patch-fanout
Skill from tusharsrivastava/shark-skills
Install
npx skills add tusharsrivastava/shark-skills --skill patch-fanout
Runs the open skills CLI and installs the skill for your agent (Claude Code, Codex, Cursor …). Alternatively copy the skill folder into .claude/skills/ or upload it in Claude.ai under Settings → Skills.
As a Claude Code plugin
/plugin marketplace add tusharsrivastava/shark-skills
/plugin install shark@shark-skills
This skill is part of the plugin “shark”. In Claude Code the plugin installs it together with the plugin’s other skills, commands and hooks.
What does the patch-fanout skill do?
Description from the SKILL.md in the source repository.
Questions about patch-fanout
What does the patch-fanout skill do?
Port many independent patch units in parallel, one patch agent (shark:code-writer) for each unit, each in its own worktree and branch from the integration head, each with a patch note for the lead. Each agent verifies the gap against production first, writes the test first, ports into the current architecture, runs light checks on its own files only, and commits. The lead (shark:lead-merge) merges the branches as they arrive; shark:merge-audit reviews each merge. Use after a port audit gives a unit index (UNITS.md from shark:port-audit), when the user says "fan out the units", "one agent per unit", "patch agents", "re-port the gaps", "parallel fixes", or when many small independent fixes must land fast without waiting for each other.
How do I install patch-fanout?
In a terminal: npx skills add tusharsrivastava/shark-skills --skill patch-fanout. The skills CLI asks which agents to install it for. In Claude.ai you can upload the skill folder as a ZIP under Settings → Skills.
Which agents can use patch-fanout?
Skills use the open SKILL.md format, which Claude Code, Claude.ai, the Claude API, OpenAI Codex, Cursor, Gemini CLI and other agents support.
Is patch-fanout safe to use?
Our automatic check found no risky patterns (piped shell scripts, hidden characters, secret access, prompt overrides). It is not a full audit – read the SKILL.md and any scripts before installing.
More skills from tusharsrivastava/shark-skills
Split a working tree into a sequence of conventional commits where every commit builds and passes the gate on its own, so git bisect stays trustworthy.
Write or rewrite a cookbook tutorial chapter for engineers who join the team. ASD-STE100, one story for the whole tutorial, terms taught as "plain idea, then the name", reading-level limits checked by …
Debug a defect to its root cause by stepping through the running program with the mcp-debugger tools (create a session, set a breakpoint, start, read the stack, scopes and variables, step or …
Create or refresh .gitignore from gitignore.io (toptal) templates and keep the project-specific rules.
Drive fix rounds toward one measurable goal on N failing scenarios (bench cases, end-to-end cases, acceptance checks).
Record and prune the handoff file, the state that carries between sessions, so it stays short and live.
Sets up a repository for the shark kit, one time for each project. Finds the project file that Claude Code reads (CLAUDE.md or AGENTS.md, or makes AGENTS.md), adds the missing project sections …
Run as the long-running lead engineer who merges patch or lane branches into one integration branch as they arrive, in batches, from a queue file that is the source of truth.
Related skills in Security
Run Azure compliance and security audits with azqr plus Key Vault expiration checks. Covers best-practice assessment, resource review, policy/compliance validation, and security posture checks.
Guides Microsoft Entra ID app registration, OAuth 2.0 authentication, and MSAL integration. USE FOR: create app registration, register Azure AD app, configure OAuth, set up authentication, add API permissions, generate service principal …
Rigor Run skill for README-first deep learning repo reproduction. Use when the task is specifically to capture or normalize evidence from the selected smoke test or documented inference or evaluation command and …
When the user wants to audit or diagnose SEO, or asks why traffic dropped, a page won't rank, or whether a setup like canonicals, hreflang, or redirects is right: technical SEO, indexing …
Audits Firebase (Firestore, Cloud Storage) security rules for vulnerabilities, privilege escalation, role bypasses, create vs update inconsistencies, resource exhaustion, type safety, size limits, and hasOnly ownership checks.
Audit a landing page, sales page or checkout page for conversion leaks and return a fix list ordered by expected revenue impact.
Audit, diagnose, or optimize website loading and interaction performance, Core Web Vitals, and Lighthouse performance scores.
Audit a browser fingerprint for internal contradictions with the liarjs CLI - canvas, WebGL, WebGL2, WebGPU, audio, 220 fonts, WebRTC and timezone probes, scored against the TLS/HTTP/ASN view of the same request. …