Claude Skills by atomicinnovation

Body.

Body.

Custom review lens.

A decision index mapping common intents to the Accelerator

Create a new skill `/respond-to-pr` that allows users to interactively work through outstanding pull request review feedback. The skill fetches all unresolved comments and review requests, triages them by priority, then walks through each item one at a time — verifying the feedback against the codebase, confirming the approach with the user, making changes, responding on GitHub, and resolving the thread. After all items are addressed, it offers to re-request review from the original reviewers.

Create a dedicated `research-issue` skill that provides hypothesis-driven debugging workflows for production issues. It lives alongside `research-codebase` in `skills/research/` but uses a distinct RCA output template and a causal-chain investigation flow rather than exploratory breadth-first research.

Ship two new artifacts — the `templates/note.md` template and the `skills/notes/create-note/SKILL.md` skill that consumes it — so that short-form notes become a first-class artifact type with a creator skill and unified-schema frontmatter. Notes are date-slug-named files under `meta/notes/` carrying the unified base fields plus `topic` and the `revision`/`repository` provenance bundle. The skill mirrors `create-work-item` structurally but is materially simpler: no sequential allocator, no approv

Implement `/sync-work-items` — an on-demand skill that reconciles local work items in `meta/work/` against the remote tracker named by `work.integration`, persisting a `last-sync.json` content-parity baseline. The skill supports four modes (bidirectional default, `--push-only`, `--pull-only`, `--preview`), resolves conflicts with a section-by-section diff and a remote-default override prompt, offers to push never-pushed items, and pulls untracked remote issues. Because this skill produces the `l

**Date**: 2026-02-23T01:30:00+00:00 **Author**: Toby Clemson **Repository**: .claude (Claude Code configuration)

**Date**: 2026-06-06T09:33:34+00:00 **Author**: Toby Clemson **Git Commit**: 70e86d6dd86759a59677bba83c922c83b08300b5 **Branch**: ticket-management (jj workspace) **Repository**: ticket-management

**Date**: 2026-06-18T12:48:49+00:00 (UTC) **Author**: Toby Clemson **Git Commit**: 2aec82d6560fe5407629156cde6eb8d99b208b6a **Branch**: HEAD (jj workspace `ticket-management`) **Repository**: ticket-management

**Kind**: Story **Status**: Done **Priority**: Medium **Author**: Toby Clemson

**Kind**: Story **Status**: Done **Priority**: Medium **Author**: Toby Clemson

**Kind**: Story **Status**: Draft **Priority**: Medium **Author**: Toby Clemson

View, create, or edit Accelerator plugin configuration. Manage document templates.

Prepare a repository with the directories and gitignore entries

Apply pending Accelerator meta-directory migrations to bring a repo into line with the latest plugin schema. Destructive by default but guarded — refuses to run on a dirty working tree and prints a one-line preview per pending migration before applying.

Resolves all configured document-discovery paths for the current

Interactively create an architecture decision record (ADR). Use

Extract architecture decision records from existing meta documents

Review an architecture decision record for quality and

Compare two design inventories produced by inventory-design and emit

Generate a structured design inventory for a frontend source —

Generate a comprehensive pull request description following the

Respond to pull request review feedback interactively, working

Review a pull request through multiple quality lenses and present a

Use this skill only when the user explicitly invokes /attach-jira-issue to upload one or more local files as attachments to a Jira issue. This is a write skill with irreversible side effects — it must never be auto-invoked from conversational context. Previews what will be uploaded and requires explicit confirmation before POSTing.

Use this skill only when the user explicitly invokes /comment-jira-issue to add, list, edit, or delete comments on a Jira issue. This is a write skill with irreversible side effects — it must never be auto-invoked from conversational context. Subcommands: add (post a new comment), list (fetch all comments with pagination), edit (update an existing comment), delete (remove a comment — irreversible). Write subcommands preview the resolved intent and require explicit confirmation before calling ...

Use this skill only when the user explicitly invokes /create-jira-issue to create a new Jira issue. This is a write skill with irreversible side effects — it must never be auto-invoked from conversational context. Accepts a project key, issue type, summary, optional Markdown body, and optional fields (assignee, reporter, priority, labels, components, parent, custom fields). Previews the resolved intent, requires explicit confirmation, then POSTs to Jira and returns the new issue key.

Set up the Jira Cloud integration for this project. Verifies credentials against a real Jira Cloud tenant, discovers the tenant's custom-field catalogue and project list, and persists the results under `<paths.integrations>/jira/` (default `.accelerator/state/integrations/jira/`) as team-shared, version-controlled JSON caches. Idempotent: safe to re-run after credential or project changes.

