CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

honcho

Configure and troubleshoot Honcho memory for Hermes.

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/autonomous-ai-agents/honcho/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

78%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 a strong, highly actionable reference: executable commands, complete config examples, cost-aware usage guidance, and a clear setup-with-verification workflow. Its main weaknesses are the total absence of progressive disclosure (a 437-line monolith with a CLI table and config reference that belong in reference files) and a few trimmable changelog-style or redundant sentences.

Suggestions

Move the CLI command table and the config-reference tables into reference files (e.g. references/cli.md, references/config.md) and keep only the most-used commands inline, turning the SKILL.md into a lean overview with one-level-deep, clearly signaled references.

Delete the changelog-style sentence "This fix addresses edge cases where raw user conclusions containing markup or special characters could corrupt the injected context block" — it describes a past change, not guidance.

Close the loop in troubleshooting entries that currently end at diagnosis (e.g. after the 'Honcho not configured' and 'memory not persisting' checks, state what to run or change if the problem persists, mirroring the verify-style feedback loop the Setup section already has).

DimensionReasoningScore

Conciseness

The body is dense reference material Claude cannot know (cadence/depth/level tables, recall modes, tool semantics), mostly free of generic explanations. Minor over-explanation remains: the changelog-style sentence "This fix addresses edge cases where raw user conclusions containing markup or special characters could corrupt the injected context block" and glosses like "You do not need to configure this -- it is automatic based on session state" could be trimmed. Fits 'efficient; minor instances of over-explanation that could be trimmed' rather than the lean 5.

4 / 5

Actionability

Commands are copy-paste ready throughout ("hermes plugins install honcho", "hermes honcho status", "hermes profile create coder --clone", "hermes honcho sync"), config blocks are complete valid JSON, and tool usage comes with concrete good/bad examples ("Prefers code examples over prose explanations" vs "User seems technical"). Setup, daily usage, and troubleshooting cases are all covered with executable guidance.

5 / 5

Workflow Clarity

Sequences are clear and ordered: install → setup wizard → explicit 'Verify' checkpoint with a connection-testing status command, and a numbered conversation-start escalation (profile → context → reasoning) with cost-aware fallbacks. Not a 5 because several troubleshooting entries end at 'check X' without a recovery loop (e.g. what to do if the connection test fails or memory still doesn't persist after the checks).

4 / 5

Progressive Disclosure

No bundle files exist at all — everything is inlined in a 437-line SKILL.md. Internal section structure is good (so not a 2), but substantial reference material belongs in separate files: the 18-command CLI table and the full config-reference tables are exactly the content anchors describe as 'should be separate is inline'. This matches 'some structure but could be better organized' rather than 'most content appropriately placed'.

3 / 5

Total

16

/

20

Passed

Description

57%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 is short, accurate, and highly distinctive thanks to the product names, but it under-sells the skill: it names only two generic actions and entirely omits any 'when to use' trigger guidance or natural trigger phrases (setup, syncing, profiles, recall, tuning). Adding a 'Use when...' clause with concrete triggers would lift completeness and trigger-term quality substantially.

Suggestions

Add an explicit trigger clause, e.g. 'Use when setting up Honcho (cloud or self-hosted), when memory is not persisting or peers are not syncing, when creating multi-profile setups, or when tuning observation, recall, or dialectic settings.'

Enumerate a few more concrete capabilities in the description itself (setup wizard, peer/profile management, recall modes, context budgets) to raise specificity beyond the generic 'configure and troubleshoot'.

Include natural user phrasings as trigger terms — 'remember across sessions', 'user modeling', 'session summary', 'peers not syncing' — so the skill matches how users actually describe the need.

DimensionReasoningScore

Specificity

"Configure and troubleshoot Honcho memory for Hermes" names the domain plus two actions ("Configure", "troubleshoot"), matching the '1-2 concrete actions, not comprehensive' anchor. It does not list the several sub-capabilities the body actually covers (setup, profiles, recall modes, dialectic tuning), so it falls short of a 4.

3 / 5

Completeness

The 'what' is clear (configure and troubleshoot Honcho memory for Hermes) but there is no 'when' / 'Use when...' clause at all, which per the guidelines caps completeness at 3. It fits the anchor 'clear what but when missing or only weakly implied'.

3 / 5

Trigger Term Quality

Keywords present are "Honcho", "memory", "Hermes", "configure", "troubleshoot" — relevant but the natural phrases users would say ("remember across sessions", "peers not syncing", "user profile", "recall", "session summary") are all missing. This matches 'some relevant keywords but missing common variations or synonyms'.

3 / 5

Distinctiveness Conflict Risk

"Honcho memory for Hermes" is a product-specific niche with named products, giving a clear niche with distinct triggers and minimal conflict risk — no other plausible skill would trigger on these terms.

5 / 5

Total

14

/

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/autonomous-ai-agents/honcho/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.