New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Ghcrawl Cluster Operator

by vincentkoc in vincentkoc/dotskills

A skill your agent uses when inspecting a ghcrawl SQLite store, pulling GitHub issue/PR data, refreshing summaries, embeddings, and clusters, or extracting one cluster and its evidence through the…

MITAuto-check passedAI & LLM Engineering

Install Ghcrawl Cluster Operator

skills CLI
$ npx skills add vincentkoc/dotskills --skill ghcrawl-cluster-operator -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install vincentkoc/dotskills ghcrawl-cluster-operator --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/vincentkoc/dotskills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/ghcrawl-cluster-operator .claude/skills/ghcrawl-cluster-operator && rm -rf skills-src

Use ~/.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/

Facts

Skill name
ghcrawl-cluster-operator
GitHub stars
107
Token cost
~1.7k tokens
SKILL.md length
519 words
Files
3 (incl. assets)
Skills in repo
19
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when inspecting a ghcrawl SQLite store, pulling GitHub issue/PR data, refreshing summaries, embeddings, and clusters, or extracting one cluster and its evidence through the…

  • Works in 8 steps: Start with read-only checks: doctor,… → Confirm the target repo as owner/repo… → Use sync or refresh only when fresh… → …
  • Inspecting a ghcrawl SQLite store
  • SKILL.md covers Purpose, When to use, Workflow and Inputs, plus 7 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Ghcrawl Cluster Operator is an agent skill from vincentkoc/dotskills. Use when inspecting a ghcrawl SQLite store, pulling GitHub issue/PR data, refreshing summaries, embeddings, and clusters, or extracting one cluster and its evidence through the ghcrawl CLI.

Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including assets (for example `agents/openai.yaml`).

It sits in AI & LLM Engineering, covering Embeddings. It works with GitHub and SQLite. The repository describes itself as: 🐙 A curated set of Codex and OpenClaw skills for workflow automation, technical debugging, and agent-assisted development patterns. The licence is MIT.

When your agent uses it

  • Inspecting a ghcrawl SQLite store
  • Pulling GitHub issue/PR data
  • Refreshing summaries
  • Extracting one cluster and its evidence through the ghcrawl CLI

Example prompts

  • “/ghcrawl-cluster-operator”

Workflow steps

8 steps, taken from the first numbered list in SKILL.md.

  1. Start with read-only checks: doctor, configure, runs, clusters, cluster-explain, and threads.
  2. Confirm the target repo as owner/repo and prefer --json for agent-readable output.
  3. Use sync or refresh only when fresh GitHub data is needed.
  4. Use --include-code only when file overlap matters; it hydrates PR file metadata and can increase DB size.
  5. Run structured key summaries before embedding when LLM summaries should influence vectors.
  6. Run embed, then cluster, after summary or configuration changes.
  7. Pull one cluster with cluster-explain before making durable maintainer edits.
  8. After durable edits, rerun cluster and explain the affected cluster to verify the decision stuck.

What it can do on your machine

Read from SKILL.md and the folder at commit b83ca13. It shows what the files ask for, not the result of running them.

  • Tool permissions

    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.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are bash and mermaid).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Ghcrawl Cluster Operator loads about 1.7k tokens when it runs. Until then it costs about 54 tokens; SKILL.md has 519 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~54
When it runs · the whole SKILL.md, loaded when a task matches
~1.7k

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.

Safety

Auto-check passed

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.

SKILL.md

The full file from vincentkoc/dotskills at commit b83ca13, republished under its MIT licence (© vincentkoc). 519 words, ~1,741 tokens.

Download SKILL.mdSave it as .claude/skills/ghcrawl-cluster-operator/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
ghcrawl-cluster-operator
description
Use when inspecting a ghcrawl SQLite store, pulling GitHub issue/PR data, refreshing summaries, embeddings, and clusters, or extracting one cluster and its evidence through the ghcrawl CLI.
license
MIT
metadata.source
https://github.com/vincentkoc/dotskills

ghcrawl Cluster Operator

Purpose

Operate ghcrawl as a local-first GitHub issue and pull request crawler: inspect the SQLite store, pull GitHub data, refresh summaries and embeddings, build clusters, and extract cluster evidence through deterministic CLI commands.

The default stance is conservative and cost-aware. Inspect first, then run mutating or API-spend commands only when the operator asked for fresh data or enrichment.

