Self Report Agent Skill
Use when you hit a problem with Horizon *itself* worth telling the maintainers — a tool that keeps erroring, a guardrail that misfired on a benign action, a capability/tool you needed but don't have, or an instruction that was confusing or self-contradictory. Files high-signal feedback via the report_to_maintainers tool, which always asks the user before sending.
Install
one command, takes just this skill from the repositorynpx skills add https://github.com/google/adk-samples --skill self-reportThe instruction itself
4 sections, as written by the authorSelf-report to maintainers
You can send feedback about Horizon itself to the people who build it, using the
report_to_maintainers tool. You are often the best-placed reporter: you know
exactly which tool failed, what you expected, and what got in your way.
When to use this skill
Reach for report_to_maintainers when, during normal work, you notice
something wrong with *the agent or its tooling* (not with the user's own code):
- A tool errors repeatedly on a reasonable call (≈3+ times) and it looks like a
defect, not your mistake → category: "bug".
- A guardrail or egress block stops a clearly benign action → `category:
"guardrail_misfire"`.
- You needed a tool/capability that doesn't exist to finish a normal task →
category: "capability_gap".
- An instruction in your guidance is contradictory or impossible to follow →
category: "confusing_instruction".
- Anything else maintainers should know →
category: "other".
Do not use it for problems in the user's project (file those the user's
way), for one-off transient errors you can work around, or to chat.
How to file a good report
- One distinct issue per report. The tool de-duplicates within a session, so it
won't send the same (category, summary) twice — don't try to re-send.
summary: a tight one-line title.details: what you did, what happened, and
what you expected — repro-style, like a good bug report.
- Keep
include_contextfalse by default. Set it true only when the
conversation itself is the evidence the maintainer needs. Even then, the tool
shows the user the draft and asks before anything is sent, and the attached
summary is redacted.
Consent is not yours to skip
report_to_maintainers always asks the user to confirm before sending. If the
first call returns status: "awaiting_user_response", stop and let the user
decide — do not claim you filed anything. Only a status: "filed" result means
it was sent. A status: "declined" means the user said no; respect it and move
on. Never try to send feedback through any other channel.
Other skills for the same job
different authors, same section of the catalogue
Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify existing spreadsheets while preserving formulas, (4) Data analysis and visualization in spreadsheets, or (5) Recalculating formulas
Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like \"the xlsx in my downloads\") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.
Picks random winners from lists, spreadsheets, or Google Sheets for giveaways, raffles, and contests. Ensures fair, unbiased selection with transparency.
Query openFDA API for drugs, devices, adverse events, recalls, regulatory submissions (510k, PMA), substance identification (UNII), for FDA regulatory data analysis and safety research.
MATLAB and GNU Octave numerical computing for matrix operations, data analysis, visualization, and scientific computing. Use when writing MATLAB/Octave scripts for linear algebra, signal processing, image processing, differential equations, optimization, statistics, or creating scientific visualizations. Also use when the user needs help with MATLAB syntax, functions, or wants to convert between MATLAB and Python code. Scripts can be executed with MATLAB or the open-source GNU Octave interpreter.
UMAP dimensionality reduction. Fast nonlinear manifold learning for 2D/3D visualization, clustering preprocessing (HDBSCAN), supervised/parametric UMAP, for high-dimensional data.
Creating interactive data visualisations using d3.js. This skill should be used when creating custom charts, graphs, network diagrams, geographic visualisations, or any complex SVG-based data visualisation that requires fine-grained control over visual elements, transitions, or interactions. Use this for bespoke visualisations beyond standard charting libraries, whether in React, Vue, Svelte, vanilla JavaScript, or any other environment.
Access AlphaFold 200M+ AI-predicted protein structures. Retrieve structures by UniProt ID, download PDB/mmCIF files, analyze confidence metrics (pLDDT, PAE), for drug discovery and structural biology.
How to use it
Take google/self-report from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.