humanize-text-en Eval
=====================

Status: review
Score: 69/100
Risk: medium
Decision: manual_review
Policy: review
Reason: Require human approval before installing into a real workspace.

Install:
npx skills add fernandotellado/ai-skills --skill humanize-text-en

Required checks:
- PASS Task fit: Task wording matches this skill metadata.
- PASS Install path: Install handoff is available.
- PASS Install command safety: standard package or runtime install path
- WARN Trust score: Potentially useful, but at least one trust signal needs human inspection.
- WARN Audit score: Needs review
- WARN Agent safety gate: Usable candidate, but the agent should surface permission and audit notes before installation.
- PASS License clarity: GPL-2.0-or-later
- PASS Permission surface: filesystem or document access

Warnings:
- Trust score: Potentially useful, but at least one trust signal needs human inspection.
- Audit score: Needs review
- Agent safety gate: Usable candidate, but the agent should surface permission and audit notes before installation.
- SKILL.md does not define an explicit step-by-step workflow for applying the humanization rules, such as read -> identify patterns -> rewrite -> verify.
- references/phrases.md says the list is not an absolute ban, but then labels a section 'Hard-banned words' and says they should be avoided entirely. This internal contradiction may cause inconsistent application.
- The 'Hard-banned' list includes normal English words like 'albeit', 'indeed', and 'certainly' that are not inherently AI-sounding; treating them as hard bans may over-correct natural prose.
- Low GitHub adoption signal
- Quality score needs review
- GitHub adoption: 40 GitHub stars
- Stars/forks activity: 40 stars, 6 forks; issue activity unavailable in current metadata

Validation plan:
1. Inspect repository, README/SKILL.md, license, and recent commits before production use.
2. Install in an isolated workspace or sandbox with no production secrets available.
3. Run the smallest representative task and record files touched, commands run, network access, and outputs.
4. Compare the selected skill against at least one alternative when the eval status is review or failed.
5. Promote only after the agent reports a successful verification result and unresolved warnings are accepted.

Do not use when:
- teams that need a vendor-supported SLA
- production agents without a repository review
- Low GitHub adoption signal
- SKILL.md does not define an explicit step-by-step workflow for applying the humanization rules, such as read -> identify patterns -> rewrite -> verify.
- references/phrases.md says the list is not an absolute ban, but then labels a section 'Hard-banned words' and says they should be avoided entirely. This internal contradiction may cause inconsistent application.
- The 'Hard-banned' list includes normal English words like 'albeit', 'indeed', and 'certainly' that are not inherently AI-sounding; treating them as hard bans may over-correct natural prose.
- Quality score needs review
- GitHub adoption: 40 GitHub stars

URLs:
- Skill: https://www.openagentskill.com/skills/fernandotellado-humanize-text-en
- Audit: https://www.openagentskill.com/skills/fernandotellado-humanize-text-en/audit
- JSON: https://www.openagentskill.com/api/agent/evals?slug=fernandotellado-humanize-text-en