agent-workflow

Plugin agent-workflow from marketplace ehnruiz in ehnruiz/claude-skills. Commands read from the repo's manifest — 18 days ago.

Skills (23)

• confluence-jira-links

  Link a Confluence page and the Jira tickets it is about, both ways, without duplicates - each ticket shown on the page as a Jira smart link, and a "mentioned in" web link on each ticket pointing back to the page. Use whenever you create or edit a Confluence page (draft or published) that discusses J

• diagnosing-bugs

  A disciplined loop for hard bugs, flaky tests and performance regressions - build a red-capable feedback loop first, reproduce and minimize, rank falsifiable hypotheses, instrument one variable at a time, then repair and remove the probes. Use when the user says "diagnose", "debug this" or "why is t

• epic-review

  Review a Jira epic (or the Jira Product Discovery idea it implements) against its own In Scope list - which items are done, partly done, not started, or have no evidence - then flag scope conflicts and stale statuses, and draft the In Scope list for the follow-on epic. Use this whenever the user is

• explain-the-number

  Like-for-like before a measured number is reported or credited to a change. Use before saying a change moved a score, a count, a before/after delta, a benchmark time or speedup, a Lighthouse or Core Web Vitals result, an eval score, or an error, conversion or traffic rate. For whether the tests and

• grilling

  Grill the user relentlessly about a plan, decision, or idea until every branch of it is settled. Use when the user wants to stress-test their thinking, says "grill me", "poke holes in this", "interrogate this plan", or asks to be questioned before building something.

• handoff

  Write a handoff note so a fresh session can continue this one's work. Use when the user says to hand off, wrap up, or save progress for later, or when a long session is about to end with work still open.

• leader-1-1-prep

  Build a prep brief for a recurring 1:1 with a skip-level or senior leader. Pulls the last meeting's notes, the tickets you touched since, recent chat threads with that leader and any drafts they are waiting on, then drafts a fixed five-block agenda with a carry-forward list and an after-action step.

• llm-integration

  Checklist for code that calls a language model or exposes a system to one. Use when writing or reviewing code that calls a model API (Anthropic, OpenAI, Bedrock, Gemini, Perplexity), a prompt or prompt template, structured model output, an MCP server or tools an agent will call, or a surface that ca

• no-ai-attribution

  Keep AI-assistant credit lines out of anything published on the user's behalf. Use before writing a commit message, pull request, issue, comment, review reply, ticket, wiki page or chat message.

• open-in-my-browser

  Open a link the user shares in their own Chrome through the Claude in Chrome extension, where their sign-ins and VPN work. Use whenever the user pastes a URL to a private or internal page (a pull request, a ticket, a wiki page, a dashboard, an internal host) or says "use my browser".

• pick-up

  Continue work from a handoff note an earlier session wrote. Use when the user says to pick up, continue or carry on from earlier work, or points at a handoff file.

• plain-writing

  Draft text a person will send or post under their own name, in plain language that does not read as machine-written. Use when drafting or editing a chat message, an email, a pull request description, a comment, a wiki page, an announcement or a post on the user's behalf, or when the user says a draf

• regression-proof

  Prove a change before claiming it is done - judge lint, typecheck, tests and git push by their exit codes rather than by reading output, and show that a bug fix's regression test fails without the fix. Use before saying "tests pass", "lint is clean", "pushed" or "fixed in <sha>"; before opening or u

• research

  Investigate a question against primary sources and capture the findings as one cited Markdown note. Use when the user wants a topic researched, a vendor's docs or API facts gathered, a library's or tool's real behavior confirmed, or reading legwork delegated while the main session keeps working.

• retro

  Review a finished coding session for what slowed the agent down or let a mistake through, and turn one lesson into a test, check or doc in the project so the next session does not repeat it. Use when the user asks for a retro or retrospective, a post-mortem of a session, or "what should we change so

• security-audit-runner

  Runs Cloudflare's security-audit skill in full audit mode from Claude Code. It builds each agent's prompt file from that skill's text, pulls each agent's JSON reply out of its transcript, and keeps the coverage ledger, findings, agent-call budget and NEEDS-VALIDATION.md. Use it together with `securi

• skill-collision-audit

  Find skills whose descriptions fight over the same request, so Claude picks one at random or the wrong one, and fix the descriptions. Use when the user asks to audit, clean up or deduplicate their skills, when a skill fires that should not have, after installing a plugin, or before adding a new skil

• supervisor

  Route a multi-step task across cheaper subagents while the main session keeps the plan, the judgment calls and the verification. Use at the start of any task with more than one step, before spawning a subagent, when picking a model for a subtask, when a subagent fails, or when the user mentions cost

• tdd

  Test-driven development, red then green, one vertical slice at a time. Use when building a feature, a rule, a config option or a bug fix test-first, when the user says "TDD", "red-green" or "write the test first", or when a subagent is handed a ticket to build.

• ticket-digest

  Turn a batch of tickets created or updated in a time window into one short, paste-ready message, one line per ticket, flagging the ones that need a decision. Use when the user asks what they filed today or this week, wants a recap or roundup for a product owner or team channel, or after filing three

• ticket-trim

  Shorten an existing ticket that is too long or too technical, moving the engineering detail into a Technical notes comment so nothing is lost. Use when the user gives a ticket key or link and asks to trim, condense, simplify or clean it up, or says a product owner or analyst found it hard to read.

• ticket-write

  Draft and file short tickets (bug, task, story, spike, epic) that a business analyst or product owner can read in under a minute, with the engineering detail moved to a first comment. Use when the user wants to create, draft or file a ticket in Jira, Linear or GitHub Issues, or to turn findings from

• writing-for-agents

  Writing documents for agents. Use when creating or editing a skill (its SKILL.md, description or reference files), when modifying AGENTS.md or CLAUDE.md, or when reviewing an agent-facing document that behaves inconsistently across runs. Prose that people read, such as a memo or a one-pager, follows

Subagents (6)

• doc-writer

  Writes prose from facts it is given, on the cheapest model: a changelog entry, a README or docs section, a pull request description, a release note, a message draft. It does not investigate beyond the lines it is pointed at.

• implementer

  Builds one scoped ticket test-first on a mid-tier model: a feature, a config option, a bug fix whose cause is known. Give it the ticket, where the change goes, the command that proves it and the files involved. It does not commit.

• researcher

  Reads primary sources in the background on a mid-tier model and writes one cited Markdown note: a vendor's docs or API, a standard, a library's source, how a tool really behaves. Give it the question and where to save the note. Used through the research skill.

• reviewer

  Reviews a diff on the strongest model along two axes, the ask and the repository's standards, and gives each finding file:line, a concrete failure scenario and a verdict (confirmed, needs_validation or rejected). Use before a pull request is opened, and to refute a finding someone else raised, such

• scout

  Read-only finder on the cheapest model. Use for "where is X", which files touch Y, the callers of a function, or a summary of a long file or log. Returns file:line pointers and short quotes, never whole files.

• tester

  Writes and runs tests without touching production code, on a mid-tier model: a regression test for a reported bug, a missing negative case, a fixture fix, or a full suite run with exit codes.

Hooks (2)

• SessionStart

  python3 "${CLAUDE_PLUGIN_ROOT}/hooks/handoff_notice.py"

• PreCompact

  python3 "${CLAUDE_PLUGIN_ROOT}/hooks/pre_compact.py"

Similar plugins