quick
Skill1 starsChanged 3 months agoMITView on GitHub
Lightweight change workflow for small-scope tasks — add a field, change a query, tweak a response. Understands the codebase, confirms with you, then implements and tests. No blueprint, no integrate.
18 other projects use a version of this.
Adopted by
Most recently taken up by
- fab-codes/agent-workflow-templatetheir own version, first seen Nov 8, 2026
- AlleyBo55/no-overthinktheir own version, first seen Nov 8, 2026
- edwinidrus/dragonhoardtheir own version, first seen Nov 8, 2026
- notque/vexjoy-agenttheir own version, first seen Nov 7, 2026
- buildomator/buildomatortheir own version, first seen Nov 4, 2026
- joetawil7/first-passtheir own version, first seen Nov 1, 2026
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.
notqueSkillplant-seed
Capture forward-looking idea as a seed for future feature design.
Also in 3 projects that use this
markmdevSkilldiscuss
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
VercelSkillnext
Next.js renderer for json-render that turns JSON specs into full Next.js applications with routes, layouts, SSR, and metadata. Use when working with @json-render/next, building Next.js apps from JSON specs, or creating AI-generated multi-page applications.
Also in 3 projects that use this
SentrySkillreview
Fixture review skill.
Also in 6 projects that use this
NVIDIASkillresearch
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
AWSSkillship
Finalize dev work on an issue branch — update docs, push, and open a PR.
Also in 3 projects that use this
Other versions18 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 18
- notque/claude-code-toolkit★ 448same name
- notque/vexjoy-agent★ 448same name
- govctl-org/govctl★ 276same name
- joetawil7/first-pass★ 128same name
- buildomator/buildomator★ 102same name
- rizukirr/vibekit★ 20same name
- jamillazarev/multica-ops★ 11same name
- codebycorey/delta-spec★ 4same name
- Yafan-Yang/ai-trading★ 4same name
- AlleyBo55/no-overthink★ 3same name
8 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.
In this repository10 other files it gives its agents.
- blueprintSkill
- codebase-designSkill
- diagnoseSkill
- grill-with-docsSkill
- improve-codebase-architectureSkill
- integrateSkill
- setup-runtimeSkill
- setupSkill
- setup-styleSkill
- tddSkill
The file
We split this skill into the rules it gives an agent
12 rules. 0 are common, 10 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 15 edited versions we read keep these.
10
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 13
If the change turns out to need architectural discussion, hand off to /grill-with-docs.
- Distinctive: line 21
Read the user's request.
- Distinctive: line 22
Search the codebase for the relevant files — the controller, service, DAO, DTO, mapper XML that the change touches.
- Distinctive: line 23
Read CONTEXT.md (if it exists) for domain terminology.
- Distinctive: line 30
Before writing any code, present to the user:
- Distinctive: line 44
Wait for confirmation. Do not proceed until the user responds.
- Very specific: line 48
Read docs/house-style.md if it exists, then implement the change following the project's existing patterns — DTO → Mapper XML → Service, or …
- Distinctive: line 50
For a new field: add the field across all layers, then write one test asserting the field is present with the expected value.
- Distinctive: line 52
For a changed query: update the query, then write or update a test asserting the new behaviour.
- Distinctive: line 56
Prefer unit tests (mock external dependencies).
- Distinctive: line 60
Run the module's test suite to confirm no regressions.
- Distinctive: line 69
No interactive prompts beyond the Confirm phase.
“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.
Files
Quick
Purpose
For changes small enough that a full grill→blueprint→tdd→integrate pipeline is overkill. /quick reads the code, confirms the approach with you, then implements and tests.
If the change turns out to need architectural discussion, hand off to /grill-with-docs.
Execution
Phase 1: Understand
- Read the user's request.
- Search the codebase for the relevant files — the controller, service, DAO, DTO, mapper XML that the change touches.
- Read CONTEXT.md (if it exists) for domain terminology. If CONTEXT-MAP.md exists, read it and read each context relevant to the topic; if unclear which context applies, ask the user.
- Form a clear understanding: what changes, where, and why.
Output: a one-paragraph summary of what you understand the task to be, plus the files and layers involved. List any key method signatures or query fragments that will change (e.g. getUser response gains age: Integer).
Phase 2: Confirm
Before writing any code, present to the user:
- What you'll change — specific layers and direction (not implementation details).
ADR check — will this change introduce a new architectural decision?
No ADR needed → present the plan and ask: "Proceed?"
ADR possibly needed → warn the user and let them decide:
"This change may introduce a new architectural decision ([brief reason]) and could be larger than a quick change. Do you want to:
- Execute — proceed without an ADR, update CONTEXT.md only
- ADR + execute — write a new ADR and update CONTEXT.md, then execute
- Blueprint — the change is substantial; run
/blueprintfor a full plan instead - Grill — hand off to
/grill-with-docsinstead"
- Wait for confirmation. Do not proceed until the user responds.
Phase 3: Implement
Read docs/house-style.md if it exists, then implement the change following the project's existing patterns — DTO → Mapper XML → Service, or whatever layering the codebase uses. Then write a focused unit test that exercises the new or changed behaviour.
For a new field: add the field across all layers, then write one test asserting the field is present with the expected value.
For a changed query: update the query, then write or update a test asserting the new behaviour.
For multi-file changes serving one behaviour: implement all files, then write the test that covers the end-to-end behaviour.
Prefer unit tests (mock external dependencies). Use a lightweight integration test only when the behaviour must be verified across layers. Run the test for this change to confirm it works.
Phase 4: Report
- Run the module's test suite to confirm no regressions. If the change crosses module boundaries, widen the scope accordingly.
- Report what was changed, what tests were added, and the test results.
Rules
/quickhandles one behaviour — a single change serving one goal. Scope questions are resolved in Phase 2.- ADR judgment follows the same three-condition test as
/grill-with-docs: hard to reverse, surprising without context, the result of a real trade-off. - No interactive prompts beyond the Confirm phase. No checkbox tools.
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
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.

