$ ~/registry/skill/openclaw-agents-skills-openclaw-landable-bug-sweep

SKILL

openclaw-landable-bug-sweep

Name: openclaw-landable-bug-sweep
Author: openclaw

Find and fix small high-confidence OpenClaw bugs ready to land.

Stars

★ 382,582

Source

GitHub

Updated

2026-07-11

// securityCaution

Prompt only, no code
Open source
Community-trusted· 377.5k

Summary

The material indicates a prompt-only workflow with no required secrets and no declared remote endpoints, backed by an open-source GitHub source and very high community adoption, so overall risk is low. Caution is still warranted because its intended workflow drives code changes and PR operations, which may indirectly involve code execution and repository data access when paired with other tools in a host environment.

CredentialsLow risk

The material explicitly states that no keys or environment variables are required, and the README does not ask for tokens, API keys, or account credentials. Based on the provided facts, there is no clear sign of credential collection, storage, or misuse.

Network egressLow risk

The system metadata declares no remote endpoints, and the skill is classified as prompt-only. Although the README mentions GitHub CI, PR URLs, and companion skills, this skill itself does not declare direct external connections or explicit data exfiltration.

Code executionCaution

The README describes a maintainer workflow and includes intended actions such as `git status`, `git pull`, testing, and autoreview, indicating it may guide the host to run local commands and modify code. For a skill/workflow this is a normal capability, and the material does not show requests for system permissions beyond its stated purpose.

Data accessCaution

To perform bug sweeps, fixes, and PR preparation, the skill is expected to read repository code, test results, branch state, and related issue/PR context. This implies ordinary read/write access to project data, but the material does not indicate overbroad access to unrelated files, personal data, or sensitive system resources.

Supply chainLow risk

The source is an open-source GitHub repository with extremely high community adoption (about 377k stars), which is a strong risk-reducing factor; the system also marks it as open-source. The missing license declaration and unknown maintenance status are minor information gaps, but not enough on their own to justify a high-risk rating.

Recommendations

Use this skill only in controlled repositories and least-privilege environments, avoiding automatic pairing with high-privilege tools by default.
If used with GitHub, testing, or autoreview companions, verify each companion tool's network access, write permissions, and credential requirements separately.
Review the repository source and recent commits before deployment to confirm maintenance status and ensure behavior matches the README.

Audited by: gpt-5.4 · 2026-06-17

// install

Copy the install command and let the AI configure it · recommended for beginners

Please install the "openclaw-landable-bug-sweep" skill from askskill:
1. Download https://raw.githubusercontent.com/openclaw/openclaw/main/.agents/skills/openclaw-landable-bug-sweep/SKILL.md
2. Save it as ~/.claude/skills/openclaw-landable-bug-sweep/SKILL.md
3. Reload skills and tell me it's ready

// download

Download SKILL.mdInstall manifest ↗

// examples

Identify landable small bugs

Prompt

Please inspect the OpenClaw codebase and find up to 5 high-confidence, small-scope bugfix opportunities that do not touch SDK boundaries. For each candidate, describe the issue location, evidence, fix approach, potential risk, and rank them by landability.

Expected

A prioritized list of bugfix candidates with evidence, fix recommendations, and landability assessment.

Generate a fix plan for one bug

Prompt

For this OpenClaw bug candidate, provide a minimal fix plan: explain the root cause, affected files, suggested changes, tests to add, and why the change does not touch SDK boundaries.

Expected

A submission-ready minimal fix plan with code change points and test additions.

Review whether a PR is landable

Prompt

Please review this OpenClaw bugfix PR and determine whether it is a small, high-confidence, non-SDK-boundary change that is ready to land. List the reasons for or against landing, remaining risks, and exact revision suggestions if needed.

Expected

A landability review stating whether to land the PR and what revisions are still needed.

// docs

OpenClaw Landable Bug Sweep

Autonomous maintainer workflow for producing five landable OpenClaw bugfix PR URLs. Use for broad issue/PR sweeps where the bar is high and the output is PRs, not notes. Do not use for plugin SDK/API boundary work; those need separate architecture review.

Target

Return exactly five PR URLs, each with:

bug summary
why the fix is low-risk
proof: rebased-head local/Testbox/live commands or run IDs
autoreview: clean result on the exact head being shown
CI green on the exact pushed PR head
issue/duplicate cleanup done or still pending

The five URLs may be existing PRs that were reviewed/fixed, or new PRs created from issues/clusters. Do not present a PR URL to the maintainer until it has been refreshed on current main, left-tested, autoreviewed clean, pushed, and verified green in live GitHub CI. If code, tests, changelog, PR body, or branch base changes after autoreview, rerun autoreview before showing the URL.

Companion Skills

Use $gitcrawl for discovery/clustering, $openclaw-pr-maintainer for live GitHub mutation rules, $github-author-context when contributor trust matters, $openclaw-testing for proof choice, $autoreview before publishing/landing, and $crabbox for broad/E2E/live proof.

Candidate Bar

Accept only when all are true:

bug or paper cut, not feature/product/support/docs-only
root cause is proven in current code
dependency behavior checked via upstream docs/source/types when relevant
production/runtime diff is small, ideally much smaller than 500 LOC and always below 500 LOC
tests may be larger, but focused
no new dependency
no new config option
no backward-incompatible behavior
no security/product/owner-boundary decision needed
no plugin SDK, public plugin API, or src/plugin-sdk/** boundary change
no broad refactor smell
focused proof is feasible
branch can be rebased/refreshed and pushed, or a replacement PR can be created

Good examples:

provider parameter mismatch proven against dependency/API contract
CLI command diverges from adjacent command behavior
narrow runtime state/serialization bug with failing test
issue already fixed on current main, with proof and closeable duplicates

Reject:

feature requests, new knobs, migrations, release work, workflow policy, support
plugin SDK/API boundary changes, including compatibility shims, new SDK methods, SDK exports, or plugin-facing channel/provider seams
auth/security boundary changes unless explicitly assigned
bugs needing live credentials that are unavailable
PRs with red CI unless you fix, rebase, push, and recheck them green
PRs you only reviewed locally but did not refresh/push/check live
PRs whose final head has not passed $autoreview
fixes whose clean shape is a larger architecture move
speculative reports without reproducible/provable cause
UI/UX changes requiring product judgment

Sweep Loop

Start clean:
- git status -sb
- git pull --ff-only
- verify branch is expected, usually main
Build candidate clusters:
- gitcrawl open issues/PRs, neighbors, and search
- live gh issue/pr view
- include PRs linked from issues and duplicates
For each cluster:
- read issue/PR body, comments, labels, linked refs, current source, adjacent tests
- suppress maintainer-owned queue noise unless it is the best fix path
- identify opener/author and preserve credit
- decide: repair-existing-pr, create-new-pr, close-fixed-on-main, close-duplicate, or reject
Prove before patching:
- failing test, focused repro, log/source proof, or dependency contract proof
- if already fixed on main, prove with current source/test/commit and close kindly
Patch:
- prefer existing PR when good and writable
- if unwritable or wrong shape, create own PR and preserve useful contributor credit
- if no PR exists, create one
- add regression test when it fits

…

View full docs ↗

Handle ClawSweeper reports, fixes, merges, permissions, and GitHub workflow monitoring.

openclawGet→

$ loading_