check-tasks-completion-status
Audit whether a ticket is actually complete without changing files.
Skill by thunter009
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/thunter009-check-tasks-completion-status
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: security
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/check-tasks-completion-status
What's inside
- Skill name
check-tasks-completion-status- Description
- Audit whether a ticket is actually complete without changing files.
- License
- MIT
- Instructions
- 162 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Check ticket completion status Check ticket completion status by auditing the codebase and docs. Do not modify any files. If local execution isn't possible, perform a static audit and explain the limitations. Review an existing ticket/task and determine whether it is complete based on the current codebase, tests, and documentation. Provide a thorough, evidence-backed report and propose any follow-up actions. Be conservative: if uncertain, mark as "Needs Review" rather than "Complete." If I want you to check a specific task/ticket, I will include that here: $ARGUMENTS Examples for $ARGUMENTS: - File path: docs/tasks/active/01-implement-auth.md - Task title: "Implement Auth" - Issue/PR reference: "#123" or "PR-456" - Keyword(s): "payments webhook" Primary sources of truth in this repo: - docs/start-here.md - docs/tasks/ (active/, backlog/, completed/) - README.md (root) - docs/reference/, docs/how-to-guides/ - Source code, tests, configuration, feature flags - Git history (commits, branches, tags) and local PR branches (if present) ## What to do ### Identify the target ticket - If $ARGUMENTS is provided: - Resolve it to one or more task files under docs/tasks or to obvious code references. - If ambiguous, list candidates and ask me to choose before proceeding. - If $ARGUMENTS is not provided: - List tasks in docs/tasks/active/ with a short 1-line summary and ask which to check. ### Extract or define acceptance criteria - Read the matching task file(s) and pull out explicit acceptance criteria if present. - If criteria are missing or incomplete: - Derive a draft criteria set from: - Summary, Action Items, Technical Details in the task file - docs/start-here.md (Roadmap, phases) - README.md (Current Status), docs/reference/, relevant code comments/tests - Produce a concrete checklist using observable/verify-able conditions (e.g., endpoints respond, UI renders states, tests pass, env vars configured). - Present the acceptance criteria and your audit plan; pause for my confirmation before evaluating. ### Plan the audit - Outline exactly where you'll look: - Code directories/files likely impacted - Feature flags/config keys - Database schema/migrations - API routes/handlers/services - Frontend components/pages - Background jobs/cron/queues - Tests (unit/integration/e2e), plus any fixture or mock data if present - Outline which commands you'll run (if runnable), with fallbacks if running is not possible. ### Execute a static audit (no changes yet) - Search the repository for relevant symbols, routes, components, and references. - Inspect implementation completeness (not just stubs): - Data flow end-to-end (API -> service -> persistence -> UI) - Error handling and edge cases - Permissions/RLS/security checks where applicable - Feature flags enabled in non-dev envs - Configuration and environment variables required - Migrations and seed data (if needed) - Cross-check docs for drift: - docs/tasks: does this task still sit in active/ but appears done? - docs/start-here.md "Roadmap" and README "Current Status" reflect reality? ### Execute a runtime/test audit (if feasible) - Try to run tests and/or the app using minimal, standard commands (adapt as needed): - npm install - npm run build - npm test - npm run dev - If running is not feasible, explain why and provide the closest-possible verification via code/logic/tests review. - If tests exist for the ticket, verify they cover the acceptance criteria and pass locally. ### Evaluate each acceptance criterion and collect evidence - For each criterion, mark: - Met - Not met - Unclear (needs manual verification or missing data) - For each, cite evidence: - File paths and key lines/functions - Test names/paths and results - Commands run and outputs (summarized) - Screenshots or logs if available (summarize if not attachable) ### Decide status and propose actions - Overall status: - Complete - Not Complete - Needs Review (insufficient certainty) - If Complete: - Propose specific documentation updates: - Move task file from docs/tasks/active/ to docs/tasks/completed/ - Update README.md "Current Status" if applicable - Update docs/start-here.md Roadmap statuses if applicable - Propose a concise PR/commit plan (branch name, commit messages). - If Not Complete: - List the smallest next actions needed to reach completion (ordered, time-bounded). - Point to exact code locations for each action. - Recommend tests to add/fix. - Suggest who/what might be needed (env vars, credentials, external services). - If Needs Review: - List the specific uncertainties and what would resolve them. ### Ask before making changes - Do not modify code or docs yet. - Present the report and proposed changes; ask for approval. - If approved to update task docs, you may run the "update-task-documentation.md" command or draft the changes as a patch for my review.