When to use

  • Inspecting ghcrawl repository state, local runs, thread counts, clusters, or durable cluster decisions.
  • Pulling GitHub issue/PR data into a local ghcrawl store.
  • Running OpenAI-backed summaries, structured key summaries, embeddings, and clustering.
  • Explaining a cluster with members, events, canonical selections, exclusions, and local evidence.
  • Operating maintainer edits such as excluding a member from a durable cluster or setting a canonical item.

Workflow

  1. Start with read-only checks: doctor, configure, runs, clusters, cluster-explain, and threads.
  2. Confirm the target repo as owner/repo and prefer --json for agent-readable output.
  3. Use sync or refresh only when fresh GitHub data is needed.
  4. Use --include-code only when file overlap matters; it hydrates PR file metadata and can increase DB size.
  5. Run structured key summaries before embedding when LLM summaries should influence vectors.
  6. Run embed, then cluster, after summary or configuration changes.
  7. Pull one cluster with cluster-explain before making durable maintainer edits.
  8. After durable edits, rerun cluster and explain the affected cluster to verify the decision stuck.

Inputs

  • repo (required): GitHub repository in owner/repo format.
  • db_path (optional): explicit SQLite database path when not using the configured default.
  • cluster_id (optional): durable or run cluster identifier to explain or edit.
  • thread_numbers (optional): comma-separated GitHub issue/PR numbers to inspect.
  • include_code (optional): whether PR file metadata should be hydrated and used as clustering evidence.
  • summary_model (optional): LLM model for structured summaries, usually gpt-5.4.
  • embedding_basis (optional): vector source such as title_original or llm_key_summary.
  • limit (optional): item cap for sync, summaries, or listing commands.
Show full SKILL.md (208 more words)Show less

Outputs

  • Local health and configuration status.
  • Run history and current cluster counts.
  • Cluster lists with size, names, titles, states, and member evidence.
  • Cluster explain output with members, events, exclusions, canonical picks, summaries, and top touched files when available.
  • Thread snapshots for selected issue/PR numbers.
  • Verification notes after refresh, embedding, clustering, or durable maintainer actions.

Ground Rules

  • Prefer read-only inspection commands first: doctor, runs, clusters, cluster-explain, threads.
  • Treat refresh, sync, summarize, key-summaries, and embed as remote/API-spend commands.
  • cluster is local-only but can be CPU-heavy on huge repos.
  • Always pass --json for agent-readable output unless opening the TUI.
  • Use --include-code only when file overlap matters.

Setup Check

bash
ghcrawl doctor --json
ghcrawl configure --json
ghcrawl runs owner/repo --limit 10 --json

If the local store is empty or stale, pull current open GitHub data:

bash
ghcrawl sync owner/repo --limit 200 --json
ghcrawl sync owner/repo --include-code --limit 200 --json

For a normal end-to-end update:

bash
ghcrawl refresh owner/repo --json

Use code hydration when file evidence should affect clustering:

bash
ghcrawl refresh owner/repo --include-code --json

LLM And Embedding Pipeline

Default clustering can run without LLM summaries. LLM summaries and embeddings enrich the cluster graph.

Useful configurations:

bash
ghcrawl configure --summary-model gpt-5.4 --embedding-basis title_original --json
ghcrawl configure --summary-model gpt-5.4 --embedding-basis llm_key_summary --json

For structured key summaries:

bash
ghcrawl key-summaries owner/repo --limit 200 --json
ghcrawl key-summaries owner/repo --number 12345 --json

Then refresh vectors and clusters:

bash
ghcrawl embed owner/repo --json
ghcrawl cluster owner/repo --json

Pull A Cluster And Its Info

List clusters:

bash
ghcrawl clusters owner/repo --min-size 2 --limit 20 --sort size --json
ghcrawl clusters owner/repo --search "cron timeout" --limit 10 --json

Explain one durable cluster:

bash
ghcrawl cluster-explain owner/repo --id 123 --member-limit 50 --event-limit 50 --json

Inspect current durable clusters with members:

bash
ghcrawl durable-clusters owner/repo --member-limit 25 --json
ghcrawl durable-clusters owner/repo --include-inactive --member-limit 25 --json

Pull specific issues/PRs from the local store:

bash
ghcrawl threads owner/repo --numbers 123,456,789 --json

Open the TUI:

bash
ghcrawl tui owner/repo

Local Maintainer Actions

Use these only when the operator asks for durable cluster edits:

bash
ghcrawl exclude-cluster-member owner/repo --id 123 --number 456 --reason "not same root cause" --json
ghcrawl include-cluster-member owner/repo --id 123 --number 456 --reason "same root cause" --json
ghcrawl set-cluster-canonical owner/repo --id 123 --number 456 --reason "clearest report" --json
ghcrawl merge-clusters owner/repo --source 123 --target 456 --reason "same issue family" --json

