Learn-skills.dev agently-prompt-management
Use when the user is shaping how one model request or request family should be instructed or templated, including prompt slots, input/instruct/info layering, mappings, recursive placeholder injection, prompt config, YAML or config-file-driven prompt behavior, and reusable prompt structure.
install
source · Clone the upstream repo
git clone https://github.com/NeverSight/learn-skills.dev
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/NeverSight/learn-skills.dev "$T" && mkdir -p ~/.claude/skills && cp -r "$T/data/skills-md/agentera/agently-skills/agently-prompt-management" ~/.claude/skills/neversight-learn-skills-dev-agently-prompt-management && rm -rf "$T"
manifest:
data/skills-md/agentera/agently-skills/agently-prompt-management/SKILL.mdsource content
Agently Prompt Management
Use this skill when the core problem is how prompt state should be structured before one request or request family runs.
Native-First Rules
- prefer
,input(...)
,instruct(...)
, andinfo(...)
over concatenated prompt stringsoutput(...) - move reusable prompt structure into prompt config or YAML instead of ad hoc literals
- keep runtime variables as
placeholders in prompt files and inject them through mappings at load time${...} - keep task-specific request contracts in prompt config, and keep only widely reused persona setup in small code-side factories
- keep prompt composition separate from transport and orchestration
- use config files as an editable bridge when UI or product teams need to adjust prompt-driven behavior without rewriting workflow code
Anti-Patterns
- do not flatten business context into one opaque string unless the task is trivial
- do not rebuild prompt templates through ad hoc
or string concatenation when prompt mappings already fit.format(...) - do not use prompt config files as a substitute for workflow state
Read Next
references/overview.md