pre-pr-checks
Run the full pre-PR verification routine (format, lint, tests, type/package checks, coverage) in an isolated subagent so the main thread stays clean. Invoke this after a gh pr create is blocked by the pre-tool-use hook; report ready or unready back to the main thread.
What this skill does
# Pre-PR Checks
Run all PR-readiness checks in one pass. Designed to be spawned as a
background-or-foreground subagent so the main agent does not absorb
long test/coverage output into its context.
## When to use
The main agent triggers this skill when the PreToolUse hook blocks a
`gh pr create` call. The main agent spawns a subagent with this skill;
the subagent runs the full routine and replies with either:
- **"ready"** — all checks pass, main agent retries `gh pr create …
# checks-passed`
- **"not ready"** — short summary of what failed and the precise next
step the main agent should take
## Routine
Run in this order. Stop and report on the first blocking failure,
unless the failure is fixable in place (formatters, trivial lints).
### 1. Format
- `task format` if a Taskfile exists
- Otherwise language default (R: `styler::style_pkg()`, Python:
`ruff format .`, Julia: `JuliaFormatter.format(".")`)
- Commit any formatting changes with a `style:` prefix
### 2. Lint
- `task lint` if available
- Otherwise language default (R: `lintr::lint_package()`, Python:
`ruff check .`, Julia: `Aqua` or project equivalents)
- Fix all issues. Commit fixes separately from feature work.
### 3. Tests
- `task test` if available
- Otherwise language default (R: `devtools::test()`, Python:
`pytest`, Julia: `Pkg.test()`)
- All tests must pass. Do not skip or xfail to get green.
### 4. Type or package checks
- `task check` if available (runs R CMD check, Pkg.test, etc.)
- R packages: `devtools::check()` must be clean (0 errors, 0 warnings,
note-only is acceptable)
- Python: mypy / pyright if configured
- Julia: `Aqua.test_all()` if configured
### 5. Coverage on changed files only
- Identify files changed on this branch:
`git diff --name-only $(git merge-base HEAD origin/main)..HEAD`
- Report uncovered lines in those files only. Ignore pre-existing gaps
in untouched files.
- Tools:
- R: `covr::zero_coverage()` filtered to changed files
- Python: `pytest --cov=<pkg> --cov-report=term-missing` then filter
- Julia: `Coverage.process_folder()` filtered to changed files
## Skip rules
Skip a step silently if the project has no corresponding tooling
(no Taskfile target and no language default configured). Do not invent
checks. If the project has no tests at all, note it in the report and
continue.
## Reporting format
Return a short message to the main thread:
```
ready|not-ready
<one-line status per step — format, lint, tests, checks, coverage>
<if not-ready: the exact next action for the main agent>
```
Keep long test output out of the reply. The main agent should not need
to see raw stack traces — only what changed and what to do next.
## Rules
- Use `run_in_background: false` when the main agent is waiting to
retry; `true` only if it explicitly wants to keep working.
- Do not run `gh pr create` yourself; that is the main agent's job
once you report ready.
- Do not add `# checks-passed` anywhere; the main agent appends that
on retry.
- Make commits for fixes where appropriate so the main agent's retry
includes them.
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.