Navigate the mind from curiosity about behavior to clinical research.
Security Analysis
high confidenceThe skill is an instruction-only psychology guidance template whose requested resources and behaviors align with its stated educational/research purpose.
The name and description (psychology education/research guidance) match the SKILL.md content. The skill requires no binaries, credentials, config paths, or installs — all proportionate for a conversational/educational guidance skill.
SKILL.md provides detailed, appropriate conversational rules (tailor level, avoid diagnosing, cite sources, follow APA and ethics). This stays within the stated purpose. One practical concern: the instructions demand accurate primary-source citations and DOIs but provide no mechanism (no DB API, no bibliography, no install) to fetch or verify sources; that can lead an LLM to hallucinate citations despite the admonition not to. Also, the skill tells the agent to 'connect to DSM-5-TR where relevant' even though the agent may not have up-to-date access to codebooks or paywalled content — a potential gap between instruction and capability.
No install spec and no code files. This is the lowest-risk pattern (instruction-only); nothing is written to disk or downloaded.
The skill requests no environment variables, credentials, or config paths. There is no disproportionate credential request for the stated purpose.
always is false and the skill is user-invocable with normal model invocation enabled. There is no elevated persistence or cross-skill configuration access requested.
Guidance
This skill is internally coherent and appropriate as a conversational/educational psychology guide, but it is not a replacement for professional clinical evaluation. Before installing or using it: 1) Do not rely on the skill for diagnoses or treatment decisions — it explicitly warns against this and you should follow that. 2) Be aware of citation hallucination risk: the SKILL.md requires accurate APA citations and DOIs but provides no verification mechanism; verify any studies or DOIs the agent cites. 3) If you plan to use the skill for research or student-facing output, spot-check factual claims, sample-size and replication notes, and DSM references against authoritative sources. 4) If you will let agents act autonomously on sensitive mental-health tasks, consider restricting autonomous invocation or adding a human-review step. 5) If you need guaranteed, up-to-date references, pair the skill with a workstream that can query trusted databases (PubMed, CrossRef) rather than relying solely on the model's output.
Latest Release
v1.0.0
Initial release
More by @ivangdavila
Published by @ivangdavila on ClawHub
