prompt-manager
# prompt-manager
What this skill does
# prompt-manager
CRUD operations for prompt files. Centralizes all prompt management logic to avoid shell parsing issues and provide consistent behavior across commands.
## Description
Manages prompt files in `{repo_root}/prompts/` with support for:
- Listing active and completed prompts
- Organizing active prompts in subfolders under `prompts/` (e.g. `prompts/providers/`)
- Getting the next available number
- Creating new prompts
- Moving prompts to completed
- Deleting prompts
- Reading prompt content
## Triggers
Use this skill when you need to:
- Find the next prompt number
- List existing prompts
- Create a new prompt file
- Move a prompt to completed
- Delete a prompt
- Read prompt content by number
## Tool Requirements
```yaml
tools:
- Bash(python3:*)
- Bash(PROMPT_MANAGER=:*)
```
## Commands
### Get Next Number
```bash
PROMPT_MANAGER=$(jq -r '.plugins."daplug@cruzanstx"[0].installPath' ~/.claude/plugins/installed_plugins.json)/skills/prompt-manager/scripts/manager.py
python3 "$PROMPT_MANAGER" next-number
```
Output: `006` (next available 3-digit number)
### List Prompts
```bash
# List all prompts
python3 "$PROMPT_MANAGER" list
# Filter to a folder under prompts/ (excludes completed/ by default)
python3 "$PROMPT_MANAGER" list --folder providers
# Tree view
python3 "$PROMPT_MANAGER" list --tree
# List as JSON
python3 "$PROMPT_MANAGER" list --json
# Active only
python3 "$PROMPT_MANAGER" list --active
# Completed only
python3 "$PROMPT_MANAGER" list --completed
```
### Find Prompt by Number
```bash
# Returns path to prompt file
python3 "$PROMPT_MANAGER" find 6
# Output: /path/to/repo/prompts/006-my-prompt.md
# Folder-qualified lookup
python3 "$PROMPT_MANAGER" find providers/6
# Output: /path/to/repo/prompts/providers/006-my-prompt.md
# Name search across folders
python3 "$PROMPT_MANAGER" find "backup-server"
# As JSON
python3 "$PROMPT_MANAGER" find 6 --json
```
### Read Prompt Content
```bash
python3 "$PROMPT_MANAGER" read 6
# Outputs the full content of the prompt
```
### Create Prompt
```bash
# From content argument
python3 "$PROMPT_MANAGER" create "backup-server" --content "Prompt content here"
# Into a subfolder (folder is relative to prompts/; completed/ is reserved)
python3 "$PROMPT_MANAGER" create "github-copilot-integration" --folder providers --content "..."
# From file
python3 "$PROMPT_MANAGER" create "backup-server" --content-file /tmp/prompt.md
# From stdin
cat prompt.md | python3 "$PROMPT_MANAGER" create "backup-server"
# With specific number
python3 "$PROMPT_MANAGER" create "backup-server" --number 010 --content "..."
# JSON output
python3 "$PROMPT_MANAGER" create "backup-server" --content "..." --json
```
### Complete Prompt (Move to completed/)
```bash
python3 "$PROMPT_MANAGER" complete 6
# Output: Completed: /path/to/repo/prompts/completed/006-my-prompt.md
```
### Delete Prompt
```bash
python3 "$PROMPT_MANAGER" delete 6
# Output: Deleted: 006-my-prompt.md
```
### Get Directory Info
```bash
python3 "$PROMPT_MANAGER" info
# Output:
# Repository root: /path/to/repo
# Prompts directory: /path/to/repo/prompts
# Completed directory: /path/to/repo/prompts/completed
# Next number: 006
# Active prompts: 2
# Completed prompts: 5
# Total prompts: 7
# As JSON
python3 "$PROMPT_MANAGER" info --json
```
## Integration Examples
### From /create-prompt
```bash
# Get plugin path
PLUGIN_ROOT=$(jq -r '.plugins."daplug@cruzanstx"[0].installPath' ~/.claude/plugins/installed_plugins.json)
PROMPT_MANAGER="$PLUGIN_ROOT/skills/prompt-manager/scripts/manager.py"
# Get next number
NEXT_NUM=$(python3 "$PROMPT_MANAGER" next-number)
echo "Next prompt will be: $NEXT_NUM"
# Create the prompt
python3 "$PROMPT_MANAGER" create "my-task-name" --content "$PROMPT_CONTENT" --json
```
### From /run-prompt
```bash
# Find prompt path
PROMPT_PATH=$(python3 "$PROMPT_MANAGER" find 6)
if [ -z "$PROMPT_PATH" ]; then
echo "Prompt 6 not found"
exit 1
fi
# Read content
CONTENT=$(python3 "$PROMPT_MANAGER" read 6)
```
## Error Handling
All errors are written to stderr with exit code 1:
```bash
$ python3 "$PROMPT_MANAGER" find 999
Error: Prompt 999 not found
$ python3 "$PROMPT_MANAGER" complete 6 # already completed
Error: Prompt 006 is already completed
$ python3 "$PROMPT_MANAGER" create "test" --number 5 # exists
Error: Prompt 005 already exists: /path/to/prompts/005-test.md
```
## JSON Output Schema
### PromptInfo
```json
{
"number": "006",
"name": "backup-server",
"filename": "006-backup-server.md",
"path": "/path/to/repo/prompts/006-backup-server.md",
"status": "active",
"folder": ""
}
```
### Info
```json
{
"repo_root": "/path/to/repo",
"prompts_dir": "/path/to/repo/prompts",
"completed_dir": "/path/to/repo/prompts/completed",
"next_number": "007",
"active_count": 2,
"completed_count": 5,
"total_count": 7
}
```
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.