workflow
Skill404 starsChanged 49 days agoApache-2.0View on GitHub
Runs multi step work the way a careful senior engineer would: triage before code, a PRD in prds/, task.md kept current, docs synced after, and lessons recorded when a mistake repeats. Hands PRD writing to create-prd and the docs sync to update-project-docs. Use when a task spans several files or steps, changes architecture, needs a plan the user can review, or when the user says plan this, track this in task.md, or what did we learn.
74 other projects use a version of this.
Adopted by
Most recently taken up by
- raphaeltm/simple-agent-managertheir own version, first seen Nov 15, 2026
- waynesutton/convexskillsword for word, first seen Nov 15, 2026
- cognitive-fab/polygraphtheir own version, first seen Nov 15, 2026
- vercel/vercel-plugintheir own version, first seen Nov 12, 2026
- notque/vexjoy-agenttheir own version, first seen Nov 10, 2026
- zaynram/scholartheir own version, first seen Nov 8, 2026
Used with
Projects with it also use build-keil, can-debug 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.
ZhongYechengSkillbuild-keil
当需要通过 Keil MDK 命令行编译嵌入式工程,调用自带脚本解析工程文件、执行构建并定位固件产物时使用。
Also in 3 projects that use this
ZhongYechengSkillcan-debug
当需要调试 CAN 总线通信时使用,支持通过 USB-CAN 适配器监听、发送 CAN 帧和扫描节点。
Also in 3 projects that use this
iPlug2Skillbuild-cmake
Build an iPlug2 plugin project using CMake with Ninja, Xcode, or Visual Studio generators
Also in 3 projects that use this
- +9 more from ZhongYecheng
Other versions74 projects use a version of this.
Word for word · 1
- waynesutton/convexskills★ 404100% same
Edited · 0
None found.
Wrote their own version · 73
- openai/plugins★ 7.8ksame name
- vercel-labs/open-agents★ 5.8ksame name
- vercel/workflow★ 2.5ksame name
- orangehrm/orangehrm★ 1.1ksame name
- zhinkgit/embeddedskills★ 764same name
- waynesutton/markdown-site★ 628same name
- notque/vexjoy-agent★ 450same name
- notque/claude-code-toolkit★ 448same name
- brianlovin/claude-config★ 376same name
- vercel/vercel-plugin★ 336same name
63 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 repository24 other files it gives its agents.
- AGENTS.mdAGENTS.md
- templates/AGENTS.mdAGENTS.md
- avoid-feature-creepSkill
- convex-agentsSkill
- convex-best-practicesSkill
- convex-component-authoringSkill
- convex-cron-jobsSkill
- convex-file-storageSkill
- convex-functionsSkill
- convex-http-actionsSkill
- convex-migrationsSkill
- convex-realtimeSkill
- convex-schema-validatorSkill
- convex-security-auditSkill
- convex-security-checkSkill
- create-prdSkill
- devSkill
- git-safetySkill
- sec-checkSkill
- state-machinesSkill
- think-firstSkill
- update-project-docsSkill
- what-i-need-from-youSkill
- writeSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
15 rules. 0 are common, 11 are distinctive, and 4 are very specific to this project.
0
Common
Most of the 57 edited versions we read keep these.
11
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
- Distinctive: line 14
Triage: Read the request and the code before touching anything.
- Very specific: line 16
Track: Add the work to task.md under ## To Do.
- Very specific: line 19
Learn: If the user corrected the same thing twice, add a line to prds/lessons.md.
- Distinctive: line 34
Before writing code, answer these in a few lines:
- Distinctive: line 41
If the last answer is not empty, ask.
- Distinctive: line 47
Write one when any of these hold:
- Distinctive: line 62
Keep one item In Progress at a time when possible.
- Very specific: line 80
After each feature or fix, task.md, changelog.md, and files.md have to agree with the code.
- Distinctive: line 90
Keep the change set tight.
- Distinctive: line 91
Use one subagent per research question when the task is big enough to benefit.
- Distinctive: line 92
Stop and re plan if the work stops making sense.
