gh-work-execution-checklist
Compact live-execution checklist companion for approved GitHub issue work. Use during active implementation as a fast operational route; gh-work-execution remains the canonical source of truth.
Best use case
gh-work-execution-checklist is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Compact live-execution checklist companion for approved GitHub issue work. Use during active implementation as a fast operational route; gh-work-execution remains the canonical source of truth.
Teams using gh-work-execution-checklist should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/gh-work-execution-checklist/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How gh-work-execution-checklist Compares
| Feature / Agent | gh-work-execution-checklist | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Compact live-execution checklist companion for approved GitHub issue work. Use during active implementation as a fast operational route; gh-work-execution remains the canonical source of truth.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# GH Work Execution Checklist Compact companion skill for live execution. `gh-work-execution` is the canonical and authoritative route. Use this checklist to stay on-track during active work, not to replace the full route. ## Trigger notes Use when: - the issue is already planned and approved - you need a fast execution checklist while working - you want to keep GitHub updates, validation, and closeout disciplined Do not use this instead of the canonical route when scope, delegation, policy, or closeout decisions are unclear. ## Live checklist 1. Entry gate - Confirm the issue is approved for execution. - Confirm repo/worktree/policy context is known. - Confirm you know the intended validation path. - Post a concise execution-start note if execution is proceeding. - If approval, authz, environment, or validation path is missing: stop and route back per `gh-work-execution`. 2. Already-done check first - Inspect the deliverable surface before changing code. - Run the most relevant targeted validator/test. - Check issue comments, linked PRs, and recent history if it may already be landed. - Decide explicitly: `already done`, `not done`, or `uncertain`. - If `already done`, post evidence and close from the verification-first path. 3. Central vs delegated decision - Default to central unless ownership boundaries are crisp. - Delegate only when owned paths, validators, GitHub authority, and integration ownership are explicit. - Use hybrid only when recon/slices can be delegated safely but final integration stays central. - If the decision changes execution ownership or reporting flow, post that change to GitHub. 4. TDD loop - Write or update the failing targeted test first. - Implement the smallest change that should pass. - Run the narrowest relevant test loop. - Refactor only after green. - Repeat until acceptance is satisfied. 5. Targeted validation gate - Run the specific tests/validators that prove the issue is done. - Add broader validation only where risk or repo policy requires it. - Capture exact evidence for GitHub and commit messaging. - If validation is incomplete or ambiguous, do not advance. 6. Adversarial review gate - Challenge the change like a skeptical reviewer. - Check acceptance coverage, regressions, edge cases, and policy fit. - Check whether new work should become a future issue instead of being absorbed. - If non-trivial concerns remain, fix them and re-run validation. 7. Commit/push gate - Confirm the diff matches approved scope. - Confirm tests/validators used as evidence are still green. - Commit with a message tied to the landed work. - Push only after validation and review are complete. - Post the landed summary and verification evidence to GitHub. 8. Closeout - Close only when the issue is landed, or proven already satisfied/invalid with evidence. - Link any future issues discovered during execution. - Post concise final verification evidence. - Leave the issue with a clear done-state, not an implied one. ## Operating note When in doubt, stop using the checklist as a shortcut and return to `gh-work-execution` for the full decision framework, delegation rules, GitHub posting cadence, blocker handling, and closeout requirements.
Related Skills
agent-os-framework
Generate standardized .agent-os directory structure with product documentation, mission, tech-stack, roadmap, and decision records. Enables AI-native workflows.
solidworks-to-blender-pipeline
Use when converting SolidWorks .sldprt/.sldasm geometry to Blender for rendering, animation, or visualization, including questions about STEP export settings, FreeCAD as a bridge, or which mesh format (STL/OBJ/GLTF) to choose.
digitalmodel-worktree-test-execution-with-shared-venv
Run digitalmodel tests from isolated worktrees without uv editable-dependency failures by using the main repo's existing virtualenv and PYTHONPATH.
digitalmodel-orcawave-orcaflex-proof-workflows
Class-level digitalmodel OrcaWave/OrcaFlex readiness, semantic-proof, fixture-proof, and closeout workflows.
blender-worktree-test-hardening
Recover and harden digitalmodel Blender automation work in isolated worktrees when uv/editable dependency paths break and local machines lack a Blender executable.
worktree-pre-push-bypass-for-tier1-checks
Handle workspace-hub integration-branch pushes from isolated git worktrees when the pre-push hook incorrectly assumes sibling tier-1 repos exist under the worktree path.
worktree-branch-sync-hygiene
Class-level branch, worktree, dirty-main, stash, sync, and hook hygiene for workspace-hub style multi-repo work.
workspace-knowledge-doc-contracts
Class-level workspace knowledge, LLM-wiki, repo mission contracts, stale doc references, semantic taxonomy, and knowledge-source reconnaissance.
workspace-hub-overnight-plan-monitor
Monitor and reconcile workspace-hub overnight planning or implementation batches, including process status, result artifacts, issue/commit verification, and controlled failed-lane recovery.
verify-Codex-run-commit-vs-working-tree-before-closing
After a Codex implementation run, verify the claimed file set against the actual commit and working tree before treating the issue as fully complete.
plan-gated-issue-execution-wave
Execute a multi-issue architecture/planning wave in a plan-gated repo, then safely transition approved issues into implementation with file-based Codex prompts, local approval markers, subprocess monitoring, and cleanup handling for sandbox/hook edge cases.
work-around-merge-conflicts-in-test-execution
Run tests when repo has unresolved merge conflicts in config files by bypassing broken configs and executing tests directly