Weavebench Cua Reproduce
AMAP-ML/LongHorizon-Harness
Reproduce CUA-Harness experiments on WeaveBench from a GitHub checkout.
A skill your agent uses when creating, triaging, or filing GitHub issues — writing bug reports, feature requests, or task tickets; classifying severity; using the gh CLI; or handling edge cases like…
$ npx skills add kid-sid/claude-spellbook --skill github-issues -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install kid-sid/claude-spellbook github-issues --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/kid-sid/claude-spellbook.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/github-issues .claude/skills/github-issues && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "github-issues" agent skill from https://github.com/kid-sid/claude-spellbook/tree/main/skills/github-issues into .claude/skills/github-issues/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "github-issues", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/kid-sid/claude-spellbook/tree/main/skills/github-issuesType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add kid-sid/claude-spellbook --skill github-issues -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install kid-sid/claude-spellbook github-issues --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/kid-sid/claude-spellbook.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/github-issues .agents/skills/github-issues && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "github-issues" agent skill from https://github.com/kid-sid/claude-spellbook/tree/main/skills/github-issues into .agents/skills/github-issues/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "github-issues", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add kid-sid/claude-spellbook --skill github-issues -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install kid-sid/claude-spellbook github-issues --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/kid-sid/claude-spellbook.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/github-issues .cursor/skills/github-issues && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "github-issues" agent skill from https://github.com/kid-sid/claude-spellbook/tree/main/skills/github-issues into .cursor/skills/github-issues/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "github-issues", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/kid-sid/claude-spellbook.git --path skills/github-issues--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add kid-sid/claude-spellbook --skill github-issues -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install kid-sid/claude-spellbook github-issues --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/kid-sid/claude-spellbook.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/github-issues .gemini/skills/github-issues && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "github-issues" agent skill from https://github.com/kid-sid/claude-spellbook/tree/main/skills/github-issues into .gemini/skills/github-issues/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "github-issues", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install kid-sid/claude-spellbook github-issuesInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add kid-sid/claude-spellbook --skill github-issues -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/kid-sid/claude-spellbook.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/github-issues .github/skills/github-issues && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "github-issues" agent skill from https://github.com/kid-sid/claude-spellbook/tree/main/skills/github-issues into .github/skills/github-issues/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "github-issues", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add kid-sid/claude-spellbook --skill github-issues -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install kid-sid/claude-spellbook github-issues --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/kid-sid/claude-spellbook.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/github-issues .opencode/skills/github-issues && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "github-issues" agent skill from https://github.com/kid-sid/claude-spellbook/tree/main/skills/github-issues into .opencode/skills/github-issues/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "github-issues", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
github-issuesA skill your agent uses when creating, triaging, or filing GitHub issues — writing bug reports, feature requests, or task tickets; classifying severity; using the gh CLI; or handling edge cases like…
GitHub Issues is an agent skill from kid-sid/claude-spellbook. Use when creating, triaging, or filing GitHub issues — writing bug reports, feature requests, or task tickets; classifying severity; using the gh CLI; or handling edge cases like regressions, flaky failures, security vulnerabilities, or cross-repo dependencies.
Its SKILL.md is about 3.5k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Testing & QA, covering QA and bug reports. It works with GitHub. The repository describes itself as: A curated collection of skills, prompts, and workflows that extend Claude's capabilities — your personal grimoire for AI-powered development. The licence is MIT.
2 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit a7c2ac9. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Shell commands in SKILL.md call:
ghgitFrom the folder's file list and the shell code blocks in SKILL.md.
Hosts in commands or code, which the agent is likely to contact:
github.comFrom URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
GitHub Issues loads about 3.5k tokens when it runs. Until then it costs about 69 tokens; SKILL.md has 960 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from kid-sid/claude-spellbook at commit a7c2ac9, republished under its MIT licence (© kid-sid). 960 words, ~3,529 tokens.
.claude/skills/github-issues/SKILL.md (or your agent's skills folder).Write issues that are acted on — not ignored, misrouted, or reopened for missing info.
gh CLI to create or manage issues programmatically| Type | Label | Use When | Must Include |
|---|---|---|---|
| Bug | bug | Observed behavior differs from documented or expected | Repro steps, expected vs actual, environment |
| Regression | bug, regression | Previously working behavior broke in a specific version | Commit/PR that introduced it, last-good version |
| Feature | enhancement | New capability that doesn't exist yet | Problem statement, proposed solution, AC |
| Task / Chore | chore | Non-feature engineering work (refactor, migration, upgrade) | Why now, success criteria, estimated scope |
| Performance | performance | Measurable slowdown or resource regression | Benchmark before/after, profiling output |
| Security | (private) | Vulnerability, auth bypass, data exposure | Do NOT file publicly — use private advisory |
| Documentation | documentation | Missing, wrong, or outdated docs | Affected page/file, what's wrong, correct behavior |
| Flaky Test | flaky, ci | Test fails intermittently with no code change | Failure frequency, CI run links, log excerpts |
Severity = impact if it occurs. Priority = urgency to fix.
| High Priority | Low Priority | |
|---|---|---|
| High Severity | P0: fix immediately, page oncall | P1: fix this sprint |
| Low Severity | P2: schedule soon, workaround exists | P3: backlog, good first issue |
P0 triggers: data loss, auth bypass, production down, PII exposure, charge errors.
