gh-work-planning-checklist
Compact live-execution checklist companion for the canonical gh-work-planning route. Use for fast operational tracking during issue planning without replacing the full route.
Best use case
gh-work-planning-checklist is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Compact live-execution checklist companion for the canonical gh-work-planning route. Use for fast operational tracking during issue planning without replacing the full route.
Teams using gh-work-planning-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-planning-checklist/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How gh-work-planning-checklist Compares
| Feature / Agent | gh-work-planning-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 the canonical gh-work-planning route. Use for fast operational tracking during issue planning without replacing the full route.
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 Planning Checklist Use this as the compact operational checklist during live execution. `gh-work-planning` remains the canonical and authoritative source of truth. If this checklist conflicts with the full route, follow `gh-work-planning`. ## Trigger notes Use when: - work starts from a GitHub issue - you need Issue -> Plan -> Approval -> Execution discipline - you want a short runbook while posting progress live Do not use this as a substitute for the full planning route. ## Live checklist 1. Intake - Read the full issue, acceptance criteria, references, and labels. - Classify T1/T2/T3. - Post planning-start comment before any implementation. - Decision gate: continue, blocker, or future issue. 2. Resource intelligence - Stay read-only. - Check code, tests, docs, issue/PR history, standards or upstream constraints, and prior session context. - Record proof: exact files, docs, issue/PR numbers, commits, commands. - Identify implementation surface, gaps, risks, and artifact locations. - Capture out-of-scope discoveries as future-issue candidates immediately. - Confidence gate: High/Medium can proceed; Low means keep investigating or stop and post blocker. 3. Draft the plan - Write the canonical plan artifact under `docs/plans/YYYY-MM-DD-issue-NNN-<slug>.md`. - Include deliverable, file map, tests, acceptance criteria, risks, scope boundaries, and follow-up issues. - Separate required now vs later work. - Delegation gate: explicitly decide yes/no on Codex agent-team packaging. 4. Codex prompt-pack delegation check - Delegate only if work splits cleanly into non-overlapping streams. - Assign explicit owned paths, forbidden paths, dependencies, validation, and GitHub authority limits per stream. - Enforce zero git contention: no shared files, branches, or worktrees across streams. - If delegating, prepare stable prompt-pack structure: - `master-plan.md` - `stream-<id>.md` - `execution-readme.md` - If boundaries are fuzzy, do not delegate yet. 5. Adversarial review - Run independent plan review via Codex + Codex + Gemini. - Compare verdicts, synthesize findings, revise plan, and re-review if changes are material. - Review gate: no silent downgrade of major concerns. - Mark residual risk and whether plan is ready for approval. 6. GitHub posting cadence - Post meaningful cumulative updates at major planning steps: - after intake/classification - after resource intelligence - after draft-plan readiness if useful - after review synthesis - with final plan + label update - Combine rapid sub-steps into one factual update instead of spamming. - Post blockers immediately. 7. Future-issue capture - Do not silently absorb adjacent work. - Create or clearly stage future issues for out-of-scope work, follow-up optimizations, blocked dependencies, separate bugs, or institutional knowledge worth tracking. - Link future issues back to the current issue and mention them in the plan. - Decision gate at each major step: continue current issue, create future issue, stop for user decision, or stop for blocker. 8. Approval gate - Before stopping: save the plan, update planning index if used, ensure follow-up issues are created or called out, post final plan comment, add `status:plan-review`, remove stale conflicting labels. - Final plan comment should include deliverable, scope boundaries, likely files/tests, review synthesis, residual risk, future issues, and explicit approval request. - Hard stop: do not implement while awaiting approval. - On approve: move to `status:plan-approved` and hand off execution package. - On revise/reject/hold: keep execution blocked and follow the canonical route. ## One-screen reminder Issue -> Intake -> Intelligence -> Plan -> Review -> Plan Comment -> `status:plan-review` -> Wait for approval -> Execute only after approval. Canonical authority: `gh-work-planning`.
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.
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
tax-pdf-download-workaround
Handle FreeTaxUSA PDF download popups that block automation by capturing structured data and manual download workflow