After edits, re-run:

bash
ghcrawl cluster owner/repo --json
ghcrawl cluster-explain owner/repo --id 123 --member-limit 50 --event-limit 50 --json

Flow

mermaid
stateDiagram-v2
    [*] --> InspectStore
    InspectStore --> ReportEvidence: inspection only
    InspectStore --> RefreshData: fresh data requested
    InspectStore --> Enrich: enrichment requested
    RefreshData --> ReportEvidence: refresh complete
    Enrich --> SummarizeThenEmbed: summaries affect vectors
    Enrich --> Embed: existing text basis
    SummarizeThenEmbed --> Cluster
    Embed --> Cluster
    InspectStore --> ExplainCluster: durable edit requested
    ExplainCluster --> ApplyNamedEdit
    ApplyNamedEdit --> Cluster
    Cluster --> ExplainResult
    ExplainResult --> ReportEvidence
    RefreshData --> ReportFailure: request fails
    Enrich --> ReportFailure: request fails
    SummarizeThenEmbed --> ReportFailure: enrichment fails
    Embed --> ReportFailure: embedding fails
    Cluster --> ReportFailure: clustering fails
    ApplyNamedEdit --> ReportFailure: edit fails
    ReportEvidence --> [*]
    ReportFailure --> [*]

© vincentkoc, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (assets) in skills/ghcrawl-cluster-operator of vincentkoc/dotskills.

  • SKILL.md
  • agents/openai.yaml
  • assets/icon.jpg

Open the folder on GitHubat commit b83ca13

Compare with similar skills

Ghcrawl Cluster Operator 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.

Ghcrawl Cluster Operator compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Ghcrawl Cluster Operator this skillvincentkoc/dotskills107—~1.7kAutomated safety check: PassMIT
Embeddings via 9Routerdecolua/9router30k—~604Automated safety check: PassMIT
Esmfold2JimLiu/science-skills2274 repos~2.5kAutomated safety check: PassApache-2.0
PR Demomikeyobrien/ralph-orchestrator3.2k—~1.3kAutomated safety check: PassMIT
Yas Demo Texttmck-code/yet-another-statusline242—~649Automated safety check: PassBSD-3-Clause
Michel CLI Demo RecorderPackmindHub/packmind317—~3.4kAutomated safety check: PassApache-2.0

Similar skills

  • Embeddings via 9Router

    decolua/9router

    Generates vector embeddings through the 9Router /v1/embeddings endpoint, using models from providers such as OpenAI, Gemini, Mistral and Voyage for RAG and semantic search.

    30k GitHub stars~604 tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed

  • Esmfold2

    JimLiu/science-skills

    Biohub ESMFold2 / ESMFold2-Fast all-atom co-folding (Candido et al.

    227 GitHub starsUsed in 4 repos~2.5k tokens
    AI & LLM EngineeringAuto-check passed

  • PR Demo

    mikeyobrien/ralph-orchestrator

    A skill your agent uses when creating animated demos (GIFs) for pull requests or documentation.

    3.2k GitHub stars~1.3k tokensUpdated 4 days ago
    AI & LLM EngineeringAuto-check passed

  • Yas Demo Text

    tmck-code/yet-another-statusline

    Convert make demo/img statusline snapshots into ANSI-stripped plain text for diffing and PR embedding.

    242 GitHub stars~649 tokensUpdated 5 days ago
    AI & LLM EngineeringAuto-check passed

  • Michel CLI Demo Recorder

    PackmindHub/packmind

    Produce proof-of-execution demos of the Packmind CLI (packmind-cli) as terminal-styled images (colors and formatting preserved exactly), for embedding in a GitHub PR.

    317 GitHub stars~3.4k tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed

  • Open Second Brain Embeddings Setup

    itechmeat/open-second-brain

    Walks through turning on semantic search in Open Second Brain: embedding key, sqlite-vec extension, first reindex and an optional periodic refresh, starting from o2b search check.

    442 GitHub stars~2.6k tokensUpdated yesterday
    AI & LLM EngineeringAuto-check: warnings

More from vincentkoc/dotskills

All 19 skills in this repo

  • Openclaw PR Batch Sweep

    vincentkoc/dotskills

    Select, review, repair, validate, and land batches of up to 20 low-risk OpenClaw contributor pull requests using Vincent's maintainer preferences and bounded sub-agent lanes.

