agentleFS
Sign inStart free
codebycoreycodebycorey/delta-spec/skills/quick/SKILL.md

quick

Skill4 starsChanged 9 months agoMITView on GitHub

Quick start a change with minimal interaction. Use when fast-tracking a straightforward change that needs proposal, design, and tasks in one step.

We split this skill into the rules it gives an agent

9 rules. 0 are common, 3 are distinctive, and 6 are very specific to this project.

  • 0

    Common

    Most of the 13 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 6

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Create a complete change setup (proposal, design, tasks) with a single confirmation point.

    line 8
  2. Very specific:

    Arguments: If $ARGUMENTS is provided, use it as the name and optional description parameters.

    line 10
  3. Very specific:

    If name and description provided → use them

    line 18
  4. Very specific:

    If only name provided → infer description from conversation context

    line 19
  5. Distinctive:

    If neither provided → infer both from conversation context

    line 20
  6. Very specific:

    If specs/.delta/<name>/ already exists:

    line 25
  7. Distinctive:

    Ask: Continue with existing change, or pick a different name?

    line 27
  8. Very specific:

    If new → create specs/.delta/<name>/ directory

    line 28
  9. Very specific:

    Create specs/.delta/<name>/proposal.md using the standard template.

    line 32

“Common” is measured: kept by at least 6 in 10 of the 13 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

/ds:quick <name> [description] - Quick start a change

Create a complete change setup (proposal, design, tasks) with a single confirmation point.

Arguments: If $ARGUMENTS is provided, use it as the name and optional description parameters. Otherwise, infer from conversation context.

Step 0: Version Check

See version-check.md for the standard version compatibility check procedure.

Step 1: Parse arguments or infer from context

  • If name and description provided → use them
  • If only name provided → infer description from conversation context
  • If neither provided → infer both from conversation context
  • Generate a kebab-case name if inferring (e.g., "add-user-auth")

Step 2: Check for existing change

  • If specs/.delta/<name>/ already exists:
    • Warn: "Change '<name>' already exists"
    • Ask: Continue with existing change, or pick a different name?
  • If new → create specs/.delta/<name>/ directory

Step 3: Create proposal

Create specs/.delta/<name>/proposal.md using the standard template. See proposal-template.md.

Fill in sections based on the provided description and conversation context. Keep it concise but complete.

Step 4: Show proposal and confirm

Display the generated proposal to the user, then ask:

Proceed with planning and task generation? [y/N]

  • On "y" or "yes" → continue to Step 5
  • On "n", empty, or anything else → stop here
    • Tell user: "Proposal saved. You can refine it with /ds:new <name> or continue later with /ds:plan"

Note: Steps 5-7 run without additional prompts.

Step 5: Run planning

Execute the planning phase without interaction:

  1. Explore the codebase - Find relevant code, patterns, architecture
  2. Create design.md - See design-template.md for the format
  3. Create delta specs - Generate specs/.delta/<name>/specs/<domain>.md files

Step 6: Run task generation

Execute task generation without interaction:

  1. Analyze design and delta specs
  2. Identify implementation tasks
  3. Create tasks.md with ordered, actionable tasks
  4. Check for test infrastructure - include test tasks if tests exist

Step 7: Output summary

Display a summary of everything created:

✓ Created proposal.md
✓ Created design.md
✓ Created specs/<domain>.md
✓ Created tasks.md (N tasks)

Ready to implement. Run `/ds:archive` when complete.

Behavior Notes

  • Designed for straightforward changes with well-understood scope
  • For complex changes requiring discussion, use /ds:new → /ds:plan → /ds:tasks
  • The proposal confirmation is the single gate — it must capture the intended scope
  • Archive still requires separate confirmation (/ds:archive)

Download now (ZIP)

  • Other versions15 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 15

    1. notque/vexjoy-agent★ 444same name
    2. notque/claude-code-toolkit★ 442same name
    3. govctl-org/govctl★ 272same name
    4. joetawil7/first-pass★ 128same name
    5. buildomator/buildomator★ 101same name
    6. rizukirr/vibekit★ 20same name
    7. jamillazarev/multica-ops★ 11same name
    8. Yafan-Yang/ai-trading★ 4same name
    9. beeltec/skills★ 2same name
    10. foliveira/harmonia★ 2same name

    5 more not listed

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • Used alongsideProjects with it also use plant-seed, discuss and 4 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.
    • buildomatorSkill

      plant-seed

      Capture a forward-looking idea with trigger conditions — surfaces automatically at the right milestone

      Also in 3 projects that use this

    • markmdevSkill

      discuss

      Discuss a problem with other AI agents before implementing. Spawns one or more autonomous claude -p conversations with different perspectives (architect, critic, domain expert), runs multi-round discussions, and synthesizes findings. Use when facing design decisions, architecture tradeoffs, knowledge organization questions, or any problem that benefits from multiple viewpoints before committing to an approach. Also use proactively when you're uncertain about a direction.

      Also in 4 projects that use this

    • NVIDIASkill

      research

      Before designing a feature, research how comparable libraries solve the problem, check best practices, known pitfalls, and upstream changes. Use when starting a new feature, investigating an unfamiliar area, or the user asks to research something.

      Also in 4 projects that use this

    • AWSSkill

      ship

      Finalize dev work on an issue branch — update docs, push, and open a PR.

      Also in 3 projects that use this

    • Hugging FaceSkill

      implement

      Make tests pass. Invoke after /write-tests produces failing tests.

      Also in 3 projects that use this

    • SentrySkill

      review

      Fixture review skill.

      Also in 4 projects that use this

  • In this repository12 other files it gives its agents.

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.

Check your setup, free