BitterPillEngineering
BitterPillEngineering is a Prompt design & optimisation skill for AI agents, published by danielmiessler in the LifeOS repository on GitHub. Skillspace rates BitterPillEngineering C (73/100) and it passed the safety scan; a judge model has also reviewed it.
Audits any AI instruction set for over-prompting using the core test — would a smarter model make this rule unnecessary? Applies Five Questions to every rule (Claude already does this? Contradiction? Redundant? One-off fix? Vague?) then classifies as CUT/RESOLVE/MERGE/EVALUATE/SHARPEN/MOVE/KEEP. Workflows: Audit (full system, token savings), QuickCheck (single file). Principle: less scaffolding = better output. USE WHEN BPE, bitter pill, audit setup, over-prompting, trim instructions, dead weight, simplify setup, clean up CLAUDE.md. NOT FOR attacking logical flaws in ideas (use RedTeam).
- Grade
- C
- Quality
- 73 / 100
- Safety
- Passed
- GitHub stars
- 16,717
Placed #4 of 6 in the judged category final for Prompt design & optimisation.
This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.
Our review
- Architecture
- 94 / 100
- Maturity
- Structured: ships references or scripts
- Security scan
- Low-risk patterns
- License
- MIT
- Adoption
- Adopted by 0 other repositories, in 0 collections
- Scope
- Portable: works in any project. General audit method for over-prompted AI instruction sets
Judge review
Placed #4 of 6 in the judged category final for Prompt design & optimisation.
- Trigger
85 85 - Instructions
88 88 - Specificity
82 82 - Safety
72 72 - Disclosure
78 78 - Maintenance
80 80
A genuinely principled meta-audit framework (Five Questions plus a HOW-vs-WHAT test) for trimming instruction bloat, undercut by its own mandatory local-notification ritual.
What the scanner flagged
- mentions secrets in text
Not checked yet
- No blind task eval yet
- Sibling files (scripts, references) not fetched; security scan covers SKILL.md only
Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.