Issue Pipeline — From GitHub Issue to Reviewed PR

    1

    Take one GitHub issue through diagnosis, a reviewed plan, isolated implementation, a traceable PR review and CI readiness.

    $20

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Issue Pipeline — From GitHub Issue to Reviewed PR

    Example session with this skill installed

    Check this synthetic PR's readiness. The current head, local tests, adherence and independent review all reference the same snapshot. Plan review passed. The repository requires test@app, but that CI job never reported because runner billing prevented it from starting. Keep the PR open; do not waive CI or mutate GitHub.

    • Read your context and instructions
    • Compiled the issue pipeline

    Synthetic readiness demonstration

    The packaged check_readiness.py helper was executed locally against a synthetic evidence record with matching head/base snapshots and a missing required test@app check. It returned exit code 1 and this complete JSON result:

    {"status":"HELD","blockers":["CI_MISSING: test@app"],"notice":"Checks supplied evidence only; does not authorize merge or verify live GitHub state."}
    

    Workflow decision

    Keep the PR open and held. The missing required job is not a successful CI run, even though local tests and review passed. Record the context and cause, preserve the plan, Implementation Report and worktree, and restore CI so the required check can run on the same head. If the code or base changes, refresh the snapshot and repeat affected gates before reporting readiness.

    Validation scope

    This demonstrates the local evidence helper and the prescribed decision, not a live GitHub implementation or merge. The helper checks supplied records; it cannot verify their truth, human approvals or complete repository policy. No issue, PR or repository was changed for this demonstration.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Turn a GitHub issue into a traceable, reviewed pull request. Issue Pipeline separates planning, implementation and review so the plan becomes a concrete contract rather than an informal suggestion.

    The workflow carries acceptance criteria, a caller and side-effects map, a focused coder brief and test evidence through each stage. A claim-by-claim Implementation Report explains what matched the plan, what changed and what remains unresolved. Review and CI evidence are tied to the current head and base; stale checks or missing required CI leave the PR held.

    Includes the complete per-issue procedure, independent review contract, evidence format and a read-only Python helper that checks a supplied readiness record. The helper does not contact GitHub or certify the truth of its inputs. The coding agent performs the workflow using its own authorized tools and fresh isolated sessions. Default behavior leaves the PR open; merging requires the user's authorization.

    Created from my public project: https://github.com/lhermoso/claude-workflows . The original MIT-licensed issue-pipeline command is freely available there. This standalone edition removes private command paths and fixed provider runners, bundles the required procedures, adds explicit recovery and evidence rules, and includes a tested consistency helper. The MIT license and attribution are included.

    Best for one issue at a time. Drain Issues adds dependency-aware backlog scheduling and includes this core per-issue procedure; you do not need both purchases. Model usage, GitHub services and project infrastructure are not included.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Agents & Orchestration.

    This is an agent workflow, not a hosted service or an unattended scheduler. Results depend on the host's agent isolation, tool permissions, repository test suite and GitHub policy. AI review can miss defects. Missing CI or independent reviewer capability blocks completion. Model usage and infrastructure costs are separate from this one-time skill purchase. Local helper tests and simulated workflow decisions do not establish live end-to-end reliability.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 26 days ago

    Accounts
    GitHub
    Software
    Git
    GitHub tools
    orGitHub CLI
    Project test runtimes
    Optional
    Python 3.9+

    GitHub access can come from your agent host's tools or gh. The agent must start fresh isolated sessions. Python runs optional helpers.

    Permissions

    Terminal / Shell
    Read Files
    Write Files
    Network Access

    Allowed Hosts

    api.github.com

    File Scopes

    **/*
    .git/**

    Reads and writes only the selected repository, task-owned isolated worktrees and private run records. Runs authorized project tests and Git operations; uses GitHub for issue/PR data and authorized assignment, commits, pushes, reports and merges. Fresh agent sessions receive task-relevant evidence under the host's controls. Credentials stay in the existing authorized host/CLI integration; never paste them into prompts or logs. No deployment, branch-protection changes, admin bypass or persistent background service. Dry-run performs no project execution or Git/GitHub mutation.

    Listed26 days ago

    What's inside

    Frequently Asked Questions

    A coding agent that can launch fresh isolated sessions, Git, repository tools, authorized GitHub access and your project's test runtimes. The optional local helpers need Python 3.9+ with no third-party packages. Model usage is not included.

    Only within the user's authorized task scope and after current review, test, CI and platform gates pass. It never changes branch protection or uses admin bypass. Dry-run is inspection only.

    This is the author's standalone adaptation of https://github.com/lhermoso/claude-workflows . The original MIT-licensed commands remain free. This edition bundles its procedures, evidence contracts and tested local helpers without private command paths or provider-specific runners.

    No. It records evidence and stops on unresolved gates, but AI review and tests can miss defects. Live GitHub execution and Agensi delivery were not tested during package preparation.

    New in Agents & Orchestration