- Distinctive: line 93
Before calling it done, ask: would a staff engineer approve this diff as is?
- Distinctive: line 103
Add a lesson when:
- Very specific: line 109
Read prds/lessons.md at the start of any session in that repo.
- Distinctive: line 116
Write a PRD for a one line change.
“Common” is measured: kept by at least 6 in 10 of the 57 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
Workflow
One loop for any task bigger than a typo. Triage, plan in a PRD, track in task.md, sync docs when done, and write down what went wrong so it does not repeat.
Skip this for one file fixes: a typo, a copy change, a single obvious bug. Just fix those.
The loop
- Triage. Read the request and the code before touching anything.
- PRD. Load
create-prdand writeprds/<slug>.md. Share it when the plan has a real choice in it. - Track. Add the work to
task.mdunder## To Do. Move items as they land. - Build. Small steps. Verify each one.
- Sync docs. Load
update-project-docsto updatetask.md,changelog.md, andfiles.md, then print the commit message. - Learn. If the user corrected the same thing twice, add a line to
prds/lessons.md.
Related skills, load them when the step comes up:
| Step | Skill |
| Writing the PRD | create-prd |
| Syncing docs after a change | update-project-docs |
| Any git command that could discard work | git-safety |
| Scope starts to drift | avoid-feature-creep |
| Blocked on the user, or the next step needs them | what-i-need-from-you |
| Before a deploy or a public repo | sec-check |
Triage
Before writing code, answer these in a few lines:
- What is missing, broken, or incomplete?
- What are two or three likely causes or approaches?
- Which one is most likely, and why?
- What is still unclear enough to ask about?
If the last answer is not empty, ask. One question, not five. Then wait.
For bugs, name the root cause before proposing the fix. A fix without a root cause is a guess.
When a PRD is needed
Write one when any of these hold:
- three or more files will change
- the schema changes
- an architectural choice is being made (auth, hosting, data model)
- a bug took real investigation to diagnose
- the work will be referenced later as a guide
Skip it for a single file fix that is obvious from logs or types, a typo, a CSS tweak, or a copy change.
Task tracking
task.md has three sections: ## To Do, ## In Progress, ## Completed.
- New work goes under To Do with a link to its PRD.
- Keep one item In Progress at a time when possible.
- An item moves to Completed after verification, not after the edit.
- Completed entries carry a
YYYY-MM-DD HH:mm UTCtimestamp, the files touched, and the verification command or outcome.
Good entry:
- [x] 2026-09-15 18:40 UTC Fix duplicate heartbeat writes. prds/heartbeat-dedup.md. convex/stats.ts, src/hooks/usePageTracking.ts. Verified: npx convex dev clean, no OCC retries in dashboard for 10 min.Bad entry:
- [x] fixed heartbeatDocs sync
After each feature or fix, task.md, changelog.md, and files.md have to agree with the code. update-project-docs has the rules. In short:
changelog.mdfollows Keep a Changelog. Dates come fromgit log --date=short, never from memory.files.mdgets new files added and stale descriptions fixed.- Claims about what shipped come from the diff, not from the plan.
Trigger it with /update, @update, or "update project docs".
Execution style
- Keep the change set tight. The request sets the scope. Extra ideas go in the summary, not the diff.
- Use one subagent per research question when the task is big enough to benefit. Do not run parallel edits on the same file.
- Stop and re plan if the work stops making sense. Update the PRD, then continue.
- Before calling it done, ask: would a staff engineer approve this diff as is?
Learning loop
prds/lessons.md is a flat list. One line per lesson, newest at the bottom:
- 2026-09-15 Do not add returns validators that duplicate the schema doc shape; share a validator constant instead.Add a lesson when:
- the user corrects the same pattern a second time
- a verification step catches something the plan missed
- a tool or API behaved differently from the docs
Read prds/lessons.md at the start of any session in that repo.
Never
- Deploy, publish, commit, or push. The user does those.
- Mark a task done without running the verification step in the PRD.
- Invent a date. Run
git logor use the current UTC time. - Write a PRD for a one line change.
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.

