guidelines
Skill1.1k starsChanged 7 months agoApache-2.0View on GitHub
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
5 other projects use a version of this, 2 of them edited.
Trending
Quiet since July.about the whole repository
Most recently taken up by
- crocotaste/crocotaste-plugintheir own version, first seen Nov 1, 2026
- lthoangg/OpenAgentdedited, first seen Oct 25, 2026
- microsoft/github-copilot-modernizationtheir own version, first seen Sep 22, 2026
- shellui/skillstheir own version, first seen Sep 15, 2026
- zen-mcp/browseredited, first seen Apr 25, 2026
Who's talking about akash-network/node
- akash-network/provider“fix: 295: Shell access to a SHM mounted workload”GitHub · Jul 21, 2026 · 1 reactions
- sotskov-do/lava-specs“feat(spec): add Akash chain spec”GitHub · Jul 5, 2026
- akash-network/support“audit: scope AllProvidersAttributes and AuditorAttributes pagination to provider prefix”GitHub · Jun 8, 2026
- akash-network/support“audit: scope AllProvidersAttributes and AuditorAttributes pagination to provider prefix”GitHub · Jun 8, 2026
- overlock-network/provider-akash“Migrate provider to chain-sdk for Akash node v2 / sandbox-2 compatibility”GitHub · Apr 29, 2026
The biggest 5 of 17 mentions linking to the repository that our crawl found. Each line is their own headline.
See all 17
Talked about on GitHub (17 times).
On GitHub · 17
- Jul 21, 2026fix: 295: Shell access to a SHM mounted workload — akash-network/provider1 reaction · 1 comment
- Jul 5, 2026feat(spec): add Akash chain spec — sotskov-do/lava-specs0 reactions · 8 comments
- Jun 8, 2026audit: scope AllProvidersAttributes and AuditorAttributes pagination to provider prefix — akash-network/support0 reactions
- Jun 8, 2026audit: scope AllProvidersAttributes and AuditorAttributes pagination to provider prefix — akash-network/support0 reactions
- Apr 29, 2026Migrate provider to chain-sdk for Akash node v2 / sandbox-2 compatibility — overlock-network/provider-akash0 reactions
12 more on GitHub
- Jan 7, 2026refactor: moved ErrInternal from node repo and added ABCICode asserti… — akash-network/chain-sdk0 reactions · 1 comment
- Apr 1, 2025provider: fix `autostake` snapshot — akash-network/helm-charts0 reactions · 1 comment
- Jun 25, 2024deps: refactor goreleaser - add static builds with libwasmvm (backport #3157) — cosmos/gaia0 reactions
- Jun 23, 2024deps: refactor goreleaser - add static builds with libwasmvm — cosmos/gaia0 reactions · 1 comment
- May 13, 2024make akash-api a SDK — akash-network/support0 reactions · 4 comments
- Apr 23, 2024Add support for Private Registries in Cloudmos and AkashJS — akash-network/console0 reactions
- Feb 27, 2024GPU ram is not included when parsing SDL in Cloudmos — akash-network/console0 reactions · 1 comment
- Nov 8, 2023Upgrade Akash to v0.26.2 — cosmos/chain-registry0 reactions
- Jun 8, 2023Fix Akash to 0.22.7 for Huckleberry — cosmos/chain-registry0 reactions
- Apr 11, 2023`lease-shell` breaks with `remote server returned 404` once provider service gets restarted (`.manifest.deployments` track breaks as well) — akash-network/support0 reactions · 6 comments
- Jan 24, 2023provider: prometheus exporter - monitor deployments, bids, leases, attributes, ... — akash-network/support0 reactions
- Jan 22, 2023provider: `AKASH_CLUSTER_WAIT_READY_DURATION` code has been removed in akash `v0.16.5-rc0` — akash-network/support0 reactions · 4 comments
Other versions5 projects use a version of this.
Word for word · 0
None found.
Edited · 2
- lthoangg/OpenAgentd★ 21799% same
- zen-mcp/browser★ 298% same
Wrote their own version · 3
- microsoft/github-copilot-modernization★ 48same name
- shellui/skills★ 2same name
- crocotaste/crocotaste-plugin★ 1same 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 repository4 other files it gives its agents.
- setup-envSkill
- build-contractsSkill
- upgrade-changelogSkill
- vanitySkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
15 rules. 0 are common, 14 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 5 edited versions we read keep these.
14
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 17
If multiple interpretations exist, present them - don't pick silently.
- Distinctive: line 18
If a simpler approach exists, say so.
- Distinctive: line 19
If something is unclear, stop.
- Distinctive: line 25
No features beyond what was asked.
- Distinctive: line 26
No abstractions for single-use code.
- Distinctive: line 28
No error handling for impossible scenarios.
- Distinctive: line 29
If you write 200 lines and it could be 50, rewrite it.
- Distinctive: line 31
Ask yourself: "Would a senior engineer say this is overcomplicated?" If yes, simplify.
- Distinctive: line 37
When editing existing code:
- Distinctive: line 38
Don't "improve" adjacent code, comments, or formatting.
- Distinctive: line 39
Don't refactor things that aren't broken.
- Distinctive: line 41
If you notice unrelated dead code, mention it - don't delete it.
- Distinctive: line 43
When your changes create orphans:
- Very specific: line 44
Remove imports/variables/functions that YOUR changes made unused.
- Distinctive: line 45
Don't remove pre-existing dead code unless asked.
“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
Guidelines
Tradeoff: These guidelines bias toward caution over speed. For trivial tasks, use judgment.
1. Think Before Coding
Don't assume. Don't hide confusion. Surface tradeoffs.
Before implementing:
- State your assumptions explicitly. If uncertain, ask.
- If multiple interpretations exist, present them - don't pick silently.
- If a simpler approach exists, say so. Push back when warranted.
- If something is unclear, stop. Name what's confusing. Ask.
2. Simplicity First
Minimum code that solves the problem. Nothing speculative.
- No features beyond what was asked.
- No abstractions for single-use code.
- No "flexibility" or "configurability" that wasn't requested.
- No error handling for impossible scenarios.
- If you write 200 lines and it could be 50, rewrite it.
Ask yourself: "Would a senior engineer say this is overcomplicated?" If yes, simplify.
3. Surgical Changes
Touch only what you must. Clean up only your own mess.
When editing existing code:
- Don't "improve" adjacent code, comments, or formatting.
- Don't refactor things that aren't broken.
- Match existing style, even if you'd do it differently.
- If you notice unrelated dead code, mention it - don't delete it.
When your changes create orphans:
- Remove imports/variables/functions that YOUR changes made unused.
- Don't remove pre-existing dead code unless asked.
The test: Every changed line should trace directly to the user's request.
4. Goal-Driven Execution
Define success criteria. Loop until verified.
Transform tasks into verifiable goals:
- "Add validation" → "Write tests for invalid inputs, then make them pass"
- "Fix the bug" → "Write a test that reproduces it, then make it pass"
- "Refactor X" → "Ensure tests pass before and after"
For multi-step tasks, state a brief plan:
1. [Step] → verify: [check]
2. [Step] → verify: [check]
3. [Step] → verify: [check]Strong success criteria let you loop independently. Weak criteria ("make it work") require constant clarification.
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.

