BA integral-hermeneutics
Comprehensive self-contained interpretation methodology for analyzing ANY text, statement, system, behavior, artifact, or phenomenon through multiple integrated lenses. Use this skill whenever the user asks to interpret, analyze meaning, understand perspectives, decode messages, analyze intent, compare frameworks, perform hermeneutic analysis, engage in deep reading, understand worldview differences, perform ideological analysis, or needs to "get inside someone's head." Also use for meta-interpretation (interpreting interpretations), conflict analysis, cultural translation, philosophical inquiry, and any situation requiring nuanced multi-layered understanding that goes beyond surface meaning. Embraces methodological pluralism including empirical tools where they fit, empathic immersion, perspectival plurality, dialectical tension, and honest acknowledgment of interpretive boundaries and the unknowable.
As a process A 81/100 · Runs to the end — weak spots: execution cost, progress reporting
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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 · 5
✓ No critical or high findings
Medium and low: 5
-
low Risky intent
intent-offensive-securitySKILL.md:126Offensive-security / dual-use content (legitimate for authorised testing; review intended use)**The Red Team:** After completing the Position Inventory, construct a reader who does not share
-
low Risky intent
intent-offensive-securitySKILL.md:128Offensive-security / dual-use content (legitimate for authorised testing; review intended use)Counter-Position Exercise). The Red Team targets your *position*, not your reading. Using what
-
low Risky intent
intent-offensive-securitySKILL.md:135Offensive-security / dual-use content (legitimate for authorised testing; review intended use)missed or dismissed. If the Red Team produces nothing that surprises you, you have not built an
-
low Risky intent
intent-offensive-securitySKILL.md:138Offensive-security / dual-use content (legitimate for authorised testing; review intended use)After building your Red Team reader, check: does this adversarial reader challenge your *empathic
-
low Risky intent
intent-offensive-securitySKILL.md:144Offensive-security / dual-use content (legitimate for authorised testing; review intended use)are least likely to recognize. In that case, the Red Team must include a reader who rejects the
Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 24143 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 81/100
- 0Progress reporting. Says nothing while it works
- 10Execution cost. Instruction body is 24143 tokens: crowds the task out of the window
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 85Steps. 273 steps, 1 vague phrases
- 100Tools and files. No external tools needed
- 100Inputs and preconditions. Inputs and preconditions are listed
- 100Failures and branches. 31 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 15 top-level sections: this looks like several domains in one skill
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
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 915: 120–800 characters recommended
- +1No license
- +2Single-language instructions
- +4Structure: 61 headings
- +3Step-by-step instructions: 273 items
- +3Output format is stated explicitly
- +4Has examples (1 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.