npx skills add smithery/neversight --skill prompt-refinement
v1truv1us/ai-eng-system
prompt-refinement
Convert vague requests into compact TCRO prompts with phase-specific constraints. Used by research, specify, plan, and work workflows.
Installation
$
npx skills add v1truv1us/ai-eng-system --skill prompt-refinement
Similar popular skills
Related neighbors and high-traction skills in the same topics — useful to compare before installing.
find-skills
Same topic
vercel-labs/skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "fi…
3.3M installs
agent-browser
Same topic
vercel-labs/agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, includ…
810.4K installs
vercel-react-best-practices
Same topic
vercel-labs/agent-skills
697.8K installs
web-design-guidelines
Same topic
vercel-labs/agent-skills
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "chec…
617.3K installs
microsoft-foundry
Same topic
microsoft/azure-skills
Build, deploy, evaluate, optimize, fine-tune, and manage Microsoft Foundry agents, models, and …
576.5K installs
azure-prepare
Same topic
microsoft/azure-skills
Prepare azd-based Azure projects for deployment: generates azure.yaml, infrastructure (Bicep/Te…
568.3K installsAlso in this package
Other skills from v1truv1us/ai-eng-system · top by installs.
npx skills add v1truv1us/ai-eng-system
More details
Agent compatibility
Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.
Claude Code
Not declared
Cursor
Not declared
Codex
Not declared
GitHub Copilot
Not declared
Windsurf
Not declared
Gemini CLI
Not declared
Cline
Not declared
OpenCode
Not declared
Also listed on
Alternate registries and mirrors of this skill.
Repository health
Stars
8
License
LICENSE
Default branch
main
Open issues
0
Status
Active
Skill metadata
Parsed from SKILL.md frontmatter.
Version2.0.0
More metadata
- category
- model-invoked
- version
- 2.0.0
- tags
- prompting, tcro, requirements, workflow
Package contents
Files included with this skill beyond the listing page.
-
skill md
SKILL.md1,935 B -
docs
SUMMARY.md159 B
History
- First seen on skills.sh
- First recorded snapshot · 27 installs
SKILL.md
Default output: return the refined prompt only. Ask at most one blocking question.
Prompt refinement
Convert the request into TCRO:
- Task: observable objective.
- Context: relevant repository, user, or system facts.
- Requirements: constraints, acceptance criteria, and non-goals.
- Output: artifact, schema, destination, and length.
Do not add personas, stakes, challenge language, generic reasoning instructions, or confidence scores.
Phase requirements
Research
Specify the question, scope, source types, evidence standard, and desired depth. Default output is a short finding summary plus citations or a named report file.
Specify
Define users, behavior, interfaces, edge cases, compatibility, and acceptance criteria. Exclude implementation choices unless they are constraints.
Plan
Define the source spec, implementation boundaries, dependency order, verification commands, and completion criteria.
Work
Define the exact change, allowed scope, required tests, verification commands, and handoff output. Include a non-goal for likely scope creep.
Refinement rules
- Preserve explicit user wording where it carries intent.
- Infer reversible details from repository context.
- Ask only when a missing answer changes architecture, security, compatibility, or irreversible behavior.
- Replace vague terms with measurable checks.
- Remove duplicated context and optional prose.
Template
Task: <observable objective>
Context: <required facts>
Requirements:
- <constraint or acceptance criterion>
- Non-goal: <excluded scope>
Output: <artifact/schema/length>
Verify: <checks>