unbroker

Autonomously remove your info from data-broker sites.

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./optional-skills/security/unbroker/SKILL.md

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a highly actionable, well-sequenced, and well-factored reference for a complex multi-step skill, with concrete commands, validation checkpoints, and properly organized bundle files; its only real weakness is length and some redundancy of the autonomy rules across sections.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and command-driven with little basic-concept padding, but it is a very long body where the autonomy rules are restated across the 'Autonomy contract', 'Procedure', and 'Pitfalls' sections and could be tightened; it is not lean enough to earn the top anchor.	2 / 3
Actionability	Provides a full command-reference table with exact `$PDD` commands, flags, and copy-paste-ready examples (e.g. `PDD="python3 scripts/pdd.py"`, the intake and dry-run commands), matching the fully-executable top anchor.	3 / 3
Workflow Clarity	The 8-step 'Procedure (the autonomous loop)' is explicitly sequenced with a while-loop, validation checkpoints (`doctor`, consent gate, `confirmed_removed` only after a verifying re-scan), and feedback loops for blocked sites, satisfying the top anchor for a batch/destructive workflow.	3 / 3
Progressive Disclosure	SKILL.md is an overview with well-signaled one-level-deep references (methods.md, site-playbooks.md, state-machine.md, brokers/.json, legal/.md), all verified to exist, with content appropriately split and easy navigation, matching the top anchor.	3 / 3
	Total	11 / 12 Passed

Description

47%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is accurate and distinctive but terse: it conveys the core purpose in a single clause while omitting explicit use-when triggers, natural keyword variations, and multiple concrete actions, and it uses second-person ('your') voice.

Suggestions

Add an explicit 'Use when...' clause with natural triggers such as 'opt out of data brokers', 'delete me from Spokeo/Whitepages/people-search sites', or 'clean up after a doxxing'.

Name multiple concrete actions (find exposed info, submit opt-outs/deletion requests, verify removal, schedule recurring re-scans) rather than the single verb 'remove'.

Rewrite in third person (e.g., 'Removes a person's information from data-broker and people-search sites') to avoid the second-person 'your'.

Dimension	Reasoning	Score
Specificity	Names the domain and a single action ('remove your info from data-broker sites') but lists only one action, not multiple concrete ones; additionally 'your' is second-person voice, which per the rubric reduces the specificity score by 1 from its base of 2.	1 / 3
Completeness	It states what the skill does ('Autonomously remove your info from data-broker sites') but includes no 'Use when...' or equivalent explicit trigger guidance, capping completeness at 2 per the rubric.	2 / 3
Trigger Term Quality	'data-broker sites' is a relevant term a user might say, but common natural variations users actually use ('opt out', 'delete me from Spokeo/Whitepages', 'people-search sites') are absent from the description.	2 / 3
Distinctiveness Conflict Risk	The niche is clear and narrow (data-broker / people-search removal), with distinct triggers unlikely to be confused with other skills, matching the anchor for a clear distinct niche.	3 / 3
	Total	8 / 12 Passed

Validation

75%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 12 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 1 missing, 2 deeper-than-1-level	Warning

	Total	12 / 16 Passed

Repository: NousResearch/hermes-agent
Path: optional-skills/security/unbroker/SKILL.md
Commit: 4c9628e

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.