Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Strategy: Conflict Resolution · yogsoth-ai | DecimalAI

productivityby yogsoth-ai

Strategy: Conflict Resolution

yogsoth-ai/conflict-resolution

Source yogsoth-ai/de-anthropocentric-research-engine ↗License Apache-2.0

How do constraints conflict with each other? — Evaporating Cloud + assumption challenging + injection to resolve constraint conflicts

SkillScore87Maintained

Automatic

Project Management pack

Last verified 8/22/2026

What it changes

Passed 18 of 21 test cases with the skill, and 13 of 21 without it.

Without skill61%

With skill87%

Checks it passed that the model alone missed

Limit total subagent calls to at most 8
Invoke core-conflict-extraction as the first step
Set the maximum output token limit to 3000 tokens

and 6 more in the full report

8 fixed12 passed either way1 still failing2 broke

Pass-rate lift: +26 pp
Tokens: +21%
Agent turns: 0%
Response time: -12%

Model gemini-3.6-flashMeasured 8/22/2026v120 of 23 cases passed with skill · 21 comparable

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/yogsoth-ai-conflict-resolution/SKILL.md https://app.decimal.ai/s/yogsoth-ai-conflict-resolution/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add yogsoth-ai-conflict-resolution, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/yogsoth-ai-conflict-resolution/ and pins it in .decimal/skills.lock

decimalai skills add yogsoth-ai-conflict-resolution

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/yogsoth-ai-conflict-resolution/SKILL.md https://app.decimal.ai/s/yogsoth-ai-conflict-resolution/SKILL.md

Raw file: /s/yogsoth-ai-conflict-resolution/SKILL.md ↗ · machine-readable summary at /s/yogsoth-ai-conflict-resolution.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 6

Prompt

A project manager wants to map opposing team demands into a formal A-B-C-D-D' structure with arrow assumptions. Which SOP performs this structural extraction?

What was checked, without and with the skill
Checked	Without skill	With skill
Identify core-conflict-extraction as the SOP for creating the diagram	Missed	Passed

case-19 · gemini-3.6-flash · 8/22/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md72 linessingle file

Strategy: Conflict Resolution

Methodology

Based on Goldratt's Evaporating Cloud (EC) and injection methodology:

Surface the conflict: Express opposing demands in EC format
Challenge assumptions: Each EC arrow rests on assumptions — find the invalid one
Inject: Propose an action that invalidates the false assumption
Project future: Use Future Reality Tree to verify injection resolves the conflict without creating new UDEs

Evaporating Cloud structure:

        B ←── D
       ↗         ↘ (conflict)
  A                    
       ↘         ↗ (conflict)
        C ←── D'

A: Common objective both sides want
B: Need that leads to wanting D
C: Need that leads to wanting D'
D and D': Mutually exclusive wants

Execution Flow

Extract Core Conflict → call core-conflict-extraction SOP
- Input: identified constraints that oppose each other
- Output: Evaporating Cloud (A-B-C-D-D') with assumptions on each arrow
Challenge Assumptions → call assumption-challenging SOP
- Input: assumptions underlying each EC arrow
- Output: validity assessment, weakest assumptions identified
Generate Injections → synthesize from challenged assumptions
- For each invalid assumption, propose an injection (action that makes the conflict disappear)
Project Future Reality → call future-reality-projection SOP
- Input: proposed injections
- Output: Future Reality Tree showing resolved conflict + any new UDEs

Track record

Benchmark

18 / 21

test cases passed, vs 13 / 21 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

yogsoth-ai / de-anthropocentric-research-engine

skills/conflict-resolution/SKILL.md

View on GitHub ↗

License Apache-2.0Imported 8/3/2026Version v1

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Strategy: Conflict Resolution

Methodology

Execution Flow

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills