CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

sherlock

Find accounts for a username across 400+ platforms.

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./optional-skills/security/sherlock/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

81%Weight 40%Scale 1-5

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

The body is highly actionable with a complete, validated workflow and strong error-recovery guidance. Its weaknesses are repeated installation instructions across three sections and reference-worthy content (Installation, Pitfalls) inlined in a fairly long single file.

Suggestions

Consolidate the three copies of install instructions (Requirements, step 1, Installation section) into one place and reference it from the others.

Drop the duplicated "Example terminal call" JSON block or the repeated default command in step 3 — one of the two suffices.

Move the Installation and Pitfalls sections into a reference file (e.g. INSTALL.md / TROUBLESHOOTING.md) to keep SKILL.md a lean overview.

DimensionReasoningScore

Conciseness

Installation instructions are repeated three times (Requirements, step 1's install offer, and the dedicated Installation section with the same pipx/pip/Docker commands), and the "Example terminal call" JSON block duplicates the step-3 command. This is mostly efficient but with several redundant sections that could be tightened, matching anchor 3 rather than the minor-trim case of anchor 4.

3 / 5

Actionability

The skill provides an exact default command with flags ("sherlock --print-found --no-color \"<username>\" --timeout 90"), an executable example terminal call, concrete output-parsing examples, and a full worked example interaction with a response format. Everything is copy-paste ready and covers the common cases, matching anchor 5.

5 / 5

Workflow Clarity

A clear 5-step sequence (install check, username extraction, command build, execute, parse/present) is paired with an explicit Verification checklist and a Pitfalls section with error-recovery guidance for no results, timeouts, Tor, false positives, and rate limiting. The operation is a read-only single search, so the batch/destructive cap does not apply.

5 / 5

Progressive Disclosure

The body is a single well-sectioned SKILL.md with no bundle files and clear headers, so navigation is easy and references are one level (none). However, at ~180 lines, the Installation and Pitfalls sections are content that could be split into reference files to keep the overview lean, matching anchor 4's minor organization gaps rather than a lean overview.

4 / 5

Total

17

/

20

Passed

Description

53%Weight 40%Scale 1-5

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 states a single clear capability concisely but omits any 'when to use' trigger guidance and the natural synonyms users would say (social media, OSINT, username availability). It is specific enough to avoid most conflicts but under-serves discoverability.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks to find social media accounts for a username, check username availability, or conduct OSINT/username reconnaissance."

Include natural synonyms such as "social media", "OSINT", and "username search" so the skill triggers on the phrasings users actually say.

Optionally mention a second concrete action (e.g. checking username availability) to raise specificity coverage.

DimensionReasoningScore

Specificity

The description names a concrete action ("Find accounts") and the domain ("username", "400+ platforms"), matching the anchor for 1-2 concrete actions without comprehensive coverage. It does not list multiple actions needed for a 4.

3 / 5

Completeness

The "what" is clear (find accounts for a username across platforms), but there is no "Use when..." clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

"accounts", "username", and "platforms" are relevant keywords, but common user phrasings like "social media", "OSINT", or "check username availability" are missing. This matches the anchor for some relevant keywords with missing variations.

3 / 5

Distinctiveness Conflict Risk

Cross-platform username search is a fairly niche purpose with only minor overlap risk against general search/recon skills. It falls short of anchor 5's clear niche with distinct triggers because the description lacks the trigger phrasings that would lock in the niche.

4 / 5

Total

13

/

20

Passed

Validation

81%

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

Validation — 13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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

Total

13

/

16

Passed

Repository

NousResearch/hermes-agent

Path

optional-skills/security/sherlock/SKILL.md

Reviewed

Table of Contents

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.