reflect
Skill893 starsChanged yesterdayBSD-3-ClauseView on GitHub
Reflect on recent work and bring all project documentation up to date. Use after landing a chunk of work, or when asked to update docs, agent instructions, or project knowledge.
183 other projects use a version of this.
Adopted by
Most recently taken up by
- TencentBlueKing/bk-litetheir own version, first seen Nov 16, 2026
- GoBeromsu/craft-skillstheir own version, first seen Nov 16, 2026
- gfunc/skillstheir own version, first seen Nov 16, 2026
- shiwenbin1617/pstacktheir own version, first seen Nov 16, 2026
- anis-dr/skillstheir own version, first seen Nov 16, 2026
- backnotprop/pstacktheir own version, first seen Nov 15, 2026
Used with
Projects with it also use poteto-help, setup-pstack 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.
ianclearySkillpoteto-help
Guides users through pstack setup, /poteto-mode, and picking the skill, playbook, or principle for a task. Type /poteto-help with a question.
Also in 14 projects that use this
bnemaSkillsetup-pstack
Configure which Pi models pstack uses per role. Detects available provider/model specs and writes pstack's user configuration. Use for /setup-pstack, "configure pstack models", or changing pstack model choices.
Also in 24 projects that use this
eryzerzSkillmake-bot-ui
Use when building a custom UI (page, dashboard, buttons) that should wake a Grok Bot over a webhook, when the user must provide a webhook sender key, or when exposing that UI on Tailscale.
Also in 19 projects that use this
ianclearySkillprinciple-explain-the-number
Apply before you trust, report, or act on a number you measured: a speedup, a regression, a throughput, a latency, or an eval result. Find what limits it, and rule out that it measured something other than the work you think.
Also in 26 projects that use this
jaydubya818Skillautomate-me
Use when the user wants working preferences captured in a reusable mode skill.
Also in 39 projects that use this
jaydubya818Skillpoteto-mode
Use when non-trivial work should follow the smallest rigorous Jstack workflow.
Also in 27 projects that use this
- +6 more from jaydubya818
Other versions183 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 183
- Yeachan-Heo/oh-my-claudecode★ 41ksame name
- Yeachan-Heo/oh-my-claude-sisyphus★ 41ksame name
- github/gh-aw★ 5.6ksame name
- backnotprop/pstack★ 4.2ksame name
- github/squad★ 3.4ksame name
- rilldata/rill★ 3ksame name
- microsoft/waza★ 1.5ksame name
- llama-farm/llamafarm★ 837same name
- haddock-development/claude-reflect-system★ 373same name
- egregore-labs/egregore★ 293same name
173 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.
The file
We split this skill into the rules it gives an agent
9 rules. 0 are common, 6 are distinctive, and 3 are very specific to this project.
0
Common
Most of the 173 edited versions we read keep these.
6
Distinctive
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 7
Update all project documentation to match the current state of the code.
- Distinctive: line 9
If the user provided additional context with the prompt, treat it as a focus area (e.g.
- Distinctive: line 13
Read AGENTS.md to understand the project structure.
- Distinctive: line 15
Run git log --oneline -20 to confirm what was actually landed.
- Distinctive: line 16
Search the codebase as needed to verify current state.
- Very specific: line 28
Follow the conventions in knowledge/README.md.
- Distinctive: line 30
Remove entries about code or files that no longer exist.
- Very specific: line 31
Check sizes with wc -c knowledge/*.md.
- Very specific: line 32
Keep it public: never move anything from a PRIVATE.* file into knowledge/ without asking.
“Common” is measured: kept by at least 6 in 10 of the 173 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
Update all project documentation to match the current state of the code. Fix gaps, stale content, spelling mistakes, and anything unclear. Make all edits — do not just list findings. Do not commit; the user will review first.
If the user provided additional context with the prompt, treat it as a focus area (e.g. "only README", "check AGENTS.md is accurate").
Steps
- Read
AGENTS.mdto understand the project structure. - Review the current chat session history — primary source of context for what changed.
- Run
git log --oneline -20to confirm what was actually landed. - Search the codebase as needed to verify current state.
What to update
- Inline documentation (JSDoc, comments)
- Markdown files (
README, design docs, contributing guides) - Agent instructions and skills (
AGENTS.md,.claude/skills/,copilot-instructions, etc.) - Project knowledge in
knowledge/(or whatever convention this project uses, seeAGENTS.md) - Design docs in
design/, if the project has them
Pruning project knowledge
Follow the conventions in knowledge/README.md. In particular:
- Move finished work out of
current.md: a summary tocompleted.md, the "why" todecisions.md, anything learned tolessons.md. Delete the rest. - Remove entries about code or files that no longer exist.
- Check sizes with
wc -c knowledge/*.md. Condense files that are over the size budgets, oldest entries first, and split a file by topic once pruning isn't enough. - Keep it public: never move anything from a
PRIVATE.*file intoknowledge/without asking.
Shared playbooks and lessons
agent-practices keeps playbooks and lessons that apply across projects (see AGENTS.md). Don't edit them from here. Instead, if this work turned up something general (a tool gotcha, an upgrade step, a playbook or lesson that was wrong or out of date), end with a short list of suggested additions or fixes, drafted in the format the folder's README.md describes. Open an issue or PR on agent-practices only if the user agrees. Leave out anything specific to this project, and anything private.
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.

