prompt-engineering
Skill0 starsChanged 15 days agoMITView on GitHub
State role, task, constraints, output schema, and a verification step.
86 other projects use a version of this.
Adopted by
Most recently taken up by
- niki914/zafirotheir own version, first seen Nov 15, 2026
- Muvon/octomind-taptheir own version, first seen Nov 12, 2026
- ishandutta2007/Awesome-Claude-Skillstheir own version, first seen Nov 8, 2026
- kazemcodes/skill-treetheir own version, first seen Nov 8, 2026
- MMACABRE/SKILLStheir own version, first seen Nov 8, 2026
- Hoerire/Azurtheir own version, first seen Nov 8, 2026
Used with
Projects with it also use security-checklist, multi-agent-orchestration and 8 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.
atuljha23Skillsecurity-checklist
OWASP-style quick reference — authn/authz, injection, secrets, sessions, crypto, dependencies. Use during code review and before committing security-sensitive changes.
Also in 3 projects that use this
javalenciacaiSkillmulti-agent-orchestration
Design and coordinate multi-agent systems where specialized agents work together to solve complex problems. Covers agent communication, task delegation, workflow orchestration, and result aggregation. Use when building coordinated agent teams, complex workflows, or systems requiring specialized expertise across domains.
Also in 4 projects that use this
GoogleSkillcoding-principles
Enforces engineering, architecture, public API, and code quality standards distilled from human reviewer feedback across A2UI pull requests. Use when authoring new code, refactoring, addressing review feedback, or reviewing PR diffs. Don't use for release publishing or spec blueprint generation without code or PR changes.
Also in 3 projects that use this
mjunaidcaSkilltool-design
Design tools that agents can use effectively. Use when creating new tools for agents, debugging tool-related failures, or optimizing existing tool sets.
Also in 3 projects that use this
LangChainSkillweb-research
Use this skill for requests related to web research; it provides a structured approach to conducting comprehensive web research
Also in 4 projects that use this
LuisSambranoSkillfirecrawl
Deep web scraping, screenshots, PDF parsing, and website crawling using Firecrawl API
Also in 3 projects that use this
Other versions86 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 86
- trycompai/comp★ 2.1ksame name
- niki914/zafiro★ 371same name
- CodeAlive-AI/ai-driven-development★ 184same name
- grandamenium/cortextos★ 106same name
- nahid-sparktales/agent-dispatcher★ 59same name
- geekatron/jerry★ 37same name
- nimadorostkar/Claude-Skills-collection★ 37same name
- Bbar0n234/learnflow-ai★ 35same name
- sabahattink/antigravity-fullstack-hq★ 30same name
- VoDaiLocz/kilo-kit-mcp★ 27same name
76 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 repository99 other files it gives its agents.
- accessibilitySkill
- api-designSkill
- api-docsSkill
- authenticationSkill
- authorizationSkill
- backup-recoverySkill
- career-planSkill
- changelogSkill
- ci-pipelinesSkill
- citation-checkSkill
- cloud-costSkill
- code-reviewSkill
- content-strategySkill
- context-budgetSkill
- conversion-optimizationSkill
- copy-editingSkill
- copywritingSkill
- coverage-strategySkill
- cryptographySkill
- data-qualitySkill
- data-visualizationSkill
- debuggingSkill
- decision-logSkill
- design-systemSkill
- dockerSkill
- documentationSkill
- e2e-testingSkill
- email-marketingSkill
- etl-designSkill
- experiment-designSkill
- experiment-methodsSkill
- fact-checkingSkill
- feedback-loopSkill
- flaky-testsSkill
- forecastingSkill
- fuzz-testingSkill
- go-concurrencySkill
- grant-writingSkill
- incident-opsSkill
- incident-responseSkill
- injection-defenseSkill
- integration-testingSkill
- interview-prepSkill
- job-fitSkill
- kubernetesSkill
- legacy-codeSkill
- linux-troubleshootingSkill
- literature-reviewSkill
- llm-evaluationSkill
- marketing-analyticsSkill
- meeting-facilitationSkill
- ml-evaluationSkill
- networkingSkill
- observabilitySkill
- onboardingSkill
- paid-adsSkill
- pandas-analysisSkill
- patent-searchSkill
- peer-reviewSkill
- portfolioSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 76 edited versions we read keep these.
4
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 16
Remove anything that does not change the decision.
- Distinctive: line 17
Test one failure mode.
- Distinctive: line 31
No fabricated sources, data, or test results.
- Distinctive: line 32
If the task falls outside the method, say so and stop.
“Common” is measured: kept by at least 6 in 10 of the 76 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
Prompt engineering
Use
Apply this when the task matches the description. Keep the output decision-useful and mark unknowns.
Method
- State the context, constraints, and output contract.
- Remove anything that does not change the decision.
- Test one failure mode.
- Record what was verified.
Focus: Prompt engineering.
Verification
- Output matches the schema.
- One failure mode was tested.
- State clearly what was not verified.
Boundaries
- This is a checklist, not proof of correctness.
- No fabricated sources, data, or test results.
- If the task falls outside the method, say so and stop.
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.

