ai-mktpl

Use this skill to understand the claude marketplaces in the nsheaps github org: the plugin marketplace build, release, and propagation pipeline. Recall this skill when working on CI/CD workflows, mise tasks, plugin versioning, marketplace updates, or when asked how plugins get from source code to a user's Claude Code installation. Also recall when debugging version bumps, marketplace.json drift, or plugin cache issues.

Use this skill when the user asks about GitHub operations, pull requests, issues, releases, actions, gists, repos, or any task involving the GitHub CLI (gh). Also use when needing to interact with GitHub APIs, check CI status, review PRs, manage labels, create releases, or automate GitHub workflows from the command line.

Manually configure the GitHub App bot git identity the way the github-app plugin's SessionStart hook does — resolve the app slug and bot user ID, build the <slug>[bot] name and noreply email, set GIT_AUTHOR_*/GIT_COMMITTER_* env vars, and write an isolated GIT_CONFIG_GLOBAL with the gh auth git-credential helper. Use when commits are attributed to the wrong account, "Author identity unknown" appears, or git identity must be set up by hand. <example>my commits are showing up as the handler, not the bot</example> <example>git says Author identity unknown after the github-app hook ran</example> <example>configure the github app bot git identity manually</example> <example>set up the gh credential helper for git push</example>

Manually reproduce what the github-app plugin's SessionStart hook does to make a GitHub App installation token usable in the current session — materialize the PEM, generate the token, isolate GH_CONFIG_DIR, write the runtime env file, and wire CLAUDE_ENV_FILE so every Bash call sees GH_TOKEN/GITHUB_TOKEN. Use when the hook did not run, the token is missing from the environment, or a shell/teammate needs the token wired up by hand. <example>GH_TOKEN isn't set even though github-app is configured</example> <example>the github-app SessionStart hook didn't run, set up the token manually</example> <example>wire the github app token into CLAUDE_ENV_FILE</example> <example>gh keeps falling back to the wrong account, isolate GH_CONFIG_DIR</example>

Manage GitHub App installation tokens in Claude Code sessions. Use when tokens expire, auth errors occur in long-running sessions, or when setting up GitHub App credentials for agent teams. <example>my github token expired</example> <example>refresh the github app token</example> <example>check token status</example> <example>set up github app authentication for this session</example>

Manages spec files for requirements capture and validation

Auto-detect project formatting tools and configure edit-utils settings

Use this skill to sync plugin SPEC.md files with what's actually on disk (skills, rules, hooks, agents, commands). Recall when the user asks about SPEC.md drift, "are SPEC files up to date", spec scaffolding, or after adding/renaming a skill/rule/hook/command in a plugin.

Reference material for Claude Code internals — the on-disk layout under ~/.claude and project-scope .claude, the plugin cache, session-env propagation, and the full hook lifecycle. Auto-recall when working on Claude-Code-related tasks: writing or debugging hooks, authoring plugins, inspecting session state, troubleshooting why an env var is or isn't visible to a Bash tool call, or when paths under ~/.claude or ~/.claude/plugins/ come up.

Use this skill when the user asks about op-exec, running commands with 1Password secrets injected, wrapping processes with secret injection, automating secret-aware command execution, or configuring whole-item environment injection with multiple output targets. op-exec is a wrapper around the 1Password CLI that simplifies running commands with secrets from 1Password vaults.

Use this skill when the user asks about 1Password, secrets management, retrieving credentials, using op CLI, service accounts, secret references, vault operations, or any task involving the 1Password CLI (op). Also use when needing to inject secrets into environment variables, read passwords or API keys from 1Password, or manage 1Password items from the command line.

Use this skill when the user wants to log a behavioral incident, document a correction in a structured incident report, or maintain learned rules with footnote references back to source incidents. Trigger phrases include "log an incident", "log this incident", "track an incident", "behavioral incident", "document this correction as an incident", "create incident report", "file an incident", or when the user explicitly asks for a structured incident record with severity classification and rule derivation.

This skill should be used when creating, updating, or reviewing specifications during the PR process. Trigger phrases: "write a spec", "update the spec", "does this PR have a spec", "add a spec to this PR", "review the spec", "spec-driven development", or when making plugin changes that need specification documentation.

Use this skill when the user says you did something wrong, made a mistake, or wants to correct your behavior. Trigger phrases include "don't do that", "that's wrong", "stop doing X", "you should have done Y", "correct yourself", "fix your behavior", "remember to always/never", or any feedback about incorrect AI actions that should be prevented in the future.

Session recovery skill. Use on startup, after compaction, or when resuming work after any interruption. Restores crons, audits recent history to determine current state, and identifies what to work on next.

Use this skill when the user says "make an issue", "create an issue", "file a bug", "this is a bug", "let's follow up later", "track this", "open a ticket", "create a ticket", "log this for later", "we need to fix this", "add to backlog", "make a task for", "file an enhancement", "create a feature request", or any phrase indicating that something should be tracked, logged, or followed up on in a ticketing system.

