Skip to content

agentsope/SkillAlchemy / skills/agentsop-module-shape-selection

agentsop-module-shape-selection

Verified

ENHANCE overlay on [[dspy]] — the upfront rubric for choosing a reasoning SHAPE (Predict / ChainOfThought / ReAct / ProgramOfThought) BEFORE you write a prompt or pick an optimizer. The local `dspy` skill lists the modules but never surfaces the *selection criterion*: reasoning shape is chosen by task structure, not by reflexively defaulting to CoT. Activate every time a new LM-calling node/step is added to a pipeline. Do NOT activate for one-shot prompts, optimizer/teleprompter choice (that is the dspy SOP's job), or non-LM control flow. Search keywords: chain of thought vs ReAct, when to use CoT, reasoning type, ReAct vs CoT vs PoT, which dspy module, predict vs chain of thought.

FileKindSize
README.mdmarkdown2.1 KB
SKILL.mdskill md17.3 KB
intermediate/operation_candidates.jsonconfig5.9 KB
references/R1-source-evidence.mdmarkdown4.2 KB
# module-shape-selection (M2)

**Enhancement overlay** on the [[dspy]] library skill. Surfaces the one decision the
lib skill leaves implicit: **which reasoning shape to pick before you write a prompt.**

## What it is

The local `dspy` skill lists four modules — `Predict`, `ChainOfThought`, `ReAct`,
`ProgramOfThought` — and advises "start simple, add CoT if needed." It never makes
*"if needed"* operational, so the practical result is a **CoT-everywhere reflex**.

This overlay is the missing rubric:

```
no reasoning, no tool        → Predict
reasoning, no tool           → ChainOfThought
any real tool / action       → ReAct(tools=[...])
math / count / strict parse  → ProgramOfThought
```

Core claim: **reasoning shape is chosen by task structure, not by defaulting to CoT.**

## When it fires

Every time a **new LM-calling step/node** is added to a pipeline (a `forward()` line,
a LangGraph/CrewAI node, a fresh `dspy.<Module>(Sig)`). Hit on every new node.

## When it does NOT fire

- One-shot prompts (no pipeline).
- Optimizer / teleprompter choice → that is `[[agentsop-dspy]]`.
- Non-LM control flow.

## Files

| File | Purpose |
|---|---|
| `SKILL.md` | The overlay: 7 sections (activate / mental model / SOP / selection card / dilemma cases / anti-patterns / cross-framework). |
| `references/R1-source-evidence.md` | Line-cited evidence from the two source skills + DSPy docs. |
| `intermediate/operation_candidates.json` | Extracted, reusable selection operations. |

## Position in the stack

```
[[dspy]]        → module API, signatures, LM wiring   (HOW to call)
this overlay    → WHICH shape to call                 (WHAT shape, upfront)
[[agentsop-dspy]]    → metric + optimizer + compile         (HOW to tune it, later)
```

Shape first, optimizer second. An optimizer cannot repair a wrong shape.

## Relationship to other skills

- Depends on (cross-links): `[[dspy]]`, `[[agentsop-dspy]]`.
- Overlaps avoided: no install, no signature syntax, no optimizer tables (all live in
  the linked skills). This file adds only the selection decision.

Version 0.1.0.
writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deploymentStars: 322kUpdated Claude CodeCodexVerifiedInstall
xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.Stars: 197kUpdated Claude CodeCodexVerifiedInstall
shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy.Stars: 119kUpdated Claude CodeCodexVerifiedInstall
childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release.Stars: 118kUpdated Claude CodeCodexVerifiedInstall