile-aware web scoring so content-only sites are not penalized for API/app-only capability endpoints.
  • Added action parity inventory tooling with Markdown and CSV outputs.
  • Added agent-asset scaffolding for AGENTS.md, llms.txt, web discovery headers, capability maps, API/CLI contracts, permission matrices, API catalog, MCP card, A2A card, skills index, and eval seeds.
  • Added deeper references synthesizing the original Compound ideas: action/context parity, noun test, primitives, shared workspace, dynamic context injection, prompt-native behavior, self-modification guardrails, mobile/offline constraints, and product feedback loops.
  • Expanded guidance across websites/docs, CLIs/TUIs, APIs, SDKs, MCP/A2A/tools, app UIs, files/workspaces, security, evals, and Agent Skill packaging.

Source: SKILL.md on GitHub

Skill behaviors

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.

Third-party checks

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

Provenance

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

Capability

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