write-feature-request

A guided writer for feature requests—documents that explain a problem, proposed solution, expected outcome, and requirements. It also creates acceptance criteria, meaning testable conditions for completion.

In plain words
What is it for?
Use it to shape product ideas, prepare backlog items, define requirements, and produce testable criteria for each requirement.
Why use it?
It helps turn an idea into a complete engineering-ready request and exposes unanswered questions before work begins.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/felipecabargas/gambit/write-feature-request
Any agent
npx skills add felipecabargas/gambit --skill write-feature-request
Clone the repo
git clone --depth 1 https://github.com/felipecabargas/gambit

Made for: Claude Code, Codex.

Per session 150 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,763 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00150 $0.02763
Opus 5 $0.00075 $0.01381
Sonnet 5 $0.00030 $0.00553
Haiku 4.5 $0.00015 $0.00276

Measured 2d ago against content hash 8ca22c65de18, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

write-feature-request scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/write-feature-request/SKILL.md · 274 lines

How it starts

The opening of the file, as written. The whole thing — 274 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Feature Request Author

When to Use

Use this skill to create high-quality, structured feature requests. It's most valuable when:

  • You have an idea or problem but need help shaping it into a full FR
  • You want to ensure requirements are complete before handing off to engineering
  • You need to produce an FR with testable Acceptance Criteria (ACs) built in
  • You want to surface open questions and risks before work begins
  • You are preparing a feature for backlog refinement or stakeholder review

How the Skill Works

The skill runs in a multi-step conversation. At each step it asks focused questions, evaluates the quality of your answers, and only proceeds when it has enough information to produce excellent output.

Before starting: If the user's input reads as exploratory — vague problem description, no clear outcome defined, or language like "I'm thinking about..." or "wondering if we should..." — surface this before proceeding:

"If you're still exploring the problem space, /superpowers:brainstorming is a good first step — it sharpens the problem statement before we commit to a spec."

If the user's input is specific and outcome-focused, skip the nudge and proceed directly.

Existing FR scan (silent): Before asking questions, scan for related work:

find . -maxdepth 4 \( -name "FR-*.md" -o -name "feature-request-*.md" \) 2>/dev/null | head -10

If related FRs are found, surface them before proceeding: "I found [N] existing feature requests that may be related — [titles]. Is this a new spec, or should we update one of these?"

Phase 1 — Information Gathering

The skill collects four foundational inputs:

Input Questions Asked
Problem What pain or gap exists? Who is affected? What is the evidence this is a real problem?
Solution What do we want to build to solve it? What does it look like or do? What does it not do?
Outcomes What customer value does this deliver? What changes for users if this is shipped?
Requirements What must the feature do (functional) and how well must it do it (non-functional)? Each requirement is captured independently with its type.

Read the full file on GitHub · 274 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 274 lines · 150 tokens per session scan A 8ca22c65de18

Subscribe to this mod's changes

write-feature-request is a skill published in the GitHub repository felipecabargas/gambit (2 stars, last pushed 3mo ago), licensed MIT. It adds 150 tokens to every session and 2,763 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

antigravity

Run the Antigravity CLI (Gemini) as a collaborating AI inside Claude Code, with intelligent model routing across the software development lifecycle. Claude is the conductor/orchestrator — requirements, architecture, the hard 20%, verification, and review — and routes deterministic, high-volume work (scaffolding…

yuting0624/antigravity-for-claude-code · 199 tokens

migrate-to-antigravity

Move an existing Claude Code setup onto the Antigravity CLI (agy) — user skills, CLAUDE.md, auto-memory, MCP servers, installed plugins, permissions and trusted workspaces. Use when the user says "migrate to Antigravity", "move my Claude Code config to agy", "bring my skills/memory/MCP over", "set up agy like my…

yuting0624/antigravity-for-claude-code · 123 tokens

vr-planner

Plans how to verify changes to an os-autoinst-distri-opensuse (OSADO) checkout. Use this skill when the user asks "how do I test my change", "what verification run (VR) should I do", "which openQA job should I clone", or "what's affected by my edit". Determines required unit tests, affected test modules, YAML…

mpagot/os-autoinst-distri-opensuse-skills · 90 tokens

openqa-log-analyzer

A specialized skill for analyzing openQA logs — triage failures, measure command timing, detect infrastructure lag, extract command output, and compare runs across multiple log files.

mpagot/os-autoinst-distri-opensuse-skills · 39 tokens

local-lint-test

Recommends the fastest local commands to validate edited OSADO code before pushing. Activate when the user asks "how do I check my code", "what should I run locally", "lint my changes", "does this compile", "run perltidy", "run perlcritic", "run a unit test", "check formatting", or after editing files to verify…

mpagot/os-autoinst-distri-opensuse-skills · 111 tokens

test-catalog

Add or audit a Perldoc documentation header on an OSADO test module following the test catalog standard. Use when a user asks to "add header", "document", or "add catalog header" to a Perl test module.

mpagot/os-autoinst-distri-opensuse-skills · 50 tokens