ai-bits-and-pieces

Plan coding work as a compact implementation-step bundle with a conservative research decision, high-level overview first, and planning artifacts written only under .project_planning/YYYY-MM-DD_FEATURE_NAME/. This skill plans only — it never writes, edits, or refactors implementation code, and never skips ahead to building. If only the skill name is given, ask for a high-level description first before writing planning files.

Execute an approved coding plan as serial-first implementation steps with tight scope control, planner-defined verification strategy, and mandatory sub-agent/worktree execution.

Review coding changes against the approved plan, identify concrete bugs, regressions, and plan-adherence gaps, run approved isolated fix passes, then close the loop with optional planning-doc cleanup and PR/MR creation.

Execute an approved coding plan in staged steps with tight scope control, planner-defined verification strategy, deferred automated verification by default, and mandatory isolated sub-agent dispatch when the runtime supports safe worktree execution.

Close out a completed coding loop by validating final chain readiness, checking for leftover repository state, and optionally preparing and creating a PR or MR when the remote provider is supported.

Plan coding work in stages with a mandatory research-decision checkpoint, a high-level overview first, and planning artifacts written only under .project_planning/YYYY-MM-DD_FEATURE_NAME/. If only the skill name is given, ask for a high-level description first before writing any planning files.

Review coding changes against the approved plan, identify concrete bugs, regressions, and plan-adherence gaps, and, when approved, run a batched sequential review-fix loop using isolated sub-agents before finalization.

Fix grammar and clarity in any text while making the absolute minimum number of changes and preserving as much original wording as possible.

Summarise transcripts, articles, blog posts, meeting notes, URLs, or other long-form text into structured key points with takeaways. Use for fresh summarisation requests such as summarise, recap, distil, condense, TLDR, get the gist, key points, main idea, or what does this say. For follow-up questions about content already summarised, answer directly without the summary template. Do NOT use for translation, rewriting, or style editing.

Orchestrate the staged execution of a refactoring or implementation plan by dispatching sub-agents per stage via git worktrees, reviewing their output, and merging back into the current branch. Use this skill whenever the user asks to "run the plan", "execute the refactoring plan", "implement the stages", "orchestrate the plan", or points Claude at a plan file (e.g. .project_planning/*.md) and asks it to carry it out. Also triggers when the user says "oversee the implementation of [plan]", "dispatch agents for each stage", or any variant of "go through the plan step by step using sub-agents". This skill is intended for Claude Code only - it requires git, worktrees, and sub-agent spawning capabilities.

Crawl a codebase file by file, inspect every method and function for accumulated slop, and produce a detailed YAML report of findings with suggested fixes ready for an executor agent. Use this skill whenever the user asks to find slop, detect code smell, do a code hygiene pass, run a quality sweep, clean up vibe-coded mess, review a codebase for simplification opportunities, or any variant of "find the junk in this code". Also triggers for requests like "what needs cleaning up", "find complexity", "simplify this codebase", "code quality audit" (when not Go-specific), or "review all files for issues". This skill is language-agnostic - it handles Go, TypeScript, Python, Rust, Dart, Bash, HCL, Makefiles, Dockerfiles, and any other language. Do NOT use for single-file reviews, PR reviews, writing new features, or Go-specific audits (use go-code-audit for those).

Analyse a codebase for test coverage gaps and generate a prioritised, actionable plan to plug those gaps with a well-balanced spread of unit and functional tests. Use this skill whenever the user asks to improve test coverage, find untested code, write a test plan, identify missing tests, audit test quality, or increase confidence in their test suite. Triggers include phrases like "what's not tested", "coverage gaps", "write tests for this", "where do we need tests", "test plan", "add unit tests", "add integration tests", "improve test coverage", "our tests are weak", or any request to systematically assess or improve the testing posture of a project. Use this even when the user phrases it casually ("we barely have any tests - help") or technically ("generate a test plan targeting lines with no coverage"). Do NOT use for reviewing a single specific test file or writing one-off tests for a single function the user has already identified.

Audit a Go codebase for code quality issues and generate an ordered, step-by-step refactoring plan that an AI coding agent can execute. Use this skill whenever the user asks to audit, review, clean up, refactor, or improve the structure of a Go project - including requests like "audit my Go code", "clean up this repo", "make this codebase DRY", "refactor plan", "code quality review", "improve my Go project structure", or any mention of consolidating, reorganising, or paying down tech debt in a Go application. Also triggers when the user asks to review or improve an AGENTS.md file for a Go project. Do NOT use for single-file code reviews, PR reviews, or writing new features.

Perplexity-style web research scaffold for tool-enabled local models. Inserts a compact search contract plus a place to write the actual request.