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.

referencesreview-recipes.md

≈391 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Review recipes

Full repository audit

  1. Run scripts/audit_agent_use.py --root <repo> --markdown --output agent-use-report.md --json-output agent-use-report.json.
  2. Run scripts/action_parity_inventory.py <repo> --output action-parity-inventory.md --csv-output capability-map.csv for app/tool repos.
  3. Inspect the generated capability map and manually classify high-value workflows.
  4. Open the main routes/controllers/tools/CLI commands and verify implementation-level evidence.
  5. Score only applicable dimensions and produce a prioritized plan.

Pull request review

  1. Identify changed user actions, tool/API/CLI surfaces, prompts, auth/safety code, and docs.
  2. Ask whether each new human action has an agent path and each new agent path has context, safety, and verification.
  3. Do not require full parity for unrelated old code unless the PR worsens it.
  4. Recommend small patches: schema field, JSON output flag, dry-run option, docs link, eval, or capability-map row.

Parallel review

For a large product, split reviewers by principle:

  • Action parity.
  • Context parity.
  • Tool/API/CLI contract quality.
  • Safety/permissions/recovery.
  • Web/docs discovery.
  • Evals/observability.

Merge by capability map, not by file list, so duplicate findings collapse into user-visible workflows.

Acceptance tests for fixes

A fix is done when a fresh agent can discover the surface, choose the right action, provide required context/credentials, execute or preview safely, parse output, verify final state, and recover from one common error.

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