agentleFS
Sign inStart free
edwinidrusedwinidrus/dragonhoard/skills/quick/SKILL.md

quick

Skill2 starsChanged 9 days agoMITView on GitHub

Small fix or change without milestones or packs: one quick task (Q<nn>) through the same evidence loop, with approved lessons loaded, a failing test first, every check and a journal, then stop. Use when the user says "quick fix", "small change", "just fix X", or invokes /dragonhoard:quick "<what>". Hands off to /dragonhoard:shape when the change turns out bigger.

18 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use plant-seed, discuss and 5 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.
  • notqueSkill

    plant-seed

    Capture forward-looking idea as a seed for future feature design.

    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

  • SentrySkill

    review

    Fixture review skill.

    Also in 6 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

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 2 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 15 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read <root>/LESSONS.md and apply every approved lesson that fits.

    line 33
  2. Distinctive:

    Run every standard check and record the counts.

    line 42
  3. Distinctive:

    Write the focused test first, run it, and confirm it fails for the expected reason.

    line 44
  4. Very specific:

    Run the focused test, then every standard check.

    line 56
  5. Very specific:

    Write a journal attempt with Outcome BLOCKED, then run dragonhoard.py log Q<nn> task.blocked "<reason.

    line 70
  6. Very specific:

    If the journal shows a FAIL→PASS story or a surprising root cause, offer /dragonhoard:learn (provenance Q<nn>#<attempt>).

    line 76

“Common” is measured: kept by at least 6 in 10 of the 15 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

dragonhoard quick

CLI: python3 "${CLAUDE_PLUGIN_ROOT}/scripts/dragonhoard.py" (called dragonhoard.py below). <root> is the root in dragonhoard.json; the standard checks are its checks.

Quick tasks live outside the milestones: they are not in STATUS.md or PROGRESS.md, and next never picks them. They still leave evidence and feed lessons. In hybrid mode, quick runs in this session and does not delegate.

0. Fit

Quick is for a change that touches about three files or fewer, needs no design choice between options and adds no dependency. If the request is bigger, say so, suggest /dragonhoard:shape (or /dragonhoard:explore for an open choice), and stop.

No dragonhoard.json: run /dragonhoard:init first.

1. Start

dragonhoard.py quick "<one-line title>"   # prints the ID (Q<nn>) and its journal path

Read <root>/LESSONS.md and apply every approved lesson that fits. Read only the files the change touches.

2. Plan

Restate the goal, the files and the acceptance in three lines or fewer.

3. Verify (before building)

  • Run every standard check and record the counts. If one is red before your change, record BLOCKED (section 6); do not fix unrelated breakage.
  • Write the focused test first, run it, and confirm it fails for the expected reason. If the change cannot be tested (docs, configuration), write that in the journal and name the check that proves it instead.

4. Build

Make the smallest change that meets the acceptance, in the files you named. If it needs more files or a design decision appears, stop: record BLOCKED with "grew beyond quick: <why>; owner: /dragonhoard:shape".

5. Test and record

Run the focused test, then every standard check. Append an attempt block to the journal in the format in <root>/README.md, with the real commands and the shortest decisive output line. A failed run is an attempt with Outcome FAIL and its root cause. Two failed bounded attempts at the same issue means BLOCKED.

When it passes:

dragonhoard.py log Q<nn> task.done "<one line: what now works>" --ref quick/<journal file>
dragonhoard.py digest

6. BLOCKED

Write a journal attempt with Outcome BLOCKED, then run dragonhoard.py log Q<nn> task.blocked "<reason; owner action>" and dragonhoard.py digest.

7. Stop

Report what was done and the evidence. Commits are an owner action; do not commit unless asked. If the journal shows a FAIL→PASS story or a surprising root cause, offer /dragonhoard:learn (provenance Q<nn>#<attempt>).

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.

Check your setup, free