From thunter009/skills, MIT.
More from thunter009/skills
- 0.570score
decision-canvas
thunter009
Present batched user decisions as an interactive atrium canvas with inline grounding — code snippets with real line numbers, click-to-open file links, and…
SkillAFreshness: AClaude Code +9 - 0.529score
clean
thunter009
End-of-work cleanup sweep for a multi-agent repo — safely land genuine unpushed commits, squash open PRs, prune merged branches and worktrees, clean the…
SkillBFreshness: BClaude Code +9 - 0.526score
autoreview
thunter009
Run a structured code review (Codex default, Claude optional) as a closeout check on a local or PR branch before commit or ship.
SkillBFreshness: BClaude Code +9 - 0.520score
bug-hunt
thunter009
Run a multi-phase bug hunt with Codex, Gemini, or Claude.
SkillBFreshness: BClaude Code +9 - 0.518score
create-pull-request
thunter009
Open a GitHub pull request with repo-specific PR conventions.
SkillBFreshness: BClaude Code +9 - 0.514score
agents-md
thunter009
Create repo-specific AGENTS.md guardrails from the codebase.
SkillBFreshness: BClaude Code +9 - 0.479score
enrich-ticket-detail
thunter009
Flesh out thin or empty beads/Todoist items by mining git history, code-at-HEAD, closed tickets, and the session journal, then verify every drafted claim…
SkillCFreshness: CClaude Code +9 - 0.476score
codebase-knowledge-graph
thunter009
Build an interactive knowledge graph of any codebase via the Understand-Anything pipeline, with a batch-integrity guard the raw plugin lacks.
SkillCFreshness: CClaude Code +9 - 0.476score
docs-organize
thunter009
Reorganize loose files already in a folder into its subfolder taxonomy, with hash-based dedup, dry-run preview, and collision-safe moves.
SkillCFreshness: CClaude Code +9 - 0.474score
devbox-cleanup
thunter009
Clean up a project checkout on a remote dev box — tear down a stale agent swarm, verify unpushed work is superseded, reset the checkout to origin, and restart…
SkillCFreshness: CClaude Code +9 - 0.470score
domain-modeling
thunter009
Build and sharpen a project's ubiquitous language — a CONTEXT.md glossary plus sparse ADRs — challenging terms against the glossary and cross-referencing code…
SkillCFreshness: CClaude Code +9 - 0.469score
beads-linear-sync
thunter009
Sync beads and Linear so agent state and human tracker stay aligned.
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jul 14, 2026 (3 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/thunter009/skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from thunter009
- 0.570score
decision-canvas
thunter009
Present batched user decisions as an interactive atrium canvas with inline grounding — code snippets with real line numbers, click-to-open file links, and…
SkillAFreshness: AClaude Code +9 - 0.529score
clean
thunter009
End-of-work cleanup sweep for a multi-agent repo — safely land genuine unpushed commits, squash open PRs, prune merged branches and worktrees, clean the…
SkillBFreshness: BClaude Code +9 - 0.526score
autoreview
thunter009
Run a structured code review (Codex default, Claude optional) as a closeout check on a local or PR branch before commit or ship.
SkillBFreshness: BClaude Code +9 - 0.520score
bug-hunt
thunter009
Run a multi-phase bug hunt with Codex, Gemini, or Claude.
SkillBFreshness: BClaude Code +9 - 0.518score
create-pull-request
thunter009
Open a GitHub pull request with repo-specific PR conventions.
SkillBFreshness: BClaude Code +9 - 0.514score
agents-md
thunter009
Create repo-specific AGENTS.md guardrails from the codebase.
SkillBFreshness: BClaude Code +9
Cite this page
check-tasks-completion-status skill. Agent Mart. https://agentmart.dev/skills/thunter009-check-tasks-completion-status (last updated 2026-10-24)