Every skill in the Han suite, alphabetized. Each entry is a short scent line and a link to the skill's canonical long-form doc, which now lives inside the plugin that ships it. For how these skills chain together, see Workflows. To decide which plugin to install, see the plugin index.
See also: Repo root · Plugin index · Workflows · All agents · Concepts · Quickstart
Start on the Quickstart; it picks the right skill for what you are trying to do right now. If the skill-and-agent split is fuzzy, read Concepts first.
/agent-builder— Build a new agent from scratch through an evidence-based interview that walks the design tree decision-by-decision, then review the finished agent file against the plugin-building guidance and apply every fix./architectural-analysis— Assess a module's coupling, data flow, concurrency, risk, and SOLID alignment through a spine of structural, behavioral, risk, and architecture agents./architectural-decision-record— Create, extract, or convert architectural decision records./automated-test-planning— Produce a prioritized test plan for a branch or directory./code-overview— Produce a human-readable, progressive-disclosure overview of unfamiliar code or a PR's changes, leading with why the code exists; raises no findings./code-overview-to-confluence— Run/code-overview(changing no code), show it for review, then publish it as one Confluence page after confirmation./code-review— Run a comprehensive code review on the current branch or specified files, with a size-scaled roster of specialist agents./code-walkthrough— Walk someone through a branch's changes one step at a time in conversation, from the entry point along the flow, stopping after every step so they set the pace./coding-standard— Create and update coding standards from existing patterns or evidence-based research./design-an-api— Design the contract for an API change inside one codebase, with every element justified from one stated goal and the design run past a question round and an adversarial validation round./edit-for-readability— Rewrite the prose of a target you already have against the shared readability standard, preserving every fact./explanation-guidance— Surface the shared standard for explaining technical work to a reader who will not implement it, so a skill's questions and stops name a concrete outcome instead of a mechanism./gap-analysis— Compare two artifacts (current state versus desired state) and produce a plain-language, stakeholder-readable report indexed by stable gap IDs./guidance— Serve the authoritative guidance for building skills, agents, and plugins, or vendor the plugin-building skills into the current repository (/guidance init)./han-feedback— Capture structured post-session feedback on the Han skills and agents you used, and optionally post it as a GitHub issue to testdouble/han./html-summary— Convert astakeholder-summary.mdinto a single self-contained HTML executive report; produces the file only, does not publish it./investigate— Run an evidence-based investigation of a bug, failure, or unexpected behavior, with adversarial validation of the proposed fix./investigate-to-confluence— Run/investigate(changing no code), show the report for review, then publish it as one Confluence page after confirmation./issue-triage— Classify a vague issue or bug report, identify missing information, assess severity and reproducibility, and recommend the right next skill to run./iterative-plan-review— Stress-test an already-written plan through multiple codebase-grounded review passes./manual-test-planning— Produce a plain-language manual test plan from supplied context: named tests with by-hand steps and expected outcomes for a person to run./markdown-to-confluence— Publish one local Markdown file to a user-specified Confluence location; defaults to an unpublished draft./pairing— Build work collaboratively in reviewable pieces, handing each one back before starting the next, so you steer while the work happens./plan-a-feature— Build a feature specification from scratch through an evidence-based interview that walks the design tree and dispatches specialist reviewers./plan-a-feature-to-confluence— Run/plan-a-feature, show it for review, then publish the spec and its companion artifacts as a Confluence page tree./plan-a-phased-build— Split a body of context into a numbered sequence of vertical-slice build phases, each independently demoable to a real person and each building on the prior./plan-implementation— Turn a feature specification into an implementation plan through a facilitated team conversation./plan-work-items— Divide a trusted implementation plan into independently-grabbable, atomic work items in a single work-items file./post-code-review-to-pr— Run/code-reviewagainst a GitHub PR and post the review as comments, after a clarity check on the drafted review body./project-discovery— Scan the repository for languages, frameworks, tooling, and structure, and write a concise reference section into AGENTS.md or CLAUDE.md./project-documentation— Create and maintain documentation for features, systems, and components./project-documentation-to-confluence— Run/project-documentation, show it for review, then publish it to a user-specified Confluence location./readability-guidance— Surface the shared readability standard into a calling skill's own context so it drafts in voice and self-checks against one canonical copy./refactor— Restructure existing code without changing its behavior through a test-gated loop that re-runs the full suite after every small step./research— Research an open-ended question across the codebase and the open web and end at an adversarially-validated recommendation, without committing the team to any artifact./runbook— Create or update a runbook for a single operational scenario, with a symptom-first template and a YAGNI preflight that requires real evidence before writing./skill-builder— Build a new skill from scratch through an evidence-based interview that walks the design tree decision-by-decision, then review the finished files against the plugin-building guidance and apply every fix./stakeholder-summary— Turn a feature specification into a plain-language stakeholder summary with Mermaid diagrams, for feedback before implementation./tdd— Drive a feature or behavior through a BDD-framed red-green-refactor loop with an enforced observed-failure gate; it writes code, not a document./update-pr-description— Generate a PR description from the current branch's changes, conforming to the repository's PR template when one exists./work-items-to-issues— Publish each item in a/plan-work-itemswork-items file as a GitHub issue in its target repo, with within-repo blockers linked./work-items-to-jira— Create one Jira ticket per slice from a/plan-work-itemswork-items file in a single target project./work-items-to-linear— Create one Linear issue per slice from a/plan-work-itemswork-items file in a single target team, resolving the team's real states, labels, Projects, and members before creating anything.
See Contributing for the full process and
the skill template for the long-form layout. Add the skill's long-form doc
under its plugin's docs/skills/, a scent line to that plugin's README, and one alphabetized entry here, reusing the
long-form doc's summary line as the canonical scent so the three do not drift.