P1 triggers: feature broken for >1% of users, no workaround, SLA at risk.
Add severity to issue title: [P0], [P1], etc. for anything P1 and above.
# Create issue (interactive)
gh issue create
# Create issue with all fields
gh issue create \
--title "feat: add rate limiting to /api/v1/export" \
--body-file issue-body.md \
--label "enhancement,api" \
--assignee "@me" \
--milestone "v2.1"
# Create from heredoc (no temp file needed)
gh issue create --title "fix: null pointer in PaymentService.charge" --body "$(cat <<'EOF'
## Description
...
EOF
)"
# List, filter, search
gh issue list --label "bug" --state open --assignee "@me"
gh issue list --search "is:open label:regression sort:created-desc"
# View and edit
gh issue view 42
gh issue edit 42 --add-label "priority:high" --remove-label "needs-triage"
# Close with comment
gh issue close 42 --comment "Fixed in #87. Verified in staging."
# Reopen
gh issue reopen 42 --comment "Regression in v2.3 — reopening."
# Pin critical issues
gh issue pin 42
# Create in another repo
gh issue create --repo org/other-repo --title "..." --body "..."
# Bulk label
gh issue list --label "needs-triage" --json number --jq '.[].number' | \
xargs -I{} gh issue edit {} --add-label "bug" --remove-label "needs-triage"## Description
One sentence: what breaks, under what conditions.
## Steps to Reproduce
1. Go to `/settings/billing`
2. Click "Update card"
3. Enter card number `4000 0000 0000 0002` (decline test card)
4. Submit the form
## Expected Behavior
Error toast: "Card declined. Please try a different card."
## Actual Behavior
Spinner runs indefinitely. Network tab shows `POST /api/v1/charges` hanging.
Console: `Uncaught TypeError: Cannot read property 'status' of undefined`
## Environment
- OS: macOS 15.2
- Browser: Chrome 132 / Node 22.3
- App version / commit: v2.4.1 / `a3f9b12`
- Relevant config: `STRIPE_ENV=test`
## Logs / Screenshots
<details>
<summary>Stack trace</summary>
TypeError: Cannot read property 'status' of undefined at handleChargeError (payments.ts:214) ...
</details>
## Workaround
None found. All card submissions are broken in test mode.
## Acceptance Criteria
- [ ] Declined card returns 402 with user-facing error message
- [ ] Spinner stops on error
- [ ] No console errors thrown## Problem
Describe the pain point without prescribing the solution.
"As a team admin, I cannot revoke individual API keys without deleting the entire
integration — so a single compromised key forces us to rotate all integrations."
## Proposed Solution
What you want to happen.
"Add per-key revocation on the API Keys settings page. Revoked keys return 401
immediately; no grace period."
## Alternatives Considered
- Short-lived keys (doesn't solve the emergency revoke case)
- IP allowlisting (different problem)
## Acceptance Criteria
- [ ] Admin can revoke any key independently
- [ ] Revoked key returns 401 within 60 seconds
- [ ] Audit log entry created on revocation
- [ ] Key owner notified by email
## Additional Context
Affects all teams using our Zapier integration (~400 accounts per support data).A regression needs more than a standard bug report:
## Regression Details
- **Last good version:** v2.3.0
- **First bad version:** v2.3.1
- **Introducing commit:** `git bisect` result → `c8d1e4f`
([commit link](https://github.com/org/repo/commit/c8d1e4f))
- **Introducing PR:** #312 — "Refactor payment middleware"
## Bisect Log
```
git bisect start
git bisect bad HEAD
git bisect good v2.3.0
# ... binary search ...
c8d1e4f is the first bad commit
```Always run git bisect before filing a regression — "it worked before" without a
commit is not actionable.
## Failure Rate
~30% of runs over the last 7 days (tracked manually / via CI dashboard).
## CI Run Examples
- Failed: https://github.com/org/repo/actions/runs/12345678
- Failed: https://github.com/org/repo/actions/runs/12345900
- Passed: https://github.com/org/repo/actions/runs/12345800
## Failure Pattern
Fails consistently on: parallel runs, slow CI runners, after `db:reset`.
