CtrlK
BlogDocsLog inGet started
Tessl Logo

honcho

Configure and use Honcho memory with Hermes -- cross-session user modeling, multi-profile peer isolation, observation config, dialectic reasoning, session summaries, and context budget enforcement. Use when setting up Honcho, troubleshooting memory, managing profiles with Honcho peers, or tuning observation, recall, and dialectic settings.

67

Quality

82%

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

SKILL.md
Quality
Evals
Security

Quality

Content

65%

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

A dense, well-structured, and highly actionable reference for Honcho+Hermes configuration, but it is overlong for a SKILL.md overview with notable internal redundancy and no progressive disclosure into separate bundle files.

Suggestions

Consolidate the dialectic cadence/depth/level coverage into one place and have the 'Config Reference' table link to it, eliminating the verbatim repetition.

Move the full Config Reference and CLI Commands tables into a separate reference file (e.g. CONFIG.md) and keep SKILL.md as an overview, improving progressive disclosure and token economy.

Add an explicit validate->fix->retry loop for destructive operations such as conclusion deletion (e.g. verify the deletion via honcho_search/honcho_context afterward).

DimensionReasoningScore

Conciseness

The ~415-line body is mostly efficient and free of concepts Claude already knows, but the dialectic cadence/depth/level material is repeated verbatim across 'Three Orthogonal Knobs' and the 'Config Reference' tables, and the recall/observation/session tables are restated, adding avoidable length.

2 / 3

Actionability

Concrete, copy-paste-ready commands ('hermes profile create coder --clone', 'hermes honcho status'), executable JSON config blocks, and specific tool-call examples with parameters make the guidance fully actionable.

3 / 3

Workflow Clarity

Sequences are clear (Setup with a Verify step, the 3-step 'On conversation start' flow, when-to-call decision trees) and Troubleshooting aids recovery, but there are no explicit validate->fix->retry feedback loops for destructive operations such as honcho_conclude delete_id PII removal.

2 / 3

Progressive Disclosure

Sections and tables are well organized, but the body is a ~415-line monolithic file with no bundle files and only external URL references; the Config Reference and CLI command tables that could live in separate reference files are inlined.

2 / 3

Total

9

/

12

Passed

Description

100%

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

A strong, third-person description that pairs a concrete capability list with explicit 'Use when' triggers and clearly scoped, low-conflict triggers.

DimensionReasoningScore

Specificity

The description enumerates multiple concrete capabilities -- 'cross-session user modeling, multi-profile peer isolation, observation config, dialectic reasoning, session summaries, and context budget enforcement' -- rather than vague language.

3 / 3

Completeness

It explicitly answers both 'what' (the capability list) and 'when' via the 'Use when ...' clause with explicit triggers, satisfying the rubric's highest anchor.

3 / 3

Trigger Term Quality

'Use when setting up Honcho, troubleshooting memory, managing profiles with Honcho peers, or tuning observation, recall, and dialectic settings' covers natural phrasings a user would actually say when they need this skill.

3 / 3

Distinctiveness Conflict Risk

The Honcho-with-Hermes niche and its specific triggers (setup, memory troubleshooting, peer profile management, tuning observation/recall/dialectic) make it unlikely to fire for an unrelated skill.

3 / 3

Total

12

/

12

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.

Validation13 / 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
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.