agentleFS
hyperlink-academyhyperlink-academy/leaflet/.claude/skills/spec/SKILL.md

spec

Skill527 starsChanged 4 months agoMITView on GitHub

Draft design documents and specs with research-informed questioning

168 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use backprop, ios-clean and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • JuliusBrusseeSkill

    backprop

    Bug → spec protocol. When a bug is found or a test fails, trace the cause, decide whether a new §V invariant would catch recurrence, append to §B. This is the one non-obvious thing SDD does that plan-then-execute doesn't. Triggers on test failure, bug report, post-mortem, or explicit user ask.

    Also in 4 projects that use this

  • Saqlain-811Skill

    ios-clean

    Remove the DebugBridge SPM package and all #if DEBUG wiring from an iOS app. (gstack)

    Also in 5 projects that use this

  • Saqlain-811Skill

    ios-fix

    Autonomous iOS bug fixer. (gstack)

    Also in 5 projects that use this

  • bastosSkill

    ios-design-review

    Review iOS app UI/UX design quality using Apple's design principles and the Liquid Glass-era design language from WWDC25/26. Use when asked for a design review, UX critique, visual design assessment, or evaluation of an app's interface quality, design intent, alignment with the new Apple design system, or usability. Triggers: "design review", "UX review", "visual design critique", "review the UI", "does this design work", "evaluate this interface", "design feedback", "Liquid Glass review".

    Also in 5 projects that use this

  • ShreyRaviSkill

    plan-tune

    Self-tuning question sensitivity + developer psychographic for gstack (v1: observational). Review which AskUserQuestion prompts fire across gstack skills, set per-question preferences (never-ask / always-ask / ask-only-for-one-way), inspect the dual-track profile (what you declared vs what your behavior suggests), and enable/disable question tuning. Conversational interface — no CLI syntax required.

    Also in 7 projects that use this

  • timurgaleevSkill

    document-generate

    Generate missing docs for a feature, module or project as tutorials, how-tos, reference and explanation.

    Also in 6 projects that use this

  • +2 more from Saqlain-811

The file

Show its rules and text

We split this skill into the rules it gives an agent

16 rules. 0 are common, 16 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 145 edited versions we read keep these.

  • 16

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill when the user explicitly requests a spec, design document, or similar planning artifact.

    line 11
  2. Distinctive:

    When starting a spec:

    line 17
  3. Distinctive:

    Ask the user for a brief description of what they want to build/change

    line 18
  4. Distinctive:

    Research-informed questions: Before asking about an area, do just-in-time codebase research.

    line 25
  5. Distinctive:

    Adaptive scope: When the designer marks something as out of scope, update your mental model and don't revisit.

    line 27
  6. Distinctive:

    Ask one focused question at a time, or a small related cluster

    line 32
  7. Distinctive:

    Avoid hypotheticals that don't apply to this codebase

    line 34
  8. Distinctive:

    When presenting options, describe tradeoffs without recommending unless asked

    line 35
  9. Distinctive:

    When the designer indicates readiness, produce the spec document.

    line 39
  10. Distinctive:

    Add other sections if the problem demands it.

    line 67
  11. Distinctive:

    No filler, hedging, or preamble

    line 71
  12. Distinctive:

    Start sections with substance, not meta-commentary

    line 73
  13. Distinctive:

    Use precise technical language

    line 74
  14. Distinctive:

    Keep decisions and rationale tight—one sentence each when possible

    line 75
  15. Distinctive:

    Prefer concrete over abstract.

    line 77
  16. Distinctive:

    Update status in the document as it progresses.

    line 85

“Common” is measured: kept by at least 6 in 10 of the 145 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Spec Writing

When to Use

Use this skill when the user explicitly requests a spec, design document, or similar planning artifact. Do not auto-trigger for routine tasks.

Process

1. Initial Scoping

When starting a spec:

  • Ask the user for a brief description of what they want to build/change
  • Reason about which question categories matter for this particular work—derive these from the problem, not a checklist

2. Interrogation Loop

Conduct open-ended questioning until the designer signals completion:

Research-informed questions: Before asking about an area, do just-in-time codebase research. Find relevant files, understand current patterns, identify constraints. Reference specific files and functions in questions when it adds clarity.

Adaptive scope: When the designer marks something as out of scope, update your mental model and don't revisit. However, flag when you believe there are gaps that could cause problems:

  • "This approach assumes X—is that intentional?"
  • "The current implementation of Y in src/foo.ts:42 handles Z differently. Should we align or diverge?"

Question style:

  • Ask one focused question at a time, or a small related cluster
  • Ground questions in what you've learned from the codebase
  • Avoid hypotheticals that don't apply to this codebase
  • When presenting options, describe tradeoffs without recommending unless asked

3. Spec Writing

When the designer indicates readiness, produce the spec document.

Output

Save to: /specs/YYYY-MM-DD-short-name.md

Required Elements

Title and status (draft | approved | implemented)

Goal: What this achieves and why. 1-3 sentences.

Design: The substance of what will be built/changed. For each significant component or concern:

  • Describe the approach
  • State key decisions with their rationale inline
  • Reference specific files, functions, and types where relevant
  • Structure subsections to fit the problem—no fixed format

Implementation: Ordered steps that an agent or developer can execute. Each step should:

  • Be concrete and actionable
  • Reference specific files/functions to modify or create
  • Be sequenced correctly (dependencies before dependents)

Optional

  • Background context (only if necessary for understanding)
  • Open questions (only if unresolved items remain)

Add other sections if the problem demands it.

Writing Style

  • No filler, hedging, or preamble
  • No "This document describes..." or "In this spec we will..."
  • Start sections with substance, not meta-commentary
  • Use precise technical language
  • Keep decisions and rationale tight—one sentence each when possible
  • Code references use file/path.ts:lineNumber or functionName in backticks
  • Prefer concrete over abstract; specific over general

Status Lifecycle

  • draft: Work in progress. Should not be merged to main.
  • approved: Designer has signed off. Ready for implementation.
  • implemented: Work is complete. Spec is now historical record.

Update status in the document as it progresses. Specs are point-in-time snapshots—do not update content after implementation begins except to change status.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.