Never fails locally. Timing-dependent (test passes with `sleep 100ms` injected).
## Log Excerpt (failure)
```
FAIL src/payments/__tests__/charge.test.ts
● PaymentService › charge › handles decline
Expected: "declined"
Received: undefined
at Object.<anonymous> (charge.test.ts:42)
```
## Suspected Cause
Async setup in `beforeEach` not awaited before first assertion.# WRONG — never do this
gh issue create --title "SQL injection in /api/v1/search"
# CORRECT — use GitHub's private security advisory
gh api repos/org/repo/security-advisories \
--method POST \
--field summary="SQL injection in search endpoint" \
--field description="..." \
--field severity="high"
# Or via UI: repo → Security tab → Advisories → New advisorySecurity issues must stay private until a patch is released and deployed. Coordinated disclosure: notify maintainer → agree on fix timeline → publish advisory.
## Benchmark: Before (v2.3.0)GET /api/v1/reports/monthly p50=120ms p95=340ms p99=890ms (k6: 50 VUs, 5 min, 1000 req/min)
## Benchmark: After (v2.4.0)GET /api/v1/reports/monthly p50=1200ms p95=4100ms p99=timeout
## Profiling Output
Attached: `profile-v2.4.0.png`
Hotspot: `ReportAggregator.groupBy()` — 83% of CPU time.
Introduced by #318 (full-table scan, missing index on `reports.created_at`).
## Acceptance Criteria
- [ ] p95 ≤ 400ms under same load profile
- [ ] No full-table scans (verified via EXPLAIN ANALYZE)# In an issue body — creates a tracked reference
Depends on #42
Blocks #55
Related to #67
Part of #80 (epic)
# In a PR body — auto-closes the issue when PR merges to default branch
Fixes #42
Closes #42
Resolves #42
# Cross-repo
Fixes org/other-repo#42
# In commit message (also closes on merge)
git commit -m "fix: handle declined cards in test mode
Closes #42"Use Fixes only in the PR/commit that resolves the issue — not in the issue itself.
# Search before creating
gh issue list --search "payment decline spinner" --state all
gh issue list --search "card test mode broken" --state all
# Check closed issues too (may have a workaround)
gh issue list --search "charge 402" --state closedIf a duplicate exists:
| Label | Meaning |
|---|---|
bug | Confirmed behavior defect |
regression | Was working, now broken |
enhancement | New capability |
chore | Maintenance, no user-visible change |
documentation | Docs only |
performance | Measurable slowdown |
flaky | Intermittent test failure |
security | Vulnerability (use sparingly on public repos) |
good first issue | Isolated, well-scoped, beginner-friendly |
needs-triage | Filed but not yet classified |
needs-repro | Cannot reproduce without more info |
wontfix | Intentional behavior or out of scope |
blocked | Waiting on another issue or external dependency |
breaking-change | Fix or feature changes existing behavior |
Create a tracking issue in the primary repo:
## Scope
- [ ] org/frontend#— (UI changes)
- [ ] org/backend#— (API changes)
- [ ] org/infra#— (database migration)
This issue tracks overall completion. Sub-issues are self-contained.File sub-issues in each repo, link back to the tracker.
A fix that itself breaks existing behavior needs two issues:
breaking-change issue documenting the behavior change, migration path, and which major version it ships inAdd needs-repro label and comment:
Thanks for the report. To investigate, we need:
- Exact app version (run `app --version`)
- Browser console output when the error occurs
- Whether this reproduces in an incognito window
Will keep open for 14 days awaiting info.Always P0. Beyond the standard bug template:
Close with:
This looks like a configuration question rather than a bug.
Please open a support ticket at support.example.com or ask in #help on Discord.
Closing to keep the issue tracker focused on confirmed defects.## Platform
- Fails on: Windows 11 (PowerShell 5.1, path separator `\`)
- Passes on: macOS 15, Ubuntu 22.04
## Root Cause Hypothesis
Path concatenation uses hardcoded `/` — breaks on Windows.
Candidate line: `config.ts:88`git bisect and identify the introducing commit before filing--state all before filing- [ ] items so progress is visible--state all) before filing to detect duplicatesgit bisect- [ ] checkboxesBlocks, Depends on, Related to)See also:
development-workflow(branch naming, commit conventions, PR process) See also:ci-cd(flaky test triage in GitHub Actions, workflow run links)
© kid-sid, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in skills/github-issues of kid-sid/claude-spellbook.
