open source tool skills updated, will move to separate plugin at a later time
This commit is contained in:
Brian Madison
parent
d48d40d397
commit
8cf22a4182
|
|
@ -1,7 +1,6 @@
|
||||||
---
|
---
|
||||||
name: bmad-os-audit-file-refs
|
name: bmad-os-audit-file-refs
|
||||||
description: Audit BMAD source files for file-reference convention violations using parallel Haiku subagents. Use when checking path references in workflow and task files.
|
description: Audit BMAD source files for file-reference convention violations using parallel Haiku subagents. Use when users requests an "audit file references" for a skill, workflow or task.
|
||||||
disable-model-invocation: true
|
|
||||||
---
|
---
|
||||||
|
|
||||||
Read `prompts/instructions.md` and execute.
|
Read `prompts/instructions.md` and execute.
|
||||||
|
|
|
||||||
|
|
@ -1,7 +1,6 @@
|
||||||
---
|
---
|
||||||
name: bmad-os-changelog-social
|
name: bmad-os-changelog-social
|
||||||
description: Generate social media announcements for Discord, Twitter, and LinkedIn from the latest changelog entry. Use when user asks to create release announcements, social posts, or share changelog updates. Reads CHANGELOG.md in current working directory. Reference examples/ for tone and format.
|
description: Generate social media announcements for Discord, Twitter, and LinkedIn from the latest changelog entry. Use when user asks to 'create release announcement' or 'create social posts' or share changelog updates.
|
||||||
disable-model-invocation: true
|
|
||||||
---
|
---
|
||||||
|
|
||||||
# Changelog Social
|
# Changelog Social
|
||||||
|
|
|
||||||
|
|
@ -1,7 +1,6 @@
|
||||||
---
|
---
|
||||||
name: bmad-os-diataxis-style-fix
|
name: bmad-os-diataxis-style-fix
|
||||||
description: Fixes documentation to comply with Diataxis framework and BMad Method style guide rules
|
description: Fixes documentation to comply with Diataxis framework and BMad Method style guide rules. Use when user asks to check or fix style of files under the docs folder.
|
||||||
disable-model-invocation: true
|
|
||||||
---
|
---
|
||||||
|
|
||||||
Read `prompts/instructions.md` and execute.
|
Read `prompts/instructions.md` and execute.
|
||||||
|
|
|
||||||
|
|
@ -1,7 +1,6 @@
|
||||||
---
|
---
|
||||||
name: bmad-os-draft-changelog
|
name: bmad-os-draft-changelog
|
||||||
description: Analyzes changes since last release and updates CHANGELOG.md ONLY. Does NOT trigger releases.
|
description: "Analyzes changes since last release and updates CHANGELOG.md ONLY. Use when users requests 'update the changelog' or 'prepare changelog release notes'"
|
||||||
disable-model-invocation: true
|
|
||||||
---
|
---
|
||||||
|
|
||||||
Read `prompts/instructions.md` and execute.
|
Read `prompts/instructions.md` and execute.
|
||||||
|
|
|
||||||
|
|
@ -1,14 +0,0 @@
|
||||||
# gh-triage
|
|
||||||
|
|
||||||
Fetches all GitHub issues via gh CLI and uses AI agents to deeply analyze, cluster, and prioritize issues.
|
|
||||||
|
|
||||||
## Usage
|
|
||||||
|
|
||||||
Run from within any BMad Method repository to triage issues.
|
|
||||||
|
|
||||||
## What It Does
|
|
||||||
|
|
||||||
1. Fetches all open issues via `gh issue list`
|
|
||||||
2. Splits issues into batches
|
|
||||||
3. Launches parallel agents to analyze each batch
|
|
||||||
4. Generates comprehensive triage report to `_bmad-output/triage-reports/`
|
|
||||||
|
|
@ -1,12 +1,6 @@
|
||||||
---
|
---
|
||||||
name: bmad-os-gh-triage
|
name: bmad-os-gh-triage
|
||||||
description: Fetch all GitHub issues via gh CLI and use AI agents to deeply analyze, cluster, and prioritize issues
|
description: Analyze all github issues. Use when the user says 'triage the github issues' or 'analyze open github issues'.
|
||||||
license: MIT
|
|
||||||
disable-model-invocation: true
|
|
||||||
metadata:
|
|
||||||
author: bmad-code-org
|
|
||||||
version: "3.0.0"
|
|
||||||
compatibility: Requires gh CLI, git repository, and BMad Method with Task tool support
|
|
||||||
---
|
---
|
||||||
|
|
||||||
Read `prompts/instructions.md` and execute.
|
Read `prompts/instructions.md` and execute.
|
||||||
|
|
|
||||||
|
|
@ -1,24 +0,0 @@
|
||||||
# release-module
|
|
||||||
|
|
||||||
Automates the complete release process for npm modules.