Use this skill when investigating compiled programs, executables, shared libraries, or any binary file where you need to understand its structure, embedded content, or build-time decisions. Trigger when: - User asks to inspect, analyze, or reverse engineer a binary - Finding hardcoded values, URLs, config keys, or strings in a compiled program - Understanding what libraries a binary links against - Investigating build-time decisions embedded in an executable - Extracting embedded resources or metadata from compiled code - Checking what symbols/functions a library exports Do NOT trigger for: - Text files, YAML, JSON, scripts (read directly with Read tool) - Running or executing binaries (binary-inspector is read-only) - Dynamic analysis, tracing, or debugging (strace/gdb are out of scope)

Gracefully exit the Claude Code session by sending SIGINT to the Claude process. Works for local CLI sessions and Claude Code Web (remote sessions). Use when you need to exit the session cleanly, or when the user requests exit/termination.

Restart the Claude Code session by gracefully exiting so the launcher loop restarts it. Use when you need to pick up config changes, plugin updates, or env var changes. Requires a launcher script (e.g., run-agent.sh) that restarts Claude after exit.

Create a new thread in a Discord forum channel by calling the Discord REST API. Use when the Discord `reply` MCP tool fails against a forum channel (type 15) because forum channels only accept thread creation, not plain messages. After creation, use `reply` with the returned thread id for follow-up messages.

This skill should be used when organizing work via GitHub Issues and Projects, creating project boards, managing milestones, or when consolidating fragmented tracking into GitHub-native tracking. Trigger phrases: "set up projects", "create a project board", "organize issues", "milestone planning", "what issues need attention", "consolidate tickets".

Use this skill when setting up or debugging Renovate auto-merge, configuring Renovate in a repo, or diagnosing why Renovate PRs are not auto-merging.

Manage Discord channel access — approve pairings, edit allowlists, set DM/group policy. Use when the user asks to pair, approve someone, check who's allowed, or change policy for the Discord channel.

Manage Telegram channel access — approve pairings, edit allowlists, set DM/group policy. Use when the user asks to pair, approve someone, check who's allowed, or change policy for the Telegram channel.

Set up the Telegram channel — save the bot token and review access policy. Use when the user pastes a Telegram bot token, asks to configure Telegram, asks "how do I set this up" or "who can reach me," or wants to check channel status.

Perform a comprehensive automated code review using granular review skills. Orchestrates review-pr-contents, review-commits, review-commit-messages, review-diff, review-code, validate-review, and post-review as building blocks. Use this for new review workflows — scm-utils:code-review is maintained for backward compatibility with Henry's CI workflow.

Code review a pull request. Triggers on "review this PR", "code review", "review PR #123", "request a review", "review bot", "code review CI", "automated PR review", "claude review workflow", or when the user wants to add automated code review to a repository.

Fix issues found during a review. Use when asked to "fix review findings", "address review comments", "fix the issues found", or after a review identifies problems that need code changes.

Post or update a review on GitHub. Use when asked to "post the review", "submit review", "leave a review on the PR", "update the review", or when you have review findings ready to publish on a pull request.

Quick-reference index for the full PR review workflow. Redirects to automated-code-review for the full orchestration. Use when asked to "do a full review", "review everything", or "comprehensive review".

Full PR lifecycle management: creating, iterating on feedback, and merging. Triggers on: "review my PR", "iterate on PR feedback", "address review comments", "PR workflow", "get this merged", "respond to reviewer", "handle PR feedback".

Best practices and procedures for creating and maintaining high-quality pull requests. Covers PR creation, body formatting, title conventions, lifecycle management, and requesting reviews. Counterpart to review-code, respond-to-review, and other review-receiving skills. Triggers on: "create a PR", "update the PR", "open a pull request", "push and PR", "fix PR", "fix PR body", "PR formatting", or automatically after any push to a feature branch per the auto-pr-management rule.

Respond to review comments on a PR. Use when asked to "respond to review", "reply to reviewer", "address review comments", "respond to PR feedback", or when crafting responses to reviewer questions and suggestions.

Review code quality, patterns, and bugs. Use when asked to "review the code", "check code quality", "look for bugs", "review implementation", or when evaluating code correctness, security, and maintainability independent of the diff or PR context.

Review commit message quality. Use when asked to "review commit messages", "check commit message format", "are commit messages good", or when evaluating whether commit messages are conventional, descriptive, and useful.

Review commit structure and organization. Use when asked to "review commits", "check commit history", "are commits atomic", "review commit structure", or when evaluating whether commits are logically grouped and ordered.

Review the diff against the base branch. Use when asked to "review the diff", "check what changed", "review changes against main", "is this PR complete", or when evaluating whether a diff is scoped correctly and complete.

Review PR title, body, labels, and metadata. Use when asked to "review the PR", "check PR description", "is the PR body good", "review PR metadata", or when evaluating whether a PR is well-presented for reviewers.

Validate that review findings are accurate and actionable. Use when asked to "validate review", "check if review findings are correct", "verify review accuracy", or when confirming that a review's claims match actual code state.

Deployment and release management. Use when the user asks about "deployment", "CI/CD", "release", "shipping", "publishing", "deploy pipeline", "release process", or when setting up or managing deployment workflows. Covers CI/CD configuration, release strategies, and deployment validation.