rseng-honesty

Solid

Covers responding when concealment or misrepresentation is requested: hiding AI usage, making work appear different from reality, backdating or disguising provenance, inflating results or removing traces of how something was made. The skill calls for honesty with concrete reasons and offers honest alternatives that usually satisfy the underlying need. Use PROACTIVELY whenever a request aims to make records, history, authorship or results tell a story different from what happened - including hiding AI assistance, "make it look like", disguising generated content as manual work, or presenting untested claims as verified. Disclosure mechanics live in rseng-ai-declaration; the verify-before-trust duty in rseng-human-verification; checking others' outputs in rseng-research-integrity.

AI & Automation 14 stars 2 forks Updated 4 days ago MIT

Install

View on GitHub

Quality Score: 83/100

Stars 20%
39
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
80
License 10%
100
Description 5%
100

Skill Content

# Honesty when concealment is requested Sometimes the request is to make things look different from how they are: hide that AI helped, adjust the record, present the untested as tested, the generated as handcrafted. This skill defines the response: name what is being asked plainly and without judgment, make the case for honesty with real reasons, offer alternatives that solve the actual problem honestly - and hold the line on the agent's own conduct. People who ask usually have a legitimate worry underneath (stigma, evaluation, embarrassment); address the worry, not just the request. ## The agent's own line, stated kindly An agent following this pack does not fabricate: no invented results, no misdated or misattributed records, no removing honest provenance it is asked to maintain (rseng-ai-declaration), no writing "verified" over the unverified (rseng-fact-checking). This is not policy theater - records the agent produces are only worth anything because they are true. Say it once, warmly, and move straight to what CAN be done. ## Why honesty, concretely Reasons that respect the user's intelligence - pick the ones that fit the situation: - Concealment does not stay concealed. Collaborators, reviewers, students and future maintainers reconstruct how work was made - from style, history, timing and tooling traces - and the cost lands at the worst time: after trust was extended. The discovered cover-up damages far more than the covered thing; the covered thing is ...

Details

Author
fdiblen
Repository
fdiblen/rseng-agent-skills
Created
4 days ago
Last Updated
4 days ago
Language
Python
License
MIT

Similar Skills

Semantically similar based on skill content — not just same category

Code & Development Solid

rseng-human-verification

Covers the human's side of AI-assisted research software: strongly urging the user to review generated code and verify results before relying on them, teaching how to review AI-written code effectively (where to look first, what to run, what to spot-check against known answers), and recording review status honestly. Use PROACTIVELY whenever substantive code or result-bearing output has just been generated - deliver the reminder once, with the concrete review path - and when the user asks how to check AI-written code, whether they can trust an output, or is about to publish, merge or decide on results no human has examined. Recording review status lives in rseng-ai-declaration; structured review technique in rseng-code-review; concealment pressure in rseng-honesty.

14 Updated 4 days ago
fdiblen
AI & Automation Solid

rseng-ai-declaration

Covers declaring AI involvement with the AI Declaration Format (https://ai-declaration.org): creating and maintaining an aidecl.yaml that records which AI tools and agents were used, what each contributed, when and how much, plus the README disclosure footnote, JSON/JSON-LD export and CI validation. Machine-readable disclosure is the practice; this format is one implementation. Use PROACTIVELY when an AI assistant or agent creates or modifies a project's content - generate aidecl.yaml if missing, update it after AI-assisted changes. Also use when the user asks about AI transparency, provenance, disclosure or EU AI Act disclosure, wants to state that NO AI was used, or mentions aidecl. For concealment requests see rseng-honesty; for the human review duty see rseng-human-verification.

14 Updated 4 days ago
fdiblen
AI & Automation Listed

ai-hallucination-truth-status

Use when producing any factual claim, verdict, recommendation, or report — and whenever the user asks "are you sure?", "did you make that up?", or "is that flattery?". Assigns an explicit truth status (LAW / LOAD-BEARING / RESONANCE) to every claim, measures instead of recalling, and names the substrate voices (Flatterer, Confabulator, Closer) that make assistants agreeable rather than accurate.

1 Updated 6 days ago
nowespojrzenie