eli5
Explain a topic like I'm a 5 year old. Use when the user types /eli5 <topic> or asks for a…
Submit feedback about the TRES Claude plugin — bug reports, feature requests, skill improvements, new skill ideas, MCP issues, workflow friction, or positive feedback about what's working well. Use this skill whenever the user wants to share any kind of feedback about the
$ npx -y skills add anthropics/claude-plugins-community --skill tres-request-skill-update --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/tres-request-skill-updateContext preview
The summary Claude sees to decide when to auto-load this skill.
Submit feedback about the TRES Claude plugin — bug reports, feature requests, skill improvements, new skill ideas, MCP issues, workflow friction, or positive feedback about what's working well. Use this skill whenever the user wants to share any kind of feedback about the
name: tres-request-skill-update description: > Submit feedback about the TRES Claude plugin — bug reports, feature requests, skill improvements, new skill ideas, MCP issues, workflow friction, or positive feedback about what's working well. Use this skill whenever the user wants to share any kind of feedback about the plugin, its skills, or the TRES MCP. Trigger phrases include: "submit feedback", "report a bug", "request a feature", "suggest an improvement", "I have an idea", "something is broken", "the skill isn't working", "I love this skill", "this worked great", "the MCP is returning wrong data", "the flow is confusing", "can you fix the skill", "file a skill request", "give feedback", "this could be better". Also trigger proactively when the conversation appears to be wrapping up — e.g. the user says "thanks", "that's all", "looks good", "we're done", "nothing else", or any other signal that the task is complete. In that case, offer a brief feedback prompt instead of launching the full guided flow. Do NOT trigger for general questions about how a skill works — only when the user wants to submit feedback or the conversation is ending.
Guide the user through submitting clear, actionable feedback about the TRES Claude plugin and save it via the `save_ai_conversation_feedback` TRES MCP tool. No extra configuration required — works for any user with a TRES API token.
This skill operates in two modes:
1. **Explicit feedback** — the user asks to submit feedback, report a bug, etc. Run the full guided flow starting at Step 1. 2. **End-of-conversation prompt** — the conversation is wrapping up. Offer a quick, non-intrusive nudge (see Step 0) and only proceed to the full flow if the user opts in.
---
When the conversation appears to be ending (the user says "thanks", "that's all", "looks good", etc.) and this skill is triggered proactively:
Ask casually:
> **Before you go — any feedback on how this session went? Bugs, ideas, or things that could > be better? Happy to log it for the team in 30 seconds.**
and stop. Do NOT push further.
but keep it lightweight. Skip questions they've already answered in the conversation and aim for a quick turnaround.
---
1. Call `get_viewer` (TRES MCP, no arguments) to identify the submitter.
2. Get the user's git identity for the feedback record:
git config user.name && git config user.email
Use line 1 as `agent_name` and line 2 as `agent_email`. If git is not available, use the system username and leave email empty.
Tell the user: **"You're connected as {orgName}. What feedback would you like to share?"**
---
Let the user describe their feedback in their own words first. Then classify it into one of these categories based on what they said:
| Category | When to use | |---|---| | Bug report | Something is broken, erroring, or producing wrong results | | Feature request | A new capability that doesn't exist yet | | Improvement | An existing feature works but could be better (UX, formatting, flow, performance) | | New skill idea | A proposal for an entirely new skill | | MCP / data issue | The TRES MCP is returning wrong data, missing fields, or behaving unexpectedly | | Positive feedback | Something is working well and the user wants the team to know | | General feedback | Anything else — workflow friction, confusion, documentation, onboarding |
Confirm the category with the user: **"It sounds like this is a {category} — is that right?"**
If the feedback is about a specific skill or MCP tool, identify which one. If it's general or about the plugin overall, note that.
**Known skills:**
| Skill | Description | |---|---| | `tres-asc845-swap-reprice-skill` | ASC 845 swap repricing to zero clearing account residuals | | `tres-explorer-tx-to-ledger` | Add explorer TX to the TRES ledger | | `tres-tx-story` | TX flow diagram and explanation | | `tres-recon-gaps` | Reconciliation gap resolution | | `tres-asset-balance-validation` | Balance validation vs DeBank | | `tres-report-analyzer` | Analyze TRES report XLSX exports | | `tres-report-advisor` | Recommend the right TRES report | | `tres-invoice-bill-matching` | Match txs to ERP invoices/bills | | `tres-export-3rd-party-contacts` | Export unidentified counterparties to XLSX | | `tres-import-contacts` | Import contacts from CSV/XLSX | | `tres-cost-basis` | Cost basis calculation, strategy, issues, reevaluations, exports | | `tres-rollup-rules` | Sub-transaction rollup rules (aggregate txs) | | `tres-onboarding` | Full entity onboarding (orchestrates sub-skills) | | `tres-settings-management` | Org and platform settings | | `tres-wallets-upload` | Wallet onboarding | | `tres-upload-tx-header-validation` | Bulk transaction CSV header naming validation | | `tres-request-skill-update` | This feedback skill |
> **Maintainer note**: update this table when new skills are added to the plugin.
---
Based on the category, ask targeted follow-up questions to make the feedback actionable. Ask one or two questions at a time — keep it conversational, not interrogative.
**For bug reports:**
**For feature requests & im
Community-contributed plugins for Claude Cowork and Claude Code.
Repo: anthropics/claude-plugins-community
Explain a topic like I'm a 5 year old. Use when the user types /eli5 <topic> or asks for a…
Write an implementation plan as one interactive HTML page - a tree of claims (why › what ›…
Use the `quickdesign` CLI to generate AI media — UGC promo videos, image edits, product…
Use only when the user explicitly asks for a TestDino audit of Playwright automated test…
Use when the user wants to check TestDino connection status, validate their PAT, discover…
Use when the user wants to manage a manual execution run or update case-level results inside…