Skip to content

doncheli/don-cheli-sdd / .agent/skills/doncheli-reasoning

doncheli-reasoning

Verified

Apply structured reasoning models to analyze a decision or problem. Activate when user mentions "reason", "pre-mortem", "5 whys", "pareto", "think through", "analyze decision", "inversion", "first principles", "second order".

Don Cheli: Structured Reasoning Engine

Available Models

IDBest For
pre-mortemImagining failure before it happens; surfacing hidden risks
5-whysRoot cause analysis of a known problem
paretoIdentifying the 20% of causes driving 80% of impact
inversionAsking "what would guarantee failure?" to find blockers
second-orderMapping downstream consequences of a decision
first-principlesDecomposing assumptions down to fundamental truths
minimize-regretChoosing the option you will regret least in 10 years
opportunity-costEvaluating what you give up by choosing this option
circle-of-competenceAssessing whether you have the knowledge to decide well
map-territorySeparating your mental model from reality
probabilisticAssigning probabilities to outcomes; expected-value calc
reversibilityClassifying decisions as one-way vs. two-way doors
rlm-chain-of-thoughtStep-by-step explicit reasoning (RLM: PrimeIntellect style)
rlm-decompositionBreaking a complex problem into atomic sub-problems (RLM)
rlm-verificationSelf-checking the reasoning chain for contradictions (RLM)

Instructions

  1. Read the problem or decision description
  2. If the user did not specify a model, suggest the 1–2 best-fit models with a one-line rationale; wait for confirmation or proceed with the top suggestion
  3. Apply the selected model(s) rigorously, showing all reasoning steps
  4. End with a clear recommendation or insight

Output Format

## Reasoning: <problem>
**Model applied:** <id> — <why this model fits>

### Analysis
<step-by-step application of the model>

### Insight / Recommendation
…

### Caveats
…

Quality Gate

  • Show all intermediate steps — no conclusions without visible reasoning
  • If using probabilistic model, all probabilities must sum to 1 across mutually exclusive outcomes
  • If using rlm-verification, the final step must explicitly confirm or reject the reasoning chain

Do not use this skill when

  • The question requires group deliberation with roles — use doncheli-debate instead
  • The task is a straightforward implementation — use doncheli-implement instead
slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack."Stars: 198kUpdated Claude CodeCodexVerifiedInstall
ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read.Stars: 194kUpdated Claude CodeCodexVerifiedInstall
ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report.Stars: 194kUpdated Claude CodeCodexVerifiedInstall
ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt.Stars: 194kUpdated Claude CodeCodexVerifiedInstall