/mention-validate
Validate all @-mentions resolve to existing files
$ npx -y skills add jmagly/aiwg --skill mention-validate --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/mention-validate
Context preview
The summary Claude sees to decide when to auto-load this skill.
Validate all @-mentions resolve to existing files
SKILL.md
mention-validate.SKILL.mdnamespace: aiwg
name: mention-validate
platforms: [all]
description: Validate all @-mentions resolve to existing files
<!-- AIWG-SKILL-CALLOUT --> > **Skill access pattern (post-kernel-pivot, 2026.5+)** > > Skill names referenced in this document are AIWG skills, **not slash commands**. Most are not kernel-listed and cannot be invoked as `/skill-name` by the platform. Reach them via: > > ```bash > aiwg discover "<capability>" > aiwg show skill <name> > ``` > > Only kernel-listed skills (`aiwg-doctor`, `aiwg-refresh`, `aiwg-status`, `aiwg-help`, `use`, `steward`) are directly invokable as slash commands. See [skill-discovery rule](../../../addons/aiwg-utils/rules/skill-discovery.md).
@-Mention Validation
Validate that all @-mentions in codebase resolve to existing files.
Usage
/mention-validate # Validate current directory
/mention-validate --strict # Fail on any broken mention
/mention-validate --output report.md # Write report to file
Options
| Option | Default | Description | |--------|---------|-------------| | --target | . | Directory to validate | | --strict | false | Exit with error on broken mentions | | --output | stdout | Write report to file |
Process
1. **Scan** all files for @-mention patterns 2. **Extract** @-mention paths 3. **Resolve** paths relative to repo root 4. **Report** broken/valid mentions
Output Format
@-Mention Validation Report
===========================
✓ Valid Mentions: 42
✗ Broken Mentions: 3
Broken Mentions:
src/auth/login.ts:5
@.aiwg/requirements/UC-999.md → NOT FOUND
.aiwg/architecture/sad.md:23
@.aiwg/requirements/NFR-PERF-005.md → NOT FOUND
test/integration/api.test.ts:12
@$AIWG_ROOT/src/services/api-old.ts → NOT FOUND (deleted?)
Summary: 3 broken mentions in 3 filesExit Codes
| Code | Meaning | |------|---------| | 0 | All mentions valid | | 1 | Broken mentions found (with --strict) |
CLI Equivalent
aiwg validate-mentions [--target <dir>] [--strict]
Related Commands
- `mention-wire` - Add @-mentions
- `mention-lint` - Lint @-mention style
- `mention-report` - Generate traceability report
Validate @-mentions for: $ARGUMENTS
References
- @$AIWG_ROOT/agentic/code/addons/aiwg-utils/README.md — aiwg-utils addon overview
- @$AIWG_ROOT/docs/cli-reference.md — CLI reference for validate-mentions command
- @$AIWG_ROOT/agentic/code/addons/aiwg-utils/rules/research-before-decision.md — Verify before reporting validity
- @$AIWG_ROOT/agentic/code/frameworks/sdlc-complete/README.md — SDLC artifact paths validated by this skill
Read more
namespace: aiwg name: mention-validate platforms: [all] description: Validate all @-mentions resolve to existing files
<!-- AIWG-SKILL-CALLOUT --> > **Skill access pattern (post-kernel-pivot, 2026.5+)** > > Skill names referenced in this document are AIWG skills, **not slash commands**. Most are not kernel-listed and cannot be invoked as `/skill-name` by the platform. Reach them via: > > ```bash > aiwg discover "<capability>" > aiwg show skill <name> > ``` > > Only kernel-listed skills (`aiwg-doctor`, `aiwg-refresh`, `aiwg-status`, `aiwg-help`, `use`, `steward`) are directly invokable as slash commands. See [skill-discovery rule](../../../addons/aiwg-utils/rules/skill-discovery.md).
@-Mention Validation
Validate that all @-mentions in codebase resolve to existing files.
Usage
/mention-validate # Validate current directory /mention-validate --strict # Fail on any broken mention /mention-validate --output report.md # Write report to file
Options
| Option | Default | Description | |--------|---------|-------------| | --target | . | Directory to validate | | --strict | false | Exit with error on broken mentions | | --output | stdout | Write report to file |
Process
1. **Scan** all files for @-mention patterns 2. **Extract** @-mention paths 3. **Resolve** paths relative to repo root 4. **Report** broken/valid mentions
Output Format
@-Mention Validation Report
===========================
✓ Valid Mentions: 42
✗ Broken Mentions: 3
Broken Mentions:
src/auth/login.ts:5
@.aiwg/requirements/UC-999.md → NOT FOUND
.aiwg/architecture/sad.md:23
@.aiwg/requirements/NFR-PERF-005.md → NOT FOUND
test/integration/api.test.ts:12
@$AIWG_ROOT/src/services/api-old.ts → NOT FOUND (deleted?)
Summary: 3 broken mentions in 3 filesExit Codes
| Code | Meaning | |------|---------| | 0 | All mentions valid | | 1 | Broken mentions found (with --strict) |
CLI Equivalent
aiwg validate-mentions [--target <dir>] [--strict]
Related Commands
- `mention-wire` - Add @-mentions
- `mention-lint` - Lint @-mention style
- `mention-report` - Generate traceability report
Validate @-mentions for: $ARGUMENTS
References
- @$AIWG_ROOT/agentic/code/addons/aiwg-utils/README.md — aiwg-utils addon overview
- @$AIWG_ROOT/docs/cli-reference.md — CLI reference for validate-mentions command
- @$AIWG_ROOT/agentic/code/addons/aiwg-utils/rules/research-before-decision.md — Verify before reporting validity
- @$AIWG_ROOT/agentic/code/frameworks/sdlc-complete/README.md — SDLC artifact paths validated by this skill
Multi-agent AI framework for Claude Code, Copilot, Cursor, Warp, and 6 more platforms 200+ agents, 109+ CLI commands, 400+ deployable agent/skill/command/rule artifacts, 8 core frameworks, 32 addons, and a 40-plugin Claude Code marketplace.
Repo: jmagly/aiwg
Other skills on aiwg.
- /agent-loop-ext
Crash-resilient external agent loop with state persistence and CI/CD integration
Open skill - /agent-loop
Detect requests for iterative autonomous agent loops and route to the appropriate loop executor
Open skill - /auto-test-execution
Automatically execute tests when code-generating agents modify source files, enforcing the execute-before-return pattern
Open skill - /cross-task-learner
Enable agent loops to learn from similar past tasks and share patterns across loops
Open skill - /debug-memory
Query and manage the executable feedback debug memory
Open skill - /execute-feedback
Execute tests on generated code and iterate until passing
Open skill

