By mistakenot
End-to-end AI-agent task delivery: requirements, solution, plan, review, execute, and ship features through a structured plan-to-merge workflow.
Works through all open PR review threads by fixing code, replying to reviewers, and resolving threads. Use when 'address feedback', 'fix PR comments', 'resolve review threads', or after a code review has left feedback on the PR.
Performs a structured code review of changes with severity labels covering correctness, security, performance, error handling, testing, and architecture. Use when 'code review', 'review this PR', 'review changes', or when a structured review of implementation changes is needed.
Verifies completeness of all planning docs and commits them to main. Use when 'commit the task', 'finalize the task', 'commit task docs', or after all planning docs have been reviewed and approved. Not applicable when implementation has already started or for committing code changes.
Finalizes a feature branch and merges it to main. Addresses remaining PR feedback, runs tests, writes feedback.md, merges the PR, exits the worktree, and verifies the merge. Use when 'complete task', 'finalize and merge', 'ship this task', or when the feature branch is ready to ship.
Dispatches task execution to an idle Claude Code pane in a tmux session, freeing the current session for other work. Use when 'delegate task', 'send to executor', or when the user wants to hand off a task to a background pane.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A collection of reusable agent skills that implement the Portable Task Workflow -- an AI-agent-driven feature delivery lifecycle from requirements through merged PR.
requirements.md -> solution.md -> context.md -> plan.md -> worktree execution -> PR -> review -> merge -> feedback
Planning happens on main. Implementation happens on feature branches in isolated git worktrees. Each stage is a discrete skill invoked via slash command.
| Skill | Description |
|---|---|
new-task | Create a new task folder with requirements.md from user input |
new-solution | Write a solution design (solution.md) by exploring approaches and tradeoffs |
new-plan | Write context.md and plan.md by gathering codebase context and breaking work into phases |
execute-task | Autonomously implement a planned task end-to-end using worktree isolation |
delegate-task | Dispatch task execution to an idle Claude Code pane in a tmux session |
executor-status-check | Monitor all executor panes in a tmux session and report status |
commit-task | Verify completeness of planning docs and commit them to main |
complete-task | Finalize a feature branch and merge it to main with PR, testing, and cleanup |
code-review | Perform a structured code review with severity labels |
review-task | Review task planning documents and leave structured inline comments |
request-codex-review | Send task planning docs to Codex for review, then resolve any comments |
address-feedback | Work through open PR review threads by fixing code and resolving threads |
resolve-comments | Resolve inline review comment threads in planning docs (markdown and HTML) |
task-feedback-analyser | Extract recurring patterns from completed task feedback into workflow rules |
generate-10-ideas | Brainstorm 10 ideas by generating 100 candidates and filtering to the top 10 |
revise-readme | Update README and documentation to reflect the current state of the project |
npx skills install mistakenot/skills -s '*' -a claude-code codex -y
npx skills install mistakenot/skills -s new-task -a claude-code codex -y
This installs into .claude/skills/ and .agents/skills/.
Files in ./skills/ are compiled output. Edit the source files in ./src/ and run the Makefile targets:
make compile # Compile src/ -> skills/
make install # Compile + install locally into .claude/skills/ and .agents/skills/
make lint # Lint all skills with autoskill
make check # Compile + lint (pre-commit check)
npx claudepluginhub mistakenot/skills --plugin planning-workflowDocumentation maintenance: keep READMEs and docs in sync with the current state of the code.
Structured ideation: generate high-impact feature ideas and run synthetic user-research simulations to decide what to build next.
Author rich single-file HTML planning docs with tabs, mermaid diagrams, file-change trees, and inline comment threads.
Mine git history, PRs, and session transcripts into a structured learning diary of techniques and breakthroughs.
De-risk ideas before building: run exploratory tech spikes that validate assumptions and stress-test approaches.
Persistent file-based planning for AI coding agents. Crash-proof markdown plans (task_plan.md, findings.md, progress.md) that survive context loss and /clear, with an opt-in completion gate and multi-agent shared state. Manus-style. Works with Claude Code, Codex CLI, Cursor, Kiro, OpenCode and 60+ agents via the SKILL.md standard. Includes Arabic, German, Spanish, and Chinese (Simplified and Traditional).
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
v9.44.1 — Patch release for Gemini environment/version detection and qwen auth gating. Run /octo:setup.
AI-powered development tools for code review, research, design, and workflow automation.
Claude harness - A harness for solo developers (Vibecoders) to handle full-cycle contract development.
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques