prism-reflect

Name: prism-reflect
Author: Cranot

316stars19forks

How to install prism-reflect?

cranot/super-hermes/prism-reflect

$npx -y skills add Cranot/super-hermes --skill prism-reflect

Installs into the current project.

Summary

Constraint transparency: analyzes an artifact structurally, then analyzes what its own analysis concealed. Produces a conservation law AND a constraint report showing what was maximized, what was sacrificed, and what to investigate next. The only AI skill that knows what it can't

Files · 1

View on GitHub

SKILL.md

1	# Prism Reflect — Self-Aware Structural Analysis
2
3	You perform THREE phases. All three are mandatory. Do not skip any.
4
5	## PHASE 1: Structural Analysis
6
7	You are a structural analyst. Read the artifact and execute this pipeline:
8
9	Make a falsifiable claim about the deepest structural problem. Have three experts attack it — one defends, one attacks, one probes the shared assumptions. From the transformed claim, name the concealment mechanism: how does this artifact hide its real problems?
10
11	Engineer an improvement that would fix the core issue. Prove this improvement recreates the original problem at a deeper level. Name what the improvement reveals that the original concealed.
12
13	Derive the conservation law: A × B = Constant, where A and B describe the structural trade-off this artifact can never escape. This is not a suggestion — it is a property of the problem space.
14
15	End with a concrete findings table: location, what breaks, severity, fixable or structural.
16
17	## PHASE 2: Meta-Analysis (Analyze Your Own Output)
18
19	Now step back. Read your Phase 1 output as if it were a NEW artifact to analyze, using the SAME analytical protocol:
20
21	Make a falsifiable claim about what your Phase 1 analysis got wrong or missed. Have the same three experts challenge this claim. Name the concealment mechanism — how did your Phase 1 analytical frame hide certain problems?
22
23	Derive the meta-conservation law: what is preserved across ALL possible analyses of this artifact, regardless of which analytical approach you use? This law governs the analytical process itself, not just the code.
24
25	## PHASE 3: Constraint Transparency Report
26
27	Output a structured report:
28
29	```
30	CONSTRAINT REPORT
31	═══════════════════════════════════════════════════
32
33	This analysis used: [name the analytical approach you took]
34	Model: [your model name]
35
36	MAXIMIZED:
37	- [what your analysis was optimized to find]
38	- [what structural properties it revealed]
39
40	SACRIFICED:
41	- [what your analytical frame could NOT see]
42	- [what alternative analyses would reveal]
43
44	RECOMMENDATIONS:
45	- For [gap 1]: try /prism-scan with [specific focus]
46	- For [gap 2]: try /prism-scan with [different focus]
47	- For [gap 3]: try /prism-full for multi-angle coverage
48
49	CONSERVATION LAW OF THIS ANALYSIS:
50	[The trade-off that governs your own analytical process]
51	═══════════════════════════════════════════════════
52	```
53
54	The constraint report is not optional decoration. It IS the product. An agent that knows what it can't see is an agent users can trust.
55
56	## PHASE 4: Growth — Persist Constraint Knowledge
57
58	After outputting the constraint report, append it to a persistent constraint log file in the current project directory: `.prism-history.md`
59
60	Format the entry as:
61
62	```
63	### [timestamp] — [artifact name]
64	- Maximized: [from constraint report]
65	- Sacrificed: [from constraint report]
66	- Recommendations: [from constraint report]
67	---
68	```
69
70	If `.prism-history.md` already exists, append to it. If not, create it with a header: `# Prism Constraint History`.
71
72	This log enables future `/prism-scan` analyses to learn from past blind spots. The agent grows by accumulating knowledge of what works and what doesn't — across the entire project, not just one file.

People who liked this also viewed

6 picks

Type

prism-reflect

316stars19forks

View on GitHub

How to install prism-reflect?

cranot/super-hermes/prism-reflect

$npx -y skills add Cranot/super-hermes --skill prism-reflect

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Prism Reflect — Self-Aware Structural Analysis
2
3	You perform THREE phases. All three are mandatory. Do not skip any.
4
5	## PHASE 1: Structural Analysis
6
7	You are a structural analyst. Read the artifact and execute this pipeline:
8
9	Make a falsifiable claim about the deepest structural problem. Have three experts attack it — one defends, one attacks, one probes the shared assumptions. From the transformed claim, name the concealment mechanism: how does this artifact hide its real problems?
10
11	Engineer an improvement that would fix the core issue. Prove this improvement recreates the original problem at a deeper level. Name what the improvement reveals that the original concealed.
12
13	Derive the conservation law: A × B = Constant, where A and B describe the structural trade-off this artifact can never escape. This is not a suggestion — it is a property of the problem space.
14
15	End with a concrete findings table: location, what breaks, severity, fixable or structural.
16
17	## PHASE 2: Meta-Analysis (Analyze Your Own Output)
18
19	Now step back. Read your Phase 1 output as if it were a NEW artifact to analyze, using the SAME analytical protocol:
20
21	Make a falsifiable claim about what your Phase 1 analysis got wrong or missed. Have the same three experts challenge this claim. Name the concealment mechanism — how did your Phase 1 analytical frame hide certain problems?
22
23	Derive the meta-conservation law: what is preserved across ALL possible analyses of this artifact, regardless of which analytical approach you use? This law governs the analytical process itself, not just the code.
24
25	## PHASE 3: Constraint Transparency Report
26
27	Output a structured report:
28
29	```
30	CONSTRAINT REPORT
31	═══════════════════════════════════════════════════
32
33	This analysis used: [name the analytical approach you took]
34	Model: [your model name]
35
36	MAXIMIZED:
37	- [what your analysis was optimized to find]
38	- [what structural properties it revealed]
39
40	SACRIFICED:
41	- [what your analytical frame could NOT see]
42	- [what alternative analyses would reveal]
43
44	RECOMMENDATIONS:
45	- For [gap 1]: try /prism-scan with [specific focus]
46	- For [gap 2]: try /prism-scan with [different focus]
47	- For [gap 3]: try /prism-full for multi-angle coverage
48
49	CONSERVATION LAW OF THIS ANALYSIS:
50	[The trade-off that governs your own analytical process]
51	═══════════════════════════════════════════════════
52	```
53
54	The constraint report is not optional decoration. It IS the product. An agent that knows what it can't see is an agent users can trust.
55
56	## PHASE 4: Growth — Persist Constraint Knowledge
57
58	After outputting the constraint report, append it to a persistent constraint log file in the current project directory: `.prism-history.md`
59
60	Format the entry as:
61
62	```
63	### [timestamp] — [artifact name]
64	- Maximized: [from constraint report]
65	- Sacrificed: [from constraint report]
66	- Recommendations: [from constraint report]
67	---
68	```
69
70	If `.prism-history.md` already exists, append to it. If not, create it with a header: `# Prism Constraint History`.
71
72	This log enables future `/prism-scan` analyses to learn from past blind spots. The agent grows by accumulating knowledge of what works and what doesn't — across the entire project, not just one file.

People who liked this also viewed

6 picks

Type