plugin-impact-review
Assessment of plugin skill and hook changes needed after MCP or config changes. Evaluates skill references, hook context, config-format docs, and output style references. Invoked via skillPointer when filling plugin-impact notes.
pinned to #c42244bupdated 2 weeks ago
Ask your AI client: “install skills/plugin-impact-review”.
Requires the metahub MCP server installed in your client. Set up MCP.
mh install skills/plugin-impact-reviewmetahub onboarded this repo on the author's behalf.
If you own github.com/jpicklyk/task-orchestrator on GitHub, claim the listing to take over publishing. Your claim preserves the existing eval history and badges; only the curator label is replaced with verified-publisher on your next publish.
Stars
196
Last commit
2 weeks ago
Latest release
published
- #ai-coding-assistant
- #ai-development
- #ai-harness
- #ai-memory
- #ai-tools
- #claude
- #claude-code
- #claude-desktop
- #context-persistence
- #developer-tools
- #harness-engineering
- #harness-framework
- #mcp
- #mcp-server
- #model-context-protocol
- #task-management
- #vibe-coding
- #workflow-automation
About this skill
Pulled from SKILL.md at publish time.
Evaluate which plugin components need updating after changes to MCP tools, config format, or response shapes.
Evaluation report
WarningsAutomated checks the publisher passed at publish time — structure, docs, safety, and whether the artifact behaves as claimed.c42244b· 2 weeks ago
Kind-specific
31Skill: SKILL.md present
found at .claude/skills/plugin-impact-review/SKILL.md · frontmatter source: SKILL.md
Skill: body content present
277 words · 1,871 chars · 6 sections · 2 code blocks
Skill: triggers declaredwarn
No `trigger` phrases in SKILL.md frontmatter
Add `trigger:` lines so Claude knows when to activate this skill — e.g. `when building MCP servers` or `for diagram creation`.
Skill: allowed-tools scope
no allowed-tools restriction (Claude may use anything)
Release history
1- releasecurrentc42244bwarn2 weeks ago
Contents
Evaluate which plugin components need updating after changes to MCP tools, config format, or response shapes.
Step 1: Skill Impact
Search all skill files for references to the changed behavior:
grep -r "<tool-name>\|<config-key>\|<changed-concept>" claude-plugins/task-orchestrator/skills/
For each match:
- Does the skill reference the old behavior, field name, or response shape?
- Does the skill need updated instructions or examples?
- Are trigger phrases still accurate?
Step 2: Hook Impact
Search hook scripts for references:
grep -r "<tool-name>\|<changed-concept>" claude-plugins/task-orchestrator/hooks/
For each match:
- Does the hook inject context that references the old behavior?
- Does the hook read tool input/output fields that changed?
- Does the hook matcher still target the correct tool name?
Step 3: Config Format Documentation
Check claude-plugins/task-orchestrator/skills/manage-schemas/references/config-format.md:
- YAML structure example reflects current format
- Field reference table has all current fields
- Descriptions match current behavior
Step 4: Output Style References
Check output styles for stale references:
-
workflow-orchestrator.md— any references to changed tools, fields, or workflows - Zone 1 (shared core) vs Zone 2/3 (extensions) — changes in Zone 1 must be synced to
workflow-analyst.md
Step 5: Plugin Caching
- Are hook scripts changed? If yes,
/plugin marketplace remove+ re-add required (content cached) - Are skill files changed?
/reload-pluginssufficient (read at invocation) - Are output styles changed?
/reload-pluginssufficient
Output
Compose the plugin-impact note listing specific files and sections that need changes. Note /mcp reconnect requirements.
Reviews
No reviews yet. Be the first.
Related
Frontend Slides
Create beautiful slides on the web using Claude's frontend skills
Gpt Researcher
An autonomous agent that conducts deep research on any data using any LLM providers
orchestration-patterns
>
mh install skills/plugin-impact-review