skills

Personal daily briefing assistant. Pulls the last 24 hours of email and calendar from Outlook, summarizes today's schedule, surfaces open action items, and proposes focus blocks. Use when user says "daily briefing", "morning briefing", "daily standup prep", or invokes /daily-briefing.

Draft a customer-facing release note for a Jira ticket by gathering the ticket context (summary, description, type, fix version, comments) and any linked GitLab merge requests / code changes, then synthesizing a clear, audience- appropriate release note. Runs a clarity-council quality pass over the draft. Read-only by default; the user may opt in at the end to publish the note as a Jira comment (or into a Release Notes field if one exists). Use when user says "draft release notes", "write a release note", "release note for [TICKET-KEY]", "what changed in this ticket", or invokes /issue-draft-release-notes with a ticket key.

Generate a per-team standup markdown report by gathering activity over the last N days from Jira, GitLab, Confluence, and a local Git repo. Maps activity to team members from a roster CSV, renders a Mermaid kanban + randomized talking order, captures a `daily`-tagged sprint snapshot, and runs a clarity-council (infographics-expert burndown chart + statistics-expert forecast + scrum-master suggestions) for sprint pulse. Writes one file per team into the Obsidian vault. Use when the user says "daily standup prep", "standup report", "generate standup", "scrum prep", or invokes /daily-standup-prep.

Morning kickoff wrapper that runs sprint-snapshot (daily tag), daily-standup-prep (with sprint burndown), and daily-briefing (report only — no focus-block suggestions) in order. Re-runs idempotently — existing same-day artifacts are overwritten in place. Use when user says "good morning", "morning routine", "kick off my day", "start my day", or invokes /good-morning.

Capture a point-in-time snapshot of a scrum team's current sprint board from Jira and render it into the Obsidian vault as (1) an Obsidian Canvas with sprint overview, team workload, kanban columns, and issue cards, (2) a companion markdown summary, and (3) an append-only JSONL trend log. Auto-detects sprint phase (start / week 1 / week 2 / week 3 / end) from today's date. Supports `--as-of <date>` for historical snapshots. Reuses obsidian-canvas / obsidian-vault / obsidian-markdown for vault writes and follows the issue-* skills' Jira context-gathering patterns. Use when user says "sprint snapshot", "snapshot the sprint", "capture sprint state", "sprint planner", "scrum board snapshot", or invokes /sprint-snapshot.

Safely rebase the current branch onto its upstream target (baseline, main, or master). Auto-resolves simple merge conflicts (version bumps, changelogs). Prompts for complex ones. Use when user says "rebase", "rebase branch", "rebase onto main", "update my branch", "sync with baseline", "catch up with main", or invokes /branch-rebase.

Resolve complex git merge/rebase conflicts by reconstructing intent, preserving both branches' goals when possible, and running automated checks.

Decode messages into plain language with tone and intent analysis. Breaks down what someone actually means, analyzes emotional tone with probability scores, and flags ambiguity. Use when user says "break it down", "what does this mean", "decode this", "analyze this message", "what are they saying", or invokes /break-it-down.

Facilitates structured single-persona or multi-persona consultation for strategy, product, engineering, operations, and risk decisions. Use when the user requests a council, multiple perspectives, persona advice, tradeoff analysis, or iterative clarification and debate.

Analyze a git repository's history and produce an SVG treemap of file churn — area = lines changed, color = commit frequency. Use when user wants to find unstable areas of a codebase, predict bug-prone files, see "where do we change the most", spot refactor candidates, or invokes /codebase-churn.

Tell the agent to explain code with broader context and a higher-level perspective. Use when you're unfamiliar with a section of code or need to understand how it fits into the bigger picture.

Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable.

Extract clean markdown content from web pages using Defuddle CLI, removing clutter and navigation to save tokens. Use instead of WebFetch when the user provides a URL to read or analyze, for online documentation, articles, blog posts, or any standard web page. Do NOT use for URLs ending in .md — those are already markdown, use WebFetch directly.

Log today's load (meetings, sensory stuff, social events, deep work); skill scores the load, warns when the day is heading toward burnout, and suggests what to drop or defer. Spoon-theory accounting for your calendar. Use when user says "energy budget", "spoon check", "am I overcommitted", "what should I drop", "burnout check", or invokes /energy-budget.

Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".

Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.

Compact the current conversation into a handoff document for another agent to pick up.

Reconstruct context after a deep session or interruption — "what was I doing?" Reads recent git diff, modified files, open editors, and last commits to rebuild your mental state and propose the next concrete action. Use when user says "what was I doing", "where did I leave off", "lost my place", "context recovery", "hyperfocus recovery", or invokes /hyperfocus-recovery.

Weigh one or more ideas/concepts with a structured pros-and-cons analysis. Runs a clarity-council pass to surface arguments on both sides, optionally grills the user to expose hidden assumptions, scores each point on Impact × Confidence, and renders a markdown table per idea plus an overall recommendation (Go / Go with caveats / Don't / Needs more analysis). Use when the user wants to evaluate an idea before committing, compare two or more options on the merits, build a pros/cons list, score tradeoffs, justify a decision in writing, or asks "should I do X" / "is X worth it" / "weigh the tradeoffs" / "pros and cons of X". Differs from idea-decision-maker (which forces a fast binary pick) and idea-generate (which generates new options) — this skill deliberates on options the user already has.

Stuck between options. Forces a binary, asks three clarifying questions, picks one with reasoning. Defeats analysis paralysis without leaving the decision to a coin flip. Use when user says "I can't decide", "help me pick", "decision paralysis", "break the tie", "which should I", or invokes /idea-decision-maker. Part of the `idea-*` family — the fast counterpart to idea-choice (which deliberates and produces a written pros/cons artifact); use this one when the user needs a verdict, not a record. Sits alongside idea-generate (which produces new options) at the "convergent / pick one" end of the family.

Helps users generate, refine, and stress-test ideas from loose topics. Use when user asks to brainstorm, find new ideas, or needs creative inspiration