discover-history
Search archived tickets by keywords to find related historical context.
npx skills add majiayu000/claude-skill-registry --skill discover-history --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Discover History Search archived tickets to find related past work. ## Instructions Run the bundled script with keywords extracted from the ticket request: ```bash bash .claude/skills/discover-history/sh/search.sh <keyword1> [keyword2] ... ``` ### Keyword Extraction Extract 3-5 keywords from: - Key file paths (e.g., `ticket.md`, `drive.md`) - Domain terms (e.g., `branch`, `commit`, `archive`) - Layer names (e.g., `Config`, `UX`) ### Output Format The script returns matches sorted by relevance (match count): ``` 5 .workaholic/tickets/archive/feat-xxx/ticket-a.md 3 .workaholic/tickets/archive/feat-yyy/ticket-b.md ``` ### Interpreting Results - Higher count = more keyword matches = more relevant - Read top 5 tickets to understand context - Extract: title, overview, key files, layer
- Instructions
- Keyword Extraction
- Output Format
- Interpreting Results
bash .claude/skills/discover-history/sh/search.sh <keyword1> [keyword2] ...
What does the discover-history skill do?
Search archived tickets by keywords to find related historical context.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill discover-history --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.