chat
Skill1 starsChanged 13 days agoMITView on GitHub
Starts the ticket workflow from a request typed in chat, without a Jira or Linear ticket. Turns "fix this bug" or "add this feature" into a local ticket with testable acceptance criteria and a CHAT-<n> key, then runs the normal track. Use when someone asks in chat to fix, build, add or change something and gives no ticket key.
8 other projects use a version of this.
Adopted by
Most recently taken up by
- vercel-labs/json-rendertheir own version, first seen Nov 8, 2026
- reutavidan/zetesis-plugintheir own version, first seen Nov 1, 2026
- agoopintsai/shiprighttheir own version, first seen Nov 1, 2026
- sarvamai/skillstheir own version, first seen Sep 28, 2026
- tonydzi/second-brain-starter-kittheir own version, first seen Sep 8, 2026
- maxwellsdm1867/wheelertheir own version, first seen Aug 8, 2026
Other versions8 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 8
- vercel-labs/json-render★ 19ksame name
- sarvamai/skills★ 72same name
- maxwellsdm1867/wheeler★ 12same name
- tonydzi/second-brain-starter-kit★ 6same name
- agoopintsai/shipright★ 2same name
- Mheaus/claude-skills★ 1same name
- reutavidan/zetesis-plugin★ 0same name
- verging-ai/agent-skills★ 0same name
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 repository22 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .cursor/rules/00-ticket-workflow.mdcCursor rule
- .cursor/rules/10-general-standards.mdcCursor rule
- .cursor/rules/20-backend-standards.mdcCursor rule
- .cursor/rules/30-frontend-standards.mdcCursor rule
- .cursor/rules/40-database-standards.mdcCursor rule
- .cursor/rules/50-testing-standards.mdcCursor rule
- backend-implementSkill
- codebase-exploreSkill
- db-migrationSkill
- frontend-implementSkill
- gitlab-mrSkill
- implementation-planSkill
- jira-createSkill
- mr-feedbackSkill
- mr-reviewSkill
- quick-fixSkill
- run-checksSkill
- self-reviewSkill
- ticket-intakeSkill
- ticket-qaSkill
- write-testsSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.
0
Common
Most of the 5 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 19
Leave out Sub-tasks. More than one mergeable part → ask the human to split it into separate requests.
- Very specific: line 27
Start the track for CHAT-<n>: Bug → /quick-fix.
“Common” is measured: kept by at least 6 in 10 of the 5 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
Start from chat (no ticket)
A request typed in chat becomes a local ticket, so the same tracks, tests first and checks apply. A chat ticket has no tracker: what the workflow would post to a ticket, you say in chat and log in PROGRESS.md.
Steps
- Type: Bug (something is broken), Feature (new or changed behaviour) or Task (no behaviour change: a refactor, an upgrade). Unclear → ask.
- Draft the ticket with the template for its type, from
.cursor/skills/jira-create/: Bug →bug-template.md, Feature →enhancement-template.md, Task →task-template.md. Keep every heading.- At the top:
Type: <Bug|Feature|Task>, then the request word for word on aRequest:line. - The request says nothing about a section: write
None, or add a line under Open Questions. Never invent steps, error text, numbers, names or root causes. - Acceptance criteria: numbered, each one a check a test can make (Given / When / Then fits most).
- Leave out Sub-tasks. More than one mergeable part → ask the human to split it into separate requests.
- At the top:
- Missing parts (Bug: steps to reproduce, actual and expected result; Feature and Task: acceptance criteria): ask for them in ONE message (max 5 questions), each with your best guess so the human can answer "yes".
- Show the draft. Then write exactly:
Reply "start" or "changes: <feedback>".STOP. - On
start, pick the key:n= 1 + the highest number afterCHAT-in.agent/work/and ingit branch -a --list '*CHAT-*'(aftergit fetch -q origin), or 1 if there's none. The key isCHAT-<n>. - Save the draft as
.agent/work/CHAT-<n>/TICKET.md. Tell the human the key:Continue CHAT-<n>picks it up in a new chat, like any ticket. - Start the track for
CHAT-<n>: Bug → /quick-fix. Feature or Task → /ticket-intake (the full track).
Done when
- The human typed
start; TICKET.md has the request word for word and testable acceptance criteria - The track's first skill runs for
CHAT-<n>
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.