$ loading_
Find duplicate PRs and issues, group them, and sync duplicate status.
The skill itself appears to be an open-source, prompt-only documentation-style skill with a small direct attack surface. However, the README explicitly instructs installing external CLIs, logging in via GitHub OAuth, and performing GitHub reads/writes, which does not fully align with the declared “no keys / no remote endpoints” metadata and warrants caution around the companion toolchain.
The header declares 'no keys', but the README requires `prtags auth login` via GitHub OAuth device flow using the maintainer's account, and may also rely on an authenticated `gh` session. The skill itself does not directly collect credentials, but following the instructions would involve a privileged GitHub identity for writing tags/annotations, so credential use and permission scope should be verified.
No remote endpoints are declared, yet the README explicitly depends on live GitHub/`gh api`, fetches an install script from `raw.githubusercontent.com`, and indicates that `prtags` interacts with its own backend/mirror state. The skill itself is prompt-only and has no built-in egress, but its recommended workflow sends repository/issue data to GitHub and related companion services.
As a prompt-only artifact, the skill itself does not directly execute code. However, the README recommends running `curl ... | bash` to install the external `prtags` CLI and invoking local `gh`/`gitcrawl`/`prtags` commands. This is a standard companion-tool execution surface, and the remote script pipe-to-shell pattern should be independently reviewed for safety and integrity.
The skill itself does not declare access to local files or system resources. However, the workflow uses `gitcrawl` for local discovery and `gh`/`prtags` to read and write target PRs/issues, implying that companion tools may access local repository data and modify labels, groups, or annotations on GitHub. For this skill itself, those accesses are not built-in but are introduced by the documented companion permissions.
Positive signals include an open-source GitHub origin and very strong community trust. However, the license is undeclared, maintenance status is unknown, and the README depends on another external repository (`dutifuldev/prtags`) for the latest release and installation script. Because the skill metadata and README differ on dependency/login/network expectations, the supply chain should be reviewed as 'main repo + external CLI + install script' rather than relying solely on the main repository's high star count.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "tag-duplicate-prs-issues" skill from askskill: 1. Download https://raw.githubusercontent.com/openclaw/openclaw/main/.agents/skills/tag-duplicate-prs-issues/SKILL.md 2. Save it as ~/.claude/skills/tag-duplicate-prs-issues/SKILL.md 3. Reload skills and tell me it's ready
Use gitcrawl to search the OpenClaw repository for duplicate issues related to "login timeout", group related items into prtags, recommend the canonical issue to keep, and sync duplicate status back to GitHub.
A grouped list of duplicate issues, recommended canonical issues, and the duplicate status synced to GitHub.
Scan OpenClaw for PRs with overlapping implementations, identify duplicate changes, write thematic groupings into prtags, sync duplicate PR labels to GitHub, and include handling recommendations.
Clustered duplicate PR groups, relationship notes for each group, and the synchronization results on GitHub.
Review PRs and issues from the last 30 days in OpenClaw for duplicates, generate prtags groupings, highlight high-risk duplicate work, and sync all duplicate states to GitHub.
A duplicate-work review for the last 30 days, including grouped tags, high-risk items, and a sync status summary.
Use this skill when a maintainer needs to decide whether a pull request or issue is a duplicate of existing work.
This skill is for maintainer triage and grouping. It is not for reviewing the implementation quality of a PR.
Do not write duplicate groups or annotations until this setup is complete.
Read-only discovery can still proceed with gitcrawl and live gh.
Use $gitcrawl first for local candidate discovery.
Use the prtags skill from the prtags repo at skills/prtags/SKILL.md when it is available.
Install prtags from its latest GitHub release.
Do not rely on an old local build unless the maintainer explicitly wants to test unreleased behavior.
prtags CLI install path:
curl -fsSL https://raw.githubusercontent.com/dutifuldev/prtags/main/scripts/install-prtags.sh | bash -s -- --bin-dir "$HOME/.local/bin"
prtags should be logged in with the maintainer's own GitHub account through OAuth device flow.
Do not use a shared maintainer token for interactive triage.
prtags auth login
prtags auth status
The expected outcome is that prtags stores the logged-in maintainer identity locally and uses that account for authenticated writes.
Do not require an up-front preflight before starting the workflow. Proceed with the normal steps until you actually need a tool or account state.
As soon as you discover that prtags is missing or not logged in at the write step, stop immediately.
Do not continue in a partial write mode after that point.
If prtags is missing, ask the user to run:
curl -fsSL https://raw.githubusercontent.com/dutifuldev/prtags/main/scripts/install-prtags.sh | bash -s -- --bin-dir "$HOME/.local/bin"
If prtags auth status shows that the user is not logged in, ask the user to run:
prtags auth login
Resume only after the missing tool or login state has been fixed.
For candidate discovery in this workflow, use gitcrawl first.
Treat it as the local history and clustering layer for related issues, duplicate attempts, and closed threads.
Use live gh or gh api for the target thread and for any candidate before making an actionable judgment.
Use live GitHub when gitcrawl is missing or stale for a concrete reason, such as:
gitcrawl errors, times out, or lacks the needed neighbor/search dataWhen you fall back to live GitHub search, note that you did so and why.
If a later prtags target-level write fails because its own mirror has not caught up, stop and report that the curation backend is missing the target object instead of forcing a fallback write.
For each target PR or issue:
prtags group for that duplicate clusterprtagsprtags group writes to drive GitHub comment sync when that integration is configuredUse the tools with these boundaries:
gitcrawl is candidate generation and historical context
gh is live GitHub truth
gh search only when gitcrawl is stale, missing data, or cannot express the needed queryprtags is the maintainer curation layer
…
Fetch GitHub issues, create fixes, open PRs, and handle reviews.
Convert text to speech locally and offline with sherpa-onnx, no cloud needed.
Regenerate OpenClaw release changelog sections from Git history before releases.
Prepare and verify OpenClaw stable or beta releases and release notes.
Automate web page workflows, login checks, tab handling, and recovery steps.
Verify an OpenClaw release is fully published and working across all channels.
Deeply review code and fix only small, high-confidence OpenClaw bugs.
Review, triage, and manage OpenClaw issues and pull requests faster.
Find and fix small high-confidence OpenClaw bugs ready to land.
Refactor OpenClaw docs pages with source-checked preservation, clearer structure, and verification.
Handle ClawSweeper reports, fixes, merges, permissions, and GitHub workflow monitoring.
Complete an OpenClaw PR landing workflow end to end using the repo checklist.