Open the folder on GitHubat commit a7c2ac9
GitHub Issues next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| GitHub Issues this skillkid-sid/claude-spellbook | 189 | — | ~3.5k | Automated safety check: Pass | MIT | |
| Weavebench Cua ReproduceAMAP-ML/LongHorizon-Harness | 1.7k | — | ~1.6k | Automated safety check: Pass | MIT | |
| Evidence-Driven Testingmichaelshimeles/skills | 1.3k | 1 repos | ~3.9k | Automated safety check: Pass | None | |
| Create GitHub IssueNVIDIA/OpenShell | 15k | — | ~1.7k | Automated safety check: Pass | Apache-2.0 | |
| Triage IssuesClickHouse/clickhouse-java | 1.6k | — | ~904 | Automated safety check: Pass | Apache-2.0 | |
| Gentle AI Issue CreationGentleman-Programming/gentle-shell | 1.2k | — | ~2.5k | Automated safety check: Pass | Apache-2.0 |
AMAP-ML/LongHorizon-Harness
Reproduce CUA-Harness experiments on WeaveBench from a GitHub checkout.
michaelshimeles/skills
Records an annotated screen recording of the agent testing an app hands-on, then posts the video and a results summary to the PR and tracker issue.
NVIDIA/OpenShell
Create GitHub issues using the gh CLI. An agent skill from NVIDIA/OpenShell.
ClickHouse/clickhouse-java
Analyzes a single GitHub issue at a time. An agent skill from ClickHouse/clickhouse-java.
Gentleman-Programming/gentle-shell
Create and triage GitHub issues from repository evidence. An agent skill from Gentleman-Programming/gentle-shell.
termio-sh/termio
Diagnose a termio hang, beachball, crash, or 'it froze again' from the evidence macOS and termio actually leave behind — live process samples, crash and CPU-burn reports, the unified log, the…
kid-sid/claude-spellbook
A skill your agent uses when building or reviewing UI components for keyboard and screen reader compatibility, adding ARIA to custom widgets, auditing a page for WCAG AA conformance, or preparing…
kid-sid/claude-spellbook
A skill your agent uses when building, wiring, or debugging an Agentex agent — choosing agent type, configuring acp.py and manifest.yaml, using adk.messages or adk.state, or resolving…
kid-sid/claude-spellbook
A skill your agent uses when building production LLM applications — designing RAG pipelines, choosing vector databases, implementing agent orchestration, optimizing cost, or adding AI safety…
kid-sid/claude-spellbook
A skill your agent uses when building or refactoring Angular applications — choosing between signals, RxJS, and NgRx for state, configuring routing with guards and lazy loading, optimizing change…
kid-sid/claude-spellbook
A skill your agent uses when designing new REST endpoints, reviewing an existing API contract, adding pagination or filtering, planning a versioning strategy, or building a public or partner-facing…
kid-sid/claude-spellbook
A skill your agent uses when implementing login flows, issuing or validating JWTs, setting up OAuth2/OIDC with a provider, designing role-based or attribute-based access control, securing API…
Works with
Categories
A skill your agent uses when creating, triaging, or filing GitHub issues — writing bug reports, feature requests, or task tickets; classifying severity; using the gh CLI; or handling edge cases like…. GitHub Issues is an agent skill from kid-sid/claude-spellbook. Use when creating, triaging, or filing GitHub issues — writing bug reports, feature requests, or task tickets; classifying severity; using the gh CLI; or handling edge cases like regressions, flaky failures, security vulnerabilities, or cross-repo dependencies.
GitHub Issues fits situations like: filing GitHub issues — writing bug reports; feature requests; classifying severity; using the gh CLI.
Run `npx skills add kid-sid/claude-spellbook --skill github-issues -a claude-code`. Or copy the skill folder (skills/github-issues in kid-sid/claude-spellbook) into .claude/skills/github-issues in your project. Claude Code loads it when a task matches its description.
Run `npx skills add kid-sid/claude-spellbook --skill github-issues -a codex`. Or copy the skill folder (skills/github-issues in kid-sid/claude-spellbook) into .agents/skills/github-issues in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add kid-sid/claude-spellbook --skill github-issues -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/github-issues, .gemini/skills/github-issues, .github/skills/github-issues and .opencode/skills/github-issues in your project.
Going by SKILL.md and its folder, GitHub Issues needs the command-line tools its instructions call (gh and git).
SKILL.md names 1 domain. In commands or code: github.com; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
GitHub Issues is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 3.5k tokens (SKILL.md is roughly 14k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with GitHub Issues: Weavebench Cua Reproduce (AMAP-ML/LongHorizon-Harness, 1.7k stars), Evidence-Driven Testing (michaelshimeles/skills, 1.3k stars), Create GitHub Issue (NVIDIA/OpenShell, 15k stars) and Triage Issues (ClickHouse/clickhouse-java, 1.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
kid-sid (a GitHub user) maintains it in kid-sid/claude-spellbook, which has 189 GitHub stars. The repository holds 54 skills in this directory. The repository was last updated on August 5, 2026.
Source: kid-sid/claude-spellbook on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.