work
Skill0 starsChanged 12 days agoApache-2.0View on GitHub
Run new work in ANY repository or notes folder through the generic pipeline — planner scopes it, implementer (and designer/writer) do it, tester breaks it, another provider reviews it, then a draft PR. Use for anything bigger than a one-file change in places that do not define their own /feature skill (a repo with its own /feature keeps using it). The owner asks in plain language; route it here yourself.
42 other projects use a version of this.
Adopted by
Most recently taken up by
- Firzus/agent-skillstheir own version, first seen Nov 8, 2026
- Mharbulous/probanda-devtheir own version, first seen Nov 8, 2026
- Jasenpan1987/multi-codetheir own version, first seen Nov 8, 2026
- withpiper/pipekittheir own version, first seen Nov 8, 2026
- cekrauseee/harnesstheir own version, first seen Nov 1, 2026
- cskwork/backend-dev-skillstheir own version, first seen Nov 1, 2026
Used with
Projects with it also use authoring, done 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.
automagik-devSkillauthoring
Write or revise a Genie skill so it survives the shipped contract — frontmatter, house size, starter card, and runtime-neutral voice.
Also in 3 projects that use this
robzolkosSkilldone
Reset the working directory for the next task by ensuring no uncommitted changes exist, then switching to the main branch and pulling latest.
Also in 3 projects that use this
Google CloudSkillfix
Plan a remediation strategy after a test failure.
Also in 4 projects that use this
AlexPEClubSkillrefine
Always use when the user wants to discuss an exsiting feature or specification. Open an existing feature spec to improve, extend, or fundamentally challenge it. Pass the feature ID as argument (e.g. /refine PROJ-2).
Also in 3 projects that use this
MicrosoftSkillmerge
Merge changes from the topic branch to the merge base branch. Use when the user wants to merge their session's work back to the base branch.
Also in 3 projects that use this
Microsoft AzureSkilltest
Also in 6 projects that use this
Other versions42 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 42
- cwinvestments/memstack★ 425same name
- automagik-dev/genie★ 351same name
- namastexlabs/automagik-genie★ 351same name
- ohad6k/emulo★ 292same name
- first-fluke/fullstack-starter★ 226same name
- OutThisLife/brooklyn-skills★ 207same name
- guardana/guardana★ 203same name
- Towow-ai/Flowness★ 107same name
- assaio/assaio★ 63same name
- HubSpot/agent-cli-skills★ 28same name
32 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 repository4 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- bugfixSkill
- cross-reviewSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 37 edited versions we read keep these.
2
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
- Distinctive: line 9
Follow the repository's own AGENTS.md/CLAUDE.md over anything here.
- Distinctive: line 13
If the request reads two ways that lead to different work, ask with AskUserQuestion (options, your recommendation first) before planning.
“Common” is measured: kept by at least 6 in 10 of the 37 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
/work — generic pipeline for new work
Say in one line that you are taking this route ("I am treating this as a size-M task").
Follow the repository's own AGENTS.md/CLAUDE.md over anything here.
0. Clarify
If the request reads two ways that lead to different work, ask with AskUserQuestion (options, your recommendation first) before planning. Do not ask what the code or docs already answer.
1. Plan
Size it. S (one file): do it in this session, skip to step 3.
M/L: launch the planner agent with the request and the repo path. If it
returns ## Blocking questions, ask the user and resume it with SendMessage. For
L, show the user the plan and wait for their approval.
2. Do
Launch implementer lanes in parallel — one area per lane, never two lanes on
one file. Add designer first for a visible change and writer for docs or
notes. Pass model explicitly on every Agent call: haiku for searches and
mechanical edits, sonnet for implementation and docs; opus only when a
money or security judgement truly cannot be covered by another provider.
Never fable without asking the owner first. Delegate in the order of the
model-selection playbook (local Qwen, Jules, Gemini, Antigravity's Claude, Codex,
and Claude subagents last; relayrace providers shows the owner's own order). Mechanical, verifiable chunks may go to the local model with
relayrace qwen --optional --task … when the repo has the kit installed;
SKIPPED means do it yourself.
3. Break it
Launch tester on the result. Fix what it finds (implementer), then re-run the
failing checks.
4. Independent review
Branch, commit (in the language specified by AGENTS.md, with the attribution lines the session gives you),
push and open a draft PR. Then have a DIFFERENT provider review it
read-only with .ai/prompts/review.md, following the cross-review skill:
probe the sandbox, list every path, verify every cited line. Fix confirmed
findings and review again.
5. Close
Merge only when the owner has authorized it. Report what changed, the commands you ran with results, what was not verified, and the PR link. If the work touched the AI setup, record it in the project's setup docs or work log.
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.