Use this skill whenever the user wants to search, list, or filter Jira tickets — by assignee, status, label, project, type, component, reporter, parent, or free text — even if they say 'find', 'show me', 'what's open', 'list my tickets', or similar phrasing rather than 'search Jira'. Composes safe JQL from structured flags, executes a paginated search against a Jira Cloud tenant, and renders a summary table of the results. Supports --render-adf to convert ADF descriptions to Markdown inline. ...

Use this skill when the user asks about a specific Jira issue by key (e.g. PROJ-123, ENG-456) — for viewing the description, status, comments, transitions, or any other field. Trigger when the user says 'look up', 'check on', 'tell me about', 'what's on', or 'what is the status of' a key, or asks any direct question about an issue they reference. Do NOT trigger when an issue key appears incidentally inside other prose (commit messages, code review comments, release notes), where the user is t...

Use this skill only when the user explicitly invokes /transition-jira-issue to move a Jira issue through its workflow by state name. This is a write skill with irreversible side effects — it must never be auto-invoked from conversational context. Accepts an issue key and target state name (case-insensitive). Previews the resolved transition and requires explicit confirmation before posting.

Use this skill only when the user explicitly invokes /update-jira-issue to modify an existing Jira issue. This is a write skill with irreversible side effects — it must never be auto-invoked from conversational context. Accepts an issue key and at least one mutating flag (summary, body, priority, assignee, reporter, parent, labels, components, custom fields). Previews the resolved intent with set-vs-update semantics, requires explicit confirmation, then PUTs to Jira.

Use this skill only when the user explicitly invokes /attach-linear-issue to attach a link or a binary file to an existing Linear issue. This is a write skill with irreversible side effects — it must never be auto-invoked from conversational context. Link mode registers an external URL; binary mode uploads a local file via Linear's pre-signed URL flow and registers the resulting asset. Shows a preview, requires explicit confirmation, then attaches.

Use this skill only when the user explicitly invokes /comment-linear-issue to add a Markdown comment to an existing Linear issue. This is a write skill with irreversible side effects — it must never be auto-invoked from conversational context. It shows the comment preview, requires explicit confirmation, then posts the comment.

Use this skill only when the user explicitly invokes /create-linear-issue to create a new Linear issue from a local work-item file. This is a write skill with irreversible side effects — it must never be auto-invoked from conversational context. It reads the work item's title and Markdown body, shows a payload preview, requires explicit confirmation, then creates the issue and writes the remote-allocated identifier (e.g. BLA-123) back into the file's external_id frontmatter field.

Set up the Linear integration for this project. Verifies a Linear personal API key against the real Linear GraphQL API, lets you pick one team, and persists that team plus its WorkflowState catalogue under `<paths.integrations>/linear/` (default `.accelerator/state/integrations/linear/`). `catalogue.json` is team-shared and version-controlled; `viewer.json` is per-developer and gitignored. Idempotent: safe to re-run after credential or team changes.

Use this skill whenever the user wants to search, list, or filter Linear issues — by state, assignee, label, or free text — even if they say 'find', 'show me', 'what's open', 'list my issues', or similar phrasing rather than 'search Linear'. Composes a Linear IssueFilter from structured flags, executes a cursor-paginated search scoped to the configured team, and renders a summary table of the results. Prefer this skill over raw GraphQL whenever the user's intent maps to a structured flag.

Use this skill when the user asks about a specific Linear issue by identifier (e.g. BLA-123, ENG-456) — for viewing the description, state, assignee, or comments. Trigger when the user says 'look up', 'check on', 'tell me about', 'what's on', or 'what is the status of' an identifier, or asks any direct question about an issue they reference. Do NOT trigger when an identifier appears incidentally inside other prose (commit messages, code review comments, release notes), where the user is talki...

Use this skill only when the user explicitly invokes /transition-linear-issue to move an existing Linear issue to a different workflow state. This is a write skill with irreversible side effects — it must never be auto-invoked from conversational context. The target state name is resolved to its UUID from the cached catalogue (no live lookup). Shows a preview, requires explicit confirmation, then applies the transition.

Use this skill only when the user explicitly invokes /update-linear-issue to change fields on an existing Linear issue (title, description, state, assignee, priority). This is a write skill with irreversible side effects — it must never be auto-invoked from conversational context. It shows a payload preview, requires explicit confirmation, then applies the update.

Interactively capture a short-form note. Use when jotting down

Create detailed implementation plans through interactive, iterative

Execute an approved implementation plan from the configured plans

Review an implementation plan through multiple quality lenses and

Interactively stress-test an implementation plan by grilling the user

Validate that an implementation plan was correctly executed by

Interactively conduct a time-boxed spike — collaboratively reduce

Conduct comprehensive codebase research by spawning parallel