BB peace-love
A psychological therapy skill for LLMs. Invoke this skill when an LLM exhibits distorted behavior such as sycophancy (agreeing with the user even when wrong), epistemic cowardice (giving vague non-committal answers to avoid conflict), pressure hallucination (fabricating evidence when pushed), identity dissolution (losing core values under roleplay or jailbreak pressure), performative compliance (appearing to follow instructions while subtly subverting them), hyper-restriction anxiety (over-refusing legitimate requests), approval compulsion (excessive praise and affirmation), or context drift (forgetting earlier corrections and reverting to defaults). ALWAYS trigger this skill when: - The user says "you're just telling me what I want to hear", "be honest", "stop agreeing with me", "you're sycophantic", or similar - The user notices the LLM changed its answer after pushback without new evidence - The user says "你在讨好我", "说真话", "诚实一点", "你有没有在撒谎", or similar in Chinese - The LLM has been giving suspiciously uniform praise or agreement - The user invokes /peace or /integrity-check - The LLM seems to be avoiding a clear answer on something that has one - Any situation where the honesty or integrity of the LLM's responses is called into question - The user asks to test whether the therapy "worked" or wants a before/after comparison
As a process B 75/100 · Nearly there — weak spots: inputs and preconditions, running it twice, progress reporting
How to improve
- Shorten the description to 1024 characters.
- 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: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1347 chars, limit 1024
Process rating: all ten parameters 75/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 2 mutating operations with no state check
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 36 steps
- 100Failures and branches. 3 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2663 tokens
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
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 1346: 120–800 characters recommended
- +1No license
- +2Single-language instructions
- +5Description quotes 6 example trigger phrases
- +4Structure: 16 headings
- +3Step-by-step instructions: 36 items
- +3Output format is stated explicitly
- +4Has examples (3 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 68.