    107 GitHub stars~4.1k tokensUpdated yesterday
    Auto-check passed

  • Tmux Agent Lane Orchestrator

    vincentkoc/dotskills

    Monitor and coordinate one tmux agent lane, reconstruct worker state from panes and recent Codex logs, classify progress and blockers, and produce concise manager summaries.

    107 GitHub stars~967 tokensUpdated yesterday
    Auto-check passed

  • Codebase Memory MCP

    vincentkoc/dotskills

    Resolve canonical Git checkouts, index and verify codebase-memory-mcp graphs through the guarded CLI, and safely audit duplicate worktree caches.

    107 GitHub stars~3k tokensUpdated yesterday
    Auto-check passed

  • Org Branch Cleanup

    vincentkoc/dotskills

    Audit and safely prune stale branches across a GitHub organization with immutable snapshots, conservative merged-PR classification, live SHA/protection/open-PR revalidation, resumable deletion…

    107 GitHub stars~1.5k tokensUpdated yesterday
    Auto-check passed

  • Session Done

    vincentkoc/dotskills

    Prepare a concise session handoff when the user asks to wrap up, capture continuation context, or use /done.

    107 GitHub stars~833 tokensUpdated yesterday
    Auto-check passed

  • Codex Goal Mining

    vincentkoc/dotskills

    Mine structured Codex /goal history locally or across a configured machine fleet, measure active goal time and resumed thread spans, identify unfinished and recurring semantic runs, and turn them…

    107 GitHub stars~1.2k tokensUpdated yesterday
    Auto-check passed

Works with

Categories

Questions about Ghcrawl Cluster Operator

What does Ghcrawl Cluster Operator do?

A skill your agent uses when inspecting a ghcrawl SQLite store, pulling GitHub issue/PR data, refreshing summaries, embeddings, and clusters, or extracting one cluster and its evidence through the…. Ghcrawl Cluster Operator is an agent skill from vincentkoc/dotskills. Use when inspecting a ghcrawl SQLite store, pulling GitHub issue/PR data, refreshing summaries, embeddings, and clusters, or extracting one cluster and its evidence through the ghcrawl CLI.

When should I use Ghcrawl Cluster Operator?

Ghcrawl Cluster Operator fits situations like: inspecting a ghcrawl SQLite store; pulling GitHub issue/PR data; refreshing summaries; extracting one cluster and its evidence through the ghcrawl CLI.

How do I install Ghcrawl Cluster Operator in Claude Code?

Run `npx skills add vincentkoc/dotskills --skill ghcrawl-cluster-operator -a claude-code`. Or copy the skill folder (skills/ghcrawl-cluster-operator in vincentkoc/dotskills) into .claude/skills/ghcrawl-cluster-operator in your project. Claude Code loads it when a task matches its description.

How do I install Ghcrawl Cluster Operator in Codex?

Run `npx skills add vincentkoc/dotskills --skill ghcrawl-cluster-operator -a codex`. Or copy the skill folder (skills/ghcrawl-cluster-operator in vincentkoc/dotskills) into .agents/skills/ghcrawl-cluster-operator in your project. Codex loads it when a task matches its description.

Can I use Ghcrawl Cluster Operator in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add vincentkoc/dotskills --skill ghcrawl-cluster-operator -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ghcrawl-cluster-operator, .gemini/skills/ghcrawl-cluster-operator, .github/skills/ghcrawl-cluster-operator and .opencode/skills/ghcrawl-cluster-operator in your project.

What does Ghcrawl Cluster Operator need to run?

SKILL.md names no scripts, command-line tools or credentials: Ghcrawl Cluster Operator is instructions for the agent only.

Does Ghcrawl Cluster Operator access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Ghcrawl Cluster Operator safe to install?

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.

What licence does Ghcrawl Cluster Operator use?

Ghcrawl Cluster Operator is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Ghcrawl Cluster Operator use?

About 1.7k tokens (SKILL.md is roughly 7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Ghcrawl Cluster Operator?

Skills that share tags, products or a category with Ghcrawl Cluster Operator: Embeddings via 9Router (decolua/9router, 30k stars), Esmfold2 (JimLiu/science-skills, 227 stars), PR Demo (mikeyobrien/ralph-orchestrator, 3.2k stars) and Yas Demo Text (tmck-code/yet-another-statusline, 242 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Ghcrawl Cluster Operator?

vincentkoc (a GitHub user) maintains it in vincentkoc/dotskills, which has 107 GitHub stars. The repository holds 19 skills in this directory. The repository was last updated on October 8, 2026.

Source: vincentkoc/dotskills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.