SKILLEMALL.ai
RU Sign in

BF hersona

Use when the user wants to apply a character persona to the current session from a generic attribute template (e.g. 'ツンデレで話したい', '敬語で執筆したい', 'ヒロイン役で振舞って', 'hersona attach tsundere', '/hersona personality/tsundere', 'hersona personas install keigo_support', '出来合いパック入れて'). Loads personality / speech / archetype / visual / hobby YAMLs from attributes/<category>/<name>.yaml and injects their core_traits / catchphrases / tone / second_person / sentence_endings into the system prompt. Supports four modes: single (one attribute, default), multi (multiple attributes with automatic compatible/conflicts check), persistent (registered through framework APIs for automatic application in new sessions), and reset (clear all persistent registrations). New: the `hersona personas` subcommand installs a named persona pack (recipe of blend + weight + use_case) into the Hermes registry in one step. Backed by the hersona core package and the `hersona` CLI.

ClawHub Hermes author: shiro0x v0.1.3 MIT-0 3 files body ≈ 5 639 tokens Open the sourceclawhub.ai↗ analyzed 21 h ago

g. 'ツンデレで話したい', '敬語で執筆したい', 'ヒロイン役で振舞って', 'hersona attach tsundere', '/hersona personality/tsundere', 'hersona personas install keigosupport', '出来合いパック入れて').…

As a process F 41/100 · Will not run — References files that are not bundled: ../../docs/guides/self-introduction.md, ../../docs/guides/self-introduction.ja.md, references/self-introduction.md

PersonaTelegramAI and agentsLearningtype and topics are labelled automatically from the skill text
Runs in: OpenClaw Hermes Agent
JSON
Technical rating
B
83/100
safety, quality, tests
Safety 60%
100
Quality 40%
58
Run on models
none yet
Process rating
F
41/100
Will not run
References files that are not bundled: ../../docs/guides/self-introduction.md, ../../docs/guides/self-introduction.ja.md, references/self-introduction.md
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

How to improve

  1. For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
  2. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
  3. The text references files that are not there: add them or drop the references.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 0

✓ No critical or high findings

Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-long-hermes description is 949 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period)
  • warning body-long SKILL.md body ≈ 5639 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: ../../docs/guides/self-introduction.md
  • warning missing-ref reference to a missing file: ../../docs/guides/self-introduction.ja.md
  • warning missing-ref reference to a missing file: references/self-introduction.md
  • warning missing-ref reference to a missing file: scripts/run_quiz.py

Process rating: all ten parameters 41/100

Will not run. References files that are not bundled: ../../docs/guides/self-introduction.md, ../../docs/guides/self-introduction.ja.md, references/self-introduction.md
  • 0Tools and files. 4 referenced file(s) missing: ../../docs/guides/self-introduction.md, ../../docs/guides/self-introduction.ja.md, references/self-introduction.md
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 30Running it twice. 10 mutating operations with no state check
  • 60Steps. 96 steps, 4 vague phrases
  • 60Consistency. The Hermes dialect needs category and tags
  • 70Execution cost. Instruction body is 5639 tokens
  • 100When it triggers. States when to use and when not to
  • 100Failures and branches. 1 branches, has a failure section
  • low 11 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (14 tags): a typed call is more reliable

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +3Description length 949: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • +2Single-language instructions
  • +4Description says when NOT to use the skill
  • +4Structure: 22 headings
  • +3Step-by-step instructions: 96 items
  • +4Has examples (6 code blocks)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 58.

External checks

ClawHub: clean
This skill is a disclosed persona-management helper; its durable persona features are real but aligned with its stated purpose.
LLM: benign (high) · VirusTotal: · 15 Jul 2026