K-Dense-AI/scientific-agent-skills / skills/dhdna-profiler
dhdna-profiler
VerifiedApplies 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.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 11.1 KB |
| references/advanced-profiling.md | markdown | 4.3 KB |
references/advanced-profiling.md
View on GitHub# DHDNA Profiler — Advanced Reference
## Genre lenses
These are local reading prompts, not empirically established genre norms or expected profiles. Review all twelve dimensions; a focus list never justifies filling the others with low scores. Do not assume a topology from the genre.
| Context | Useful dimensions | Evidence to inspect |
| --- | --- | --- |
| Academic writing | Analytical Depth, Linguistic Precision, Domain Expertise, Metacognition | Argument structure, defined terms, justified methods, limitations; check cited sources separately |
| Creative writing | Creative Range, Emotional Processing, Linguistic Precision, Intuitive Reasoning | Analogies, narrative structure, expressed affect, explicitly intuitive choices; separate narrator, character, and author |
| Business communication | Strategic Thinking, Social Intelligence, Temporal Orientation, Analytical Depth | Alternatives, stakeholders, contingencies, and time horizons |
| Technical documentation | Analytical Depth, Domain Expertise, Linguistic Precision, Metacognition | Explanations, disambiguation, prerequisites, and acknowledged failure modes; verify technical correctness independently |
| Personal reflection | Emotional Processing, Metacognition, Memory Integration, Temporal Orientation | Expressed affect, revisions, recollections, and time references; do not infer health status |
## Dispersion of annotated scores
Prefer showing the per-dimension observations and missing entries. The local 1–10 scores are ordinal and cover different constructs; equal spacing and cross-dimension comparability have not been established. Their mean or standard deviation can change with arbitrary coding choices and should not be presented as a psychological summary.
If a user explicitly requests arithmetic dispersion, state this assumption and list the included dimensions, N/A exclusions, and whether population or sample SD was used. Never substitute zero for N/A. A single observed dimension cannot supply sample SD; an empty set supplies neither mean nor SD. No 1.5/3.0 cutoff establishes specialization, innovation, vulnerability, or blind spots. Standard deviation is not information-theoretic entropy.
## Repeated samples and the 4D-DHDNA proposal
The [IDNA v2 preprint](https://doi.org/10.5281/zenodo.18807387), section **2**, introduces the fourth-string temporal-attractor theory. This theoretical extension is not a validated longitudinal measurement or forecasting procedure. A time series of this skill's annotations does not implement its model or estimate its parameters.
For requested repeated-sample reflection:
1. Record the dates, designated source passages, prompt, genre, length, language, editing context, and annotation convention.
2. Describe each sample's evidence separately before comparing it.
3. Compare only dimensions with suitable evidence in both samples; preserve missingness.
4. Discuss context and rater changes that could explain the difference. When multiple raters are used, retain their separate annotations and disagreements rather than hiding them in a mean.
5. State changes as changes in the observed writing. Do not extrapolate a future psychological state, cognitive growth, or decline.
## Compact notation
Prefer dimension numbers from the main skill to avoid ambiguity between local labels and the publisher's updated names. Include a legend and sample identifier. The following is a **synthetic notation example**, not a psychological result:
```text
Sample S1; local ordinal rubric; scores supplied for illustration
D1=7 D2=NA D3=NA D4=6 D5=NA D6=7
D7=NA D8=NA D9=NA D10=NA D11=5 D12=7
```
The notation is only a compact record of annotations. It does not replace quotations, per-dimension confidence, source context, or a rationale. It cannot identify an occupation or individual.
## Review provenance
Reviewed September 30, 2026 against the [publisher's twelve public dimensions](https://www.ahkstrategies.net/dhdna), the [DHDNA preprint record](https://zenodo.org/records/18736629) and PDF (section 6.3), and the [IDNA v2 record](https://zenodo.org/records/18807387) and PDF (section 2 and section 4.3/Table 3). Both Zenodo records describe preprints; the IDNA file is `AHK_IDNA_Consolidation_v2.pdf`. The source proposals establish terminology, not the validity of this skill's local score anchors. No public MindBook scoring API is used or specified here.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack." | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |