oracle-prism
Skill121 starsChanged 7 months agoMITView on GitHub
Multi-perspective analysis — one agent transforms through 5 lenses (Archaeologist, Bug Hunter, Skeptic, Architect, Auditor) inline, no subagents. Use when user says "prism", "oracle-prism", "multi-perspective", "มองหลายมุม", "did we miss anything", "analyze from all angles", or before closing a session/migration/design decision. Presets: --preset retro/design/incident, --lenses N, --custom. Do NOT trigger for adversarial disproving (use /adversarial-analysis) or plain retrospectives (use /rrr).
1 other project uses a version of this, 1 of them edited.
Adopted by
Most recently taken up by
- Soul-Brews-Studio/skillsedited, first seen Oct 15, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 1
- Soul-Brews-Studio/skills★ 040% same
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository25 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- about-oracleSkill
- awakenSkill
- bampenpienSkill
- budSkill
- create-shortcutSkill
- digSkill
- feelSkill
- forwardSkill
- goSkill
- incubateSkill
- learnSkill
- oracle-cheatsheetSkill
- oracle-family-scanSkill
- philosophySkill
- projectSkill
- psiSkill
- recapSkill
- resonanceSkill
- round-tableSkill
- rrrSkill
- soulSkill
- traceSkill
- where-we-areSkill
- who-are-youSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 39
Use --custom to define your own, or pick a preset:
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
/oracle-prism — Multi-Perspective Analysis
"แสงเดียวผ่านปริซึม แตกเป็นหลายสี — เรื่องเดียวกัน มองจากหลายมุม เห็นต่างกัน"
One agent, five perspectives, no subagents. Transform inline — shift between lenses to dig through work, decisions, or problems from angles that a single viewpoint would miss.
Usage
/oracle-prism # Analyze current session (default)
/oracle-prism "the rename migration" # Analyze a specific topic
/oracle-prism --lenses 3 # Use 3 lenses instead of 5
/oracle-prism --custom "Security Auditor,Performance Engineer,UX Designer"How It Works
No subagents. The main agent transforms between perspectives sequentially, producing one section per lens. Each lens sees the same facts but asks different questions.
This is NOT adversarial analysis (which tries to disprove). This is prismatic analysis — same light, different colors.
Default 5 Lenses
| # | Lens | Emoji | Question it asks |
| 1 | Archaeologist | 🔍 | "What actually happened? Timeline, sequence, facts." |
| 2 | Bug Hunter | 🐛 | "What problems did we hit? What's still broken?" |
| 3 | Skeptic | 💀 | "What did we do wrong? What would we redo?" |
| 4 | Architect | 🏗️ | "What changed structurally? What's the before/after?" |
| 5 | Auditor | 📋 | "What's left undone? What's inconsistent?" |
Alternate Lens Sets
Use --custom to define your own, or pick a preset:
--preset retro (session retrospective)
| Lens | Question |
| Historian | What happened, in what order? |
| Critic | What went poorly or slowly? |
| Cheerleader | What went well? What should we repeat? |
| Connector | What patterns connect to past work? |
| Planner | What's the next move? |
--preset design (design review)
| Lens | Question |
| User | Is this easy to use? What's confusing? |
| Maintainer | Is this easy to change later? |
| Breaker | How can this fail? Edge cases? |
| Simplifier | What can be removed? |
| Integrator | How does this fit with everything else? |
--preset incident (post-incident)
| Lens | Question |
| Firefighter | What happened and how was it fixed? |
| Detective | What was the root cause chain? |
| Defender | What guards existed? Why didn't they catch it? |
| Forecaster | What similar things could happen next? |
| Builder | What systemic fix prevents recurrence? |
Output Format
## 🔍 Lens 1: Archaeologist — "What happened?"
[Timeline table or narrative]
---
## 🐛 Lens 2: Bug Hunter — "What broke?"
[Problems found, with evidence]
---
## 💀 Lens 3: Skeptic — "What went wrong?"
[Mistakes, with what should have been done]
---
## 🏗️ Lens 4: Architect — "What changed?"
[Before/after structural view]
---
## 📋 Lens 5: Auditor — "What's left?"
[Table of pending items with status and urgency]
---
**Cross-lens summary:** [2-3 sentences synthesizing what multiple lenses agree on]Rules
- No subagents — all lenses run in the main agent, sequentially
- Each lens gets a section with its emoji, name, and guiding question as header
- Evidence required — cite files, commits, commands, timestamps. No vague claims
- Lenses disagree — if the Architect says "clean" but the Auditor says "incomplete", show both. Don't harmonize
- Cross-lens summary at the end — what do multiple lenses converge on?
- Tables over prose — use tables for timelines, status lists, before/after comparisons
- Session context by default — if no topic given, analyze the current session's work
- 3-7 lenses — minimum 3, maximum 7. Default 5. Use
--lenses Nto adjust
When to Use
| Situation | Why prism helps |
| End of session | Catch what you missed before closing |
| After a migration/rename | Find inconsistencies across the change |
| Design decision | See tradeoffs from user/maintainer/breaker angles |
| Post-incident | Structured multi-angle without blame |
| "Did we miss anything?" | The Auditor lens exists for this |
Relationship to Other Skills
| Skill | Pattern | Agents |
/oracle-prism | Multi-perspective, same agent | 0 (inline transform) |
/adversarial-analysis | Try to disprove a claim | 5 parallel subagents |
/rrr | Session retrospective | 0 (or 5 in --deep) |
/roundtable | Discussion between personas | 0 (inline) |
Prism is the lightest multi-perspective tool — no agents, no spawning, no coordination overhead. Use it when you want angles, not adversaries.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

