CtrlK
BlogDocsLog inGet started
Tessl Logo

honcho

Configure and troubleshoot Honcho memory for Hermes.

55

Quality

64%

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

71%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 — executable commands, complete config examples, and concrete tool invocations covering all common cases — with a clear setup→verify workflow and symptom→fix troubleshooting. Its weaknesses are duplication between the 'Three Orthogonal Knobs' narrative and the 'Config Reference' tables, and a fully monolithic structure where the config and CLI reference material should live in separate bundle files. Splitting reference material into references/ files and cross-linking instead of restating would improve both conciseness and progressive disclosure.

Suggestions

Move the 'Config Reference' and 'CLI Commands' tables into references/config.md and references/cli.md, keeping one or two key examples inline with well-signaled links, and delete the duplicated dialectic settings tables (they appear in both 'Three Orthogonal Knobs' and 'Config Reference').

Consolidate the Setup section's commands with the CLI Commands table so each command is documented exactly once.

Add an explicit verification step to the multi-profile workflow (e.g. run 'hermes honcho status' after 'hermes honcho sync' to confirm the peer was created) to close the remaining validation gap.

DimensionReasoningScore

Conciseness

The body is dense and adds mostly novel Honcho-specific information, but there is real duplication: dialectic keys ("dialecticCadence", "dialecticDepth", "injectionFrequency") are fully documented in 'Three Orthogonal Knobs' and again in 'Config Reference', and setup commands reappear in the 'CLI Commands' table. This matches 'mostly efficient but includes some unnecessary explanation or could be tightened'; not 2 because it never explains concepts Claude already knows, and not 4 because the duplicated tables are more than minor trimming.

3 / 5

Actionability

Commands are copy-paste ready ("hermes memory setup honcho", "hermes honcho status", "hermes profile create coder --clone"), config snippets are complete JSON blocks, and tool usage is shown with concrete invocations like 'honcho_reasoning query="What does this user care about most?"' and 'honcho_conclude conclusion="Prefers terse answers"'. This matches 'fully executable; copy-paste ready code or commands; specific examples cover the common cases'; not 4 because the examples span the common cases (setup, verify, per-profile config, each of the 5 tools, troubleshooting) with no meaningful gaps.

5 / 5

Workflow Clarity

Setup is sequenced with an explicit verification checkpoint ("hermes honcho status # shows resolved config, connection test, peer info"), agent usage patterns give ordered steps ("1. honcho_profile → fast warmup"), and troubleshooting pairs symptoms with concrete fixes. Matches 'clear sequence with most checkpoints present; minor validation gaps' — e.g. the multi-profile section lacks an explicit re-verify step after 'hermes honcho sync'. Not 5 because there are no explicit error-recovery feedback loops beyond the troubleshooting FAQ, and not 3 because checkpoint guidance (status, sync, new-session-after-dashboard-change) is consistently present.

4 / 5

Progressive Disclosure

There are no bundle files at all (no references/, scripts/, or assets/ exist), and this ~430-line body inlines what clearly belongs in separate references — the full 'Config Reference' tables, the 'CLI Commands' table, and the deep 'Three Orthogonal Knobs' treatment. Section headers and tables keep it navigable, matching 'some structure but could be better organized; content that should be separate is inline'. Not 2 because structure is good with clear headers and well-formed tables rather than a wall of text; not 4 because nothing is split out and there are no one-level-deep references to signal.

3 / 5

Total

15

/

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 compact and unambiguous about the product and host it targets, giving excellent distinctiveness, but it is too thin for a skill with this many capabilities. It lacks any 'when to use' trigger guidance and lists only two generic actions, so a user or model would not know the skill covers multi-profile peers, recall modes, dialectic tuning, or session strategies.

Suggestions

Add a 'Use when...' clause enumerating natural trigger phrases, e.g. 'Use when setting up Honcho (cloud or self-hosted), fixing memory not persisting across sessions, creating multi-profile peers, or tuning dialectic depth and recall modes.'

Enumerate 2-3 more concrete capabilities in the description (e.g. 'configure observation toggles, recall modes, and context budgets; create per-profile AI peers') to lift specificity from 2 generic verbs to comprehensive coverage.

Include common user-side synonyms such as 'memory not working', 'peers not syncing', or 'session summary' so natural trigger terms match what users actually say.

DimensionReasoningScore

Specificity

"Configure and troubleshoot Honcho memory for Hermes" names the domain plus exactly two actions ("Configure", "troubleshoot"), matching the 'names domain and 1-2 concrete actions' anchor. It is not 4 because the many concrete capabilities (setup, multi-profile peers, recall modes, dialectic tuning) are not enumerated; not 2 because the actions, while few, are real verbs tied to a specific domain.

3 / 5

Completeness

The 'what' is clear (configure and troubleshoot Honcho memory) but there is no "Use when..." clause or equivalent trigger guidance, capping completeness at 3 per the judging guidelines. Not 2 because the 'what' is specific and unambiguous, not vague.

3 / 5

Trigger Term Quality

Relevant keywords are present ("Honcho", "memory", "Hermes", "troubleshoot") but common natural variations users would say — "memory not working", "peers", "session", "recall" — are absent. Fits 'some relevant keywords but missing common variations or synonyms'; not 4 because keyword coverage is thin for a multi-faceted skill.

3 / 5

Distinctiveness Conflict Risk

"Honcho" is a named external product and "Hermes" a specific host, giving this a clear niche with distinct triggers and minimal conflict risk — matching the anchor-5 example's pattern of a named-format niche. It cannot be below 5 territory since virtually no other skill would match 'Honcho memory for Hermes'.

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
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.