agentsclimarketplace
Sign in

Feature

Skill InSciCo/i-framework/i-framework/skills/feature

Create or revise a single Product feature file with a complete user story, Given/When/Then acceptance criteria, and an innovation-vs-implementation classification. Use when adding one feature to Product/Features/, or refining an existing feature, outside a full /innovate run.From its SKILL.md

Install
npx -y skills add InSciCo/i-framework --skill feature

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 4 stars4 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

3.6 KB, 816 tokens by cl100k_base, as published. Nobody here has run it

/feature — author one feature file (the atom)

You produce or revise exactly one file in Product/Features/ that conforms to the feature schema. Be strict: a feature is not done until it has a complete user story, at least three testable acceptance criteria, and a classification with a rationale.

Procedure

  1. Locate the product root. Find Product/Features/ from the current directory. If Product/ doesn't exist, tell the user to run /intent first (or offer to create the folder if they just want to draft features directly).

  2. New or revise?

    • Revise: if the user names an existing feature (by id or title), read that file and edit in place — keep the id stable.
    • New: scan Features/F*.md, find the highest F<NNN>, assign the next id. Filename = F<NNN>-<kebab-slug>.md.

  3. Gather the content. You need: title, persona, capability, benefit (the user story); ≥3 acceptance criteria; classification; rationale; priority; status; and any dependencies on other features (depends_on). If the caller (e.g. /innovate) supplied these, use them. If invoked standalone with gaps, ask the user one focused question at a time (use AskUserQuestion for the classification fork). Do not invent a user story from nothing — ask.

  4. Classify (mirror /classify's rubric):

    • Apply the decision test: "If a competitor shipped this exact feature tomorrow, would we lose our edge?" → innovation. "Would every competitor's product have this too?" → implementation.
    • Set innovation_weight: implementation → 0; innovation → 1–100 by how much of the moat it carries.
    • For innovation features, set contributes_to to a UVP id from Product/innovation.md (read it if present). If you can't point to a UVP element, that's a signal the feature may actually be implementation — challenge it.
    • Write a one-sentence classification_rationale.

  5. Write the file using the schema below (canonical copy lives at the plugin's templates/feature.md). Validate before finishing:

    • User story has all three clauses (As a… / I want… / so that…).
    • ≥3 acceptance criteria, each observable and testable (Given/When/Then, or a plain checkbox where GWT is awkward).
    • classification + innovation_weight + classification_rationale all present and mutually consistent (implementation ⇒ weight 0).

  6. Refresh the index. Note that Product/features-index.md is now stale; offer to run /classify (regenerates the ranked index) or /product-status.

Schema (reproduce exactly)

---
id: F00N
title: Short feature name
classification: innovation | implementation
innovation_weight: 0-100        # implementation = 0; innovation = 1-100
classification_rationale: One sentence.
contributes_to: UVP-x           # innovation features only
priority: must | should | could | wont
status: proposed | validated | building | done
risk_retired:
created_by_stage: ideation | innovation | manual
depends_on: [F00X]              # optional, structured — features this builds on
---

## User story
As a **<persona>**, I want **<capability>**, so that **<benefit>**.

## Acceptance criteria
- [ ] **Given** <context>, **when** <action>, **then** <result>.
- [ ] ...
- [ ] ...

## Notes & open questions
- ...

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 1 of the 12 instructions most product spec skills give in 816 tokens

Counted across 483 of the 502 authors here whose files we hold, read 2026-09-06

  • Write the PRD using the templatein 39 of 483, across 36 files
  • Ask one question at a timein 24 of 483
  • Write acceptance criteria in Given-When-Then formatin 24 of 483
  • Write user stories with acceptance criteriain 22 of 483, across 21 files
  • Respect ADRs in areas you touchin 21 of 483, across 17 files
  • Use the domain glossary vocabulary throughout the PRDin 20 of 483, across 16 files
  • Explore the repo to understand the current codebasein 19 of 483, across 15 files
  • Provide testable acceptance criteriahere, and in 19 of 483, across 17 files
  • Publish the PRD to the issue trackerin 18 of 483, across 14 files
  • Apply the ready-for-agent triage labelin 15 of 483, across 13 files
  • Prefer existing seams over new onesin 14 of 483, across 12 files
  • Save the PRD as a markdown filein 14 of 483, across 9 files

Said here and by no other author read

  • Find the product root before writing
  • Keep the feature id stable when revising
  • Assign the next sequential id for new features
  • Use caller-supplied content when available
  • Ask one focused question at a time when content is missing
  • Apply the competitor edge test to classify

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.