What does this skill do, and when should you use it?
Golden Chat Slack Finder is a focused skill for navigating an exported Slack chat dataset located at `fixtures/slack-export/`. It covers 6 messages, 3 users, two channels—#engineering and #random—and three organized sections. It is useful for locating past solutions, architectural discussions, troubleshooting steps, code examples, and shared resources. Its scope is limited to the golden_chat dataset and should not be confused with the capabilities of sibling skills in the Skill Seekers repository.
Reads Slack export content from fixtures/slack-export/; helps locate historical discussions, team decisions, troubleshooting steps, code snippets, and shared links; and uses references/index.md, references/engineering_s1-s2.md, and references/random_s3-s3.md to navigate the chat structure. The documented dataset contains 6 messages, 1 thread, 3 code snippets, 21 shared links, 3 users, and 2 channels.
- An engineer needs to find a solution previously discussed in #engineering.
- A developer wants to retrieve Python or shell snippets shared by teammates.
- A technical lead needs to review an earlier architectural discussion or decision.
- A support engineer wants to locate troubleshooting steps from past conversations.
- A team member needs to find links and resources previously shared in chat.
How do you install this skill?
- This path appears to be a generated test artifact rather than the repository's advertised conversion skill; do not infer documentation, GitHub, or PDF conversion capability from it.
- The long_helper snippet is truncated and the shared links use example.com; reference content and quality ratings should be manually checked before use.
- The files contain Slack usernames, chat content, and links; real exports require authorization, privacy review, and sensitive-information redaction before use.
- Local filesystem
The README documents installation for the complete Skill Seekers collection with pip install skill-seekers. This SKILL.md does not document how to install golden-chat as a standalone skill or where to place its folder in an Agent's skill directory.
tmp="$(mktemp -d)"
git clone --depth 1 https://github.com/yusufkaraaslan/Skill_Seekers.git "$tmp"
mkdir -p ~/.claude/skills
cp -R "$tmp/tests/golden/phase2/chat" ~/.claude/skills/
rm -rf "$tmp"Generated from the source repository and skill path; it copies only this skill's folder. If the author's install steps above differ, follow those first. To scope it to one project, replace ~/.claude/skills with that project's .claude/skills.
How do you use this skill?
Once installed, send your agent any of these to trigger it:
- Find troubleshooting discussions in golden_chat,
- Show the Python snippets shared by the team,
- Summarize architecture decisions from #engineering.
With the skill loaded, ask requests such as “Find troubleshooting discussions in golden_chat,” “Show the Python snippets shared by the team,” or “Summarize architecture decisions from #engineering.” The Agent must be able to access the Slack export and the referenced files.
What are this skill's strengths and limitations?
- Clearly scoped to one Slack export dataset.
- Includes channel, section, statistics, and reference-file navigation.
- Targets practical retrieval tasks including troubleshooting, setup, code snippets, decisions, and shared links.
- Uses only standard `name` and `description` frontmatter and shows no platform-specific extensions.
- The documented dataset is very small: 6 messages, 3 users, and 2 channels.
- It is based on fixed golden_chat fixtures rather than a live Slack workspace connection.
- Standalone installation, permissions, and update procedures are not documented.
- One code example is truncated, and most listed links use example URLs.
How does this skill compare with similar options?
Side by side with related skills; every score comes from the same FSRS standard.
| Skill | FS score | Stars | Last updated | License |
|---|---|---|---|---|
| Golden Chat Slack Finder this page | 27 · Not recommended | ★ 15k | 25d ago | MIT |
| Slack Team Chat Retrieval Skill | 21 · Not recommended | ★ 15k | 25d ago | MIT |
| Empty Slack Chat Skill | 28 · Not recommended | ★ 15k | 25d ago | MIT |
| i-have-adhd: ADHD-Friendly Output Mode | 65 · Recommended | ★ 57k | 14d ago | MIT |
| Project Memory Manager | 59 · Recommended | ★ 3k | 11d ago | Apache-2.0 |
How did FollowSkills review this skill?
The skill only references local Slack exports and reference files; no command execution, credential requests, or covert exfiltration are shown, earning a baseline score. However, shared links are unverified, and there is no sensitive-data handling, user confirmation, permission scoping, data-flow disclosure, or recovery guidance, so points are deducted.
The navigation among SKILL.md, the index, and reference files is broadly coherent and statically traceable. Reliability is reduced because the long code snippet is truncated in SKILL.md and there is no reproducible procedure or abnormal-input feedback.
The intended scenario is clear: testing the golden_chat Slack build, with lookup use cases for decisions, code, troubleshooting, and links. The path does not match the repository-level description of converting documentation, GitHub repositories, and PDFs into Claude skills; non-fit boundaries, trigger precision, and Chinese-language guidance are also missing.
The document has headings, statistics, topic summaries, and reference navigation; repository context supplies an MIT license, version metadata, and maintenance links. The selected skill itself lacks installation/dependency notes, changelog, FAQs, explicit limitations, and clear maintenance responsibility, and its generated content is truncated.
It may support limited lookup over a small Slack-history fixture. However, this path is not the advertised conversion tool, defines no operational input-to-output workflow, uses test-fixture content and example.com links, and contains incomplete snippets, so directly usable value is limited.
The skill has limited cross-corroboration across the engineering, random, and index files for message counts, channels, and reference paths. No execution was performed; quality ratings and link validity are unverified, and there is no third-party execution evidence, so the score remains low.
Open a dimension to read why it scored that way
Evidence confidence：Low — Mostly static review, author material or a limited demo; useful for discovery, not high-risk decisions.
See the full review method →