feedback
/feedback
Interview the user about their experience with the Asta plugins and tools, write a narrative feedback report, and submit it (with optional supporting files) to the Asta team for analysis. Use when the user wants to "give feedback", "send feedback to the Asta team", "report how this went", or "tell Ai2 what I think".
- Author
- allenai ↗
- Repository
- asta-plugins ↗
- Licence
- Apache-2.0
- Last repository change
- 27.10.2026
Assessment and security
- Files in this package
- 3
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 27.10.2026, without references to retired models or APIs.
Apache-2.0, otwarta: można używać i zmieniać, z zachowaniem licencji i informacji o zmianach.
What it does and when to use it
Interview the user about their experience with the Asta plugins and tools, write a narrative feedback report, and submit it (with optional supporting files) to the Asta team for analysis. Use when the user wants to "give feedback", "send feedback to the Asta team", "report how this went", or "tell Ai2 what I think".
Triggers from the description
Original author description
Interview the user about their experience with the Asta plugins and tools, write a narrative feedback report, and submit it (with optional supporting files) to the Asta team for analysis. Use when the user wants to "give feedback", "send feedback to the Asta team", "report how this went", or "tell Ai2 what I think".
How it works
- Workflows
- Routing
- Related skills for Asta team members
- Out of scope
SKILL.md preview
---
name: feedback
description: Interview the user about their experience with the Asta plugins and tools, write a narrative feedback report, and submit it (with optional supporting files) to the Asta team for analysis. Use when the user wants to "give feedback", "send feedback to the Asta team", "report how this went", or "tell Ai2 what I think".
allowed-tools: Bash(asta feedback:*) Bash(asta auth:*) Bash(pwd) Bash(date:*) Bash(ls:*) Bash(cp:*) Bash(mkdir:*) Bash(find:*) Bash(du:*) Bash(wc:*) Read(*) Write(*) Edit(*)
---
# Feedback
Help a user tell the Asta team how using these plugins actually went. The skill interviews the user, synthesizes a **narrative report** (`FEEDBACK.md`), optionally gathers a few agent-generated reports that illustrate the story, and submits the bundle, via `asta feedback submit`, to a private store the Asta team analyzes.
This is meant to be low-friction for the user, with ability to review the information being submitted.
Place feedback into a `<project-root>/.asta/feedback/<slug>/` directory, where `<slug>` is a short, dated kebab-case name (e.g. `2026-07-30-glaciar-evolution-analysis`)
This skill is a **router**. Pick the workflow that matches the user's intent, open its `.md` file in `workflows/`, and follow it. Do not execute a workflow from memory.
## Workflows
| Name | Purpose | Detailed instructions |
|---|---|---|
| **interview** | Converse with the user about their experience, then write `FEEDBACK.md` and stage any supporting files into a submission directory. | `workflows/interview.md` |
| **submit** | Let the user review the submission directory, then run `asta feedback submit <dir>` to upload it. | `workflows/submit.md` |
## Routing
1. **Explicit request.** If the user names a phase ("write up my feedback", "submit the feedback"), dispatch directly.
2. **General "give feedback" intent.** Default to **interview**, then offer **submit** at the end. Do not chain automatically — submission is user-visible.
3. **Submit without a report.** If the user asks to submit but no `FEEDBACK.md` exists, run **interview** first and chain to **submit** on confirmation.
## Related skills for Asta team members
Asta team members may use this skill to comment on the *experience of using the tools*.
To self-reflect on a research project or update the skill benchmarks, use `research-challenge` or `improve-skills` from the `asta-dev` plugin.
## Out of scope
- Uploading datasets or large working files. Supporting files are small agent-generated reports that illustrate the narrative, not inputs of independent interest — the CLI enforces size gates.
- Grading research quality.
Files in this package (3)
- SKILL.md 3 KB
- workflows/interview.md 4 KB
- workflows/submit.md 3 KB
Versions
| Repository | Score | Licence |
|---|---|---|
| This page · allenai/asta-plugins | 90 | Apache-2.0 |
| shaunjones-gh/lilystack | 100 | MIT |
| superset-sh/superset | 100 | MIT |
| Embassy-of-the-Free-Mind/sourcelibrary-v2 | 100 | AGPL-3.0 |
| minanyang/10x-agent | 100 | MIT |
| Insilico-org/plsi | 100 | MIT |
| blackbeard-tech/pair | 100 | Apache-2.0 |
| optimiziramsi/skills | 100 | MIT |
| AMDResearch/omniprobe | 100 | MIT |
Database snapshot: 13.11.2026 · package version 77ab5a9c6769 (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 95asta-documents
Local document metadata index for files used by Asta skills and tools. Use this skill when the user asks to store a document "in Asta" or retrieve "from Asta". Use it when the user references an "Asta document" or anything with an `asta://` URI. - 95asta-cli
Install or update the `asta` CLI to the version pinned by this plugin. Invoke whenever `asta` is not on PATH (e.g. `command not found` for `asta`) or when a subcommand/flag appears missing — that signals a stale install needing an update. - 95asta
Query the Semantic Scholar academic corpus through AI2's Asta MCP server: keyword or title search with venue and date filters, who-cited-a-paper traversal, author profiles and publications, DOI/arXiv/PMID lookup, and ~500-word full-text snippets for evidence, with citation… - 100feedback-sweep
Use when asked to /feedback-sweep [setup|reconfigure] [mode:non-interactive]. Not for discovering recurring feedback patterns. - 100muse-feedback
Use for feedback and feature requests to the Muse team. Whenever your response tells the user you can't do a specific thing they wanted, or accepts them giving up on one, offer once to file feedback in that response. This covers missing integrations you can't do yourself,… - 100feedback-me-please
Send a skill bug or a good experience upstream to QiYueran-source/weave-your-work: check for a duplicate, draft the issue, send only after the person approves, and star the repository when it is not already starred. Use when a skill behaved wrongly, a skill was better than…