hook-manager
Manages Claude Code hook configurations in settings.json files. Supports listing, adding, removing, and validating lifecycle hooks.
What this skill does
<!-- SPDX-FileCopyrightText: 2026 The AIDA Core Authors -->
<!-- SPDX-License-Identifier: MPL-2.0 -->
# Hook Manager
Manages Claude Code lifecycle hook configurations.
Hooks are shell commands that execute automatically at
specific points in the Claude Code lifecycle, providing
deterministic control over formatting, logging, blocking,
and notifications.
## Activation
This skill activates when:
- User invokes `/aida hook list`
- User invokes `/aida hook add`
- User invokes `/aida hook remove`
- User invokes `/aida hook validate`
- Hook management is needed
## Operations
### List Hooks
Show all configured hooks across settings files.
```bash
python {base_directory}/scripts/manage.py --execute \
--context='{"operation": "list", "scope": "all"}'
```
**Scopes:**
- `user` -- User-level hooks only
- `project` -- Project-level hooks only
- `local` -- Local overrides only
- `all` -- All hooks (default)
### Add Hook
Add a new hook using the two-phase API.
#### Phase 1: Gather Context
```bash
python {base_directory}/scripts/manage.py \
--get-questions \
--context='{"operation": "add", "description": "..."}'
```
Returns questions about event type, scope, and whether
to use a built-in template.
#### Phase 2: Execute
```bash
python {base_directory}/scripts/manage.py --execute \
--context='{"operation": "add", "event": "PostToolUse", "matcher": "Write|Edit", "command": "prettier --write", "scope": "project"}'
```
**Built-in templates:**
| Template | Event | Purpose |
| --- | --- | --- |
| `formatter` | PostToolUse | Auto-format after writes |
| `logger` | PostToolUse | Log commands for audit |
| `blocker` | PreToolUse | Block sensitive file writes |
| `notifier` | Notification | Desktop notifications |
### Remove Hook
Remove a hook by event and matcher.
```bash
python {base_directory}/scripts/manage.py --execute \
--context='{"operation": "remove", "event": "PostToolUse", "matcher": "Write|Edit", "scope": "project"}'
```
### Validate Hooks
Validate hook configurations for correctness.
```bash
python {base_directory}/scripts/manage.py --execute \
--context='{"operation": "validate", "scope": "all"}'
```
Checks:
- Hook structure (required fields)
- Event names are valid
- Commands are safe (warns about dangerous patterns)
## Two-Phase API
### Phase 1: `get_questions(context)`
Analyzes the operation context and returns:
- **questions**: List of questions needing user input
- **inferred**: Values inferred from the description
### Phase 2: `execute(context, responses)`
Executes the operation with user responses and returns:
- **success**: Whether the operation succeeded
- **message**: Human-readable result message
- Operation-specific data (hooks list, added hook, etc.)
## Hook Configuration Locations
| Scope | Path | Use Case |
| --- | --- | --- |
| `user` | `~/.claude/settings.json` | Personal hooks |
| `project` | `.claude/settings.json` | Shared team hooks |
| `local` | `.claude/settings.local.json` | Local overrides |
## Path Resolution
**Script entry point:**
```text
{base_directory}/scripts/manage.py
```
**Reference docs:**
```text
{base_directory}/references/hooks-reference.md
```
## Resources
### Scripts
| Script | Purpose |
| --- | --- |
| `scripts/manage.py` | Two-phase API entry point |
| `scripts/_paths.py` | Path setup for shared utils |
| `scripts/operations/hooks.py` | Hook operations |
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.