Felo X Search on dshDeepSeek Harness

Regressions show up on X before they show up in your issue tracker

When a release goes wrong, the first useful reports are usually posts from strangers hitting the same wall. This skill reads X so a debugging session can check whether the problem is yours alone.

Bundle
felo-skills/felo-x-search
Reads
Posts, replies, profiles
Comes back as
Signals with handles
Use it when
You are debugging blind
Mount itcp -r felo-skills/felo-x-search .dsh/skills/
Built for dshPosts and repliesSignal, not sentiment
Get an API keySee the platform guide
DeepSeek Harness logo
This skill runs on

DeepSeek Harness

Open-source agent harness (developer preview)

Read the DeepSeek Harness guide

dsh reads skills straight out of folders you point it at, so a Felo bundle is one copy away from being callable in a session — and one delete away from being gone.

Loads from
~/project/.dsh/skills/ · ~/.agents/skills/
Install is
A folder copy, no build step
Worth knowing
Only direct children of a root are read
What you get back

A feed where every post carries a reason to care

Social results are noisy by default. The skill tags each post with what it contributes — a reproduction, a workaround, a confirmation, or nothing at all.

@backend_ines14h

Upgraded overnight and our workers now leak connections after roughly six hours. Rolling back fixed it.

Reproduction
@sre_marcus11h

Same here. Setting the pool to close idle sockets is a workaround until it is patched.

Workaround
@hugo_builds9h

Cannot reproduce on 3.1, only on the new async path. Might be limited to long-lived processes.

Scope
@release_notes_bot7h

Maintainer replied in the issue thread: fix is queued for the next patch release.

Status

Ask for the distinction explicitly: "separate confirmed reports from speculation, and tell me how many people each one comes from."

Read this before you trust it

X is a lead, not a measurement

The failure mode of social data is believing it. Used well, it tells you where to look; used badly, it tells you what a loud minority thinks.

Volume is not prevalence

Four posts about a bug do not mean four percent of users hit it. They mean four people were annoyed enough to type. Pair it with your own error rates before you escalate.

Journalists and bots crowd the results

For anything newsworthy, the top results are commentary rather than experience. Ask for replies from accounts that look like practitioners, not publishers.

Absence proves nothing

No posts about your bug can mean nobody hit it, or that the people who did are not posting. Silence is not a clean bill of health.

Add it on dsh

Mount it like any other bundle, then keep it out of the way

Unlike the other skills, this one is only useful during a specific kind of session. Project-scoped installation keeps it from showing up in unrelated work.

~/project/.dsh/skills/Project

Loads for this repository only. The right place to read a bundle before you trust it with the whole machine.

~/.agents/skills/User

Loads in every project, and is the same folder other harnesses on this machine look at.

Mount the bundlemkdir -p .dsh/skills cp -r felo-skills/felo-x-search .dsh/skills/
Prove it loadedList the skills you can call from this project.
In practice

The version of this that saves an afternoon

Use it while you are already stuck, not as a monitoring chore.

Type thisCheck X for reports about this version's connection handling. Group them by what the poster actually observed, and mark which ones include a reproduction.What comes back

A grouped picture of the failure that tells you whether you are early, late, or alone — plus a workaround you can try while you wait for a fix.

Type thisFind out whether the maintainers have responded publicly about this issue, and link the thread.What comes back

The status, straight from the thread, instead of a guess from the changelog.

FAQ

What dsh users ask about X data

Can it read replies to a specific post?
Yes, and replies are usually where the useful part is. The original post is the claim; the replies are where people say whether it happened to them.
Does it need my X account?
No. It reads public data through the Felo API, so you are not handing over a personal login and the results do not shift with your own timeline.
How fresh is fresh?
Recent enough for a live incident, on the order of hours. If you need to know what happened in the last ten minutes, you want your own telemetry, not a search.
More on DeepSeek Harness

Every Felo skill for DeepSeek Harness

Five skills written for DeepSeek Harness. They follow the same pattern on this platform, so you can combine them in one session without re-explaining your setup.

Beyond ready-made skills

One API key. A full agent toolkit.

Start with a skill, then compose the exact models, live data, knowledge, and output tools your dsh workflow needs — the same key every Felo skill already uses.

Models

Use cost-efficient LLM access when your agent needs custom reasoning or generation.

  • LLM API
  • Chat completions
  • Model access
Explore LLM API →

Live information

Give agents current web and social signals instead of relying on stale context.

  • Web Search
  • X Search
  • Web Fetch
Explore live data tools →

Knowledge and output

Ground work in reusable knowledge, then turn it into shareable deliverables.

  • LiveDoc
  • PPT generation
  • Mindmaps
Explore knowledge tools →

Creative tools

Extend the workflow from research to visual and office-ready results.

  • Image generation
  • Page tools
  • Office outputs
Explore platform tools →