|
|
||||||
|
|
||||||
## Usage
|
|
||||||
|
|
||||||
Run from project root or pass project path:
|
|
||||||
```
|
|
||||||
bmad-utility-skills:release-module
|
|
||||||
```
|
|
||||||
|
|
||||||
## Prerequisite
|
|
||||||
|
|
||||||
First run `draft-changelog` to analyze changes and create a draft changelog.
|
|
||||||
|
|
||||||
## What It Does
|
|
||||||
|
|
||||||
1. Gets and confirms changelog entry
|
|
||||||
2. Confirms version bump type (patch/minor/major)
|
|
||||||
3. Updates CHANGELOG.md
|
|
||||||
4. Bumps version with `npm version`
|
|
||||||
5. Pushes git tag
|
|
||||||
6. Publishes to npm
|
|
||||||
7. Creates GitHub release
|
|
||||||
|
|
@ -1,7 +1,6 @@
|
||||||
---
|
---
|
||||||
name: bmad-os-release-module
|
name: bmad-os-release-module
|
||||||
description: Automates the complete release process for npm modules - version bump, changelog, git tag, npm publish, GitHub release
|
description: Perform requested version bump, git tag, npm publish, GitHub release. Use when user requests 'perform a release' only.
|
||||||
disable-model-invocation: true
|
|
||||||
---
|
---
|
||||||
|
|
||||||
Read `prompts/instructions.md` and execute.
|
Read `prompts/instructions.md` and execute.
|
||||||
|
|
|
||||||
|
|
@ -1,55 +0,0 @@
|
||||||
# Raven's Verdict - Deep PR Review Tool
|
|
||||||
|
|
||||||
Adversarial code review for GitHub PRs. Works with any LLM agent.
|
|
||||||
|
|
||||||
> **Status: Experimental.** We're still figuring out how to use this effectively. Expect the workflow to evolve.
|
|
||||||
|
|
||||||
## How It Works
|
|
||||||
|
|
||||||
Use `/bmad-os-review-pr` to review a specific PR:
|
|
||||||
|
|
||||||
> "Use /bmad-os-review-pr to review PR #123"
|
|
||||||
|
|
||||||
The tool will:
|
|
||||||
|
|
||||||
1. Check out the PR branch locally
|
|
||||||
2. Run an adversarial review (find at least 5 issues)
|
|
||||||
3. Transform findings into professional tone
|
|
||||||
4. Preview the review and ask before posting
|
|
||||||
|
|
||||||
See `prompts/instructions.md` for full prompt structure, severity ratings, and sandboxing rules.
|
|
||||||
|
|
||||||
## When to Use
|
|
||||||
|
|
||||||
**Good candidates:**
|
|
||||||
|
|
||||||
- PRs with meaningful logic changes
|
|
||||||
- Refactors touching multiple files
|
|
||||||
- New features or architectural changes
|
|
||||||
|
|
||||||
**Skip it for:**
|
|
||||||
|
|
||||||
- Trivial PRs (typo fixes, version bumps, single-line changes)
|
|
||||||
- PRs you've already reviewed manually
|
|
||||||
- PRs where you haven't agreed on the approach yet — fix the direction before the implementation
|
|
||||||
|
|
||||||
## Workflow Tips
|
|
||||||
|
|
||||||
**Always review before posting.** The preview step exists for a reason:
|
|
||||||
|
|
||||||
- **[y] Yes** — Post as-is (only if you're confident)
|
|
||||||
- **[e] Edit** — Modify findings before posting
|
|
||||||
- **[s] Save only** — Write to file, don't post
|
|
||||||
|
|
||||||
The save option is useful when you want to:
|
|
||||||
|
|
||||||
- Hand-edit the review before posting
|
|
||||||
- Use the findings as input for a second opinion ("Hey Claude, here's what Raven found — what do you think?")
|
|
||||||
- Cherry-pick specific findings
|
|
||||||
|
|
||||||
**Trust but verify.** LLM reviews can miss context or flag non-issues. Skim the findings before they hit the PR.
|
|
||||||
|
|
||||||
## Prerequisites
|
|
||||||
|
|
||||||
- `gh` CLI installed and authenticated (`gh auth status`)
|
|
||||||
- Any LLM agent capable of running bash commands
|
|
||||||
|
|
@ -1,7 +1,6 @@
|
||||||
---
|
---
|
||||||
name: bmad-os-review-pr
|
name: bmad-os-review-pr
|
||||||
description: Adversarial PR review tool (Raven's Verdict). Cynical deep review transformed into professional engineering findings. Use when asked to review a PR.
|
description: Adversarial PR review tool (Raven's Verdict). Cynical deep review transformed into professional engineering findings. Use when user asks to 'review a PR' and provides a PR url or id.
|
||||||
disable-model-invocation: true
|
|
||||||
---
|
---
|
||||||
|
|
||||||
Read `prompts/instructions.md` and execute.
|
Read `prompts/instructions.md` and execute.
|
||||||
|
|
|
||||||
Loading…
Reference in New Issue