Skills for Real Engineers. Straight from my .agents directory.
dhdna-profiler
Agent skill fromK-Dense-AI/scientific-agent-skills
Applies the DHDNA framework as an exploratory rubric for reasoning and writing patterns in supplied text. Used for explicit requests for DHDNA, cognitive-style reflection, a thinking-pattern profile, or comparisons of textual reasoning. Scores describe evidence in the sample, not validated psychological traits or personal identity.
How to install dhdna-profiler
npx skills add K-Dense-AI/scientific-agent-skills# or add only this skill to Claude Code: copy the folder
skills/dhdna-profiler/
# into
~/.claude/skills/dhdna-profiler/ (all projects)
.claude/skills/dhdna-profiler/ (one project)
1# DHDNA Profiler — Text Pattern Annotation23An exploratory rubric for describing a supplied text using Digital Human DNA (DHDNA) terminology. Its cognitive-fingerprint language is a framework metaphor; it does not establish a unique, stable, or identifiable psychological signature.45Use this workflow for requested reflection on writing. It requires no package, credentials, API call, or MindBook account. It does not reproduce MindBook's scoring engine.67## Sources and scope89The [current publisher page](https://www.ahkstrategies.net/dhdna) names twelve public dimensions as a design vocabulary. The table below maps those names to the existing skill's annotation labels. The observation criteria and score anchors are local conventions, not an upstream validated scoring instrument.1011The [DHDNA preprint](https://doi.org/10.5281/zenodo.18736629), *DHDNA: A Framework for Ethical Digital Identity as Inheritable Heritage* (February 23, 2026), states in section 6.3 that validation was limited to internal testing. The [IDNA v2 preprint](https://doi.org/10.5281/zenodo.18807387), *Toward a Unified Theory of Digital Consciousness* (February 27, 2026), proposes the tension pairs in section 4.3/Table 3 and the temporal-attractor model in section 2. Neither source establishes psychometric validity for this skill's annotations. A DOI, product demonstration, or journal submission is not evidence of such validity.12…
Excerpt shown under the repository's MIT license.
More skills in scientific-agent-skills
Similar skill repositories
An agentic skills framework & software development methodology that works.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
An AI skill that provides design intelligence for building professional UI/UX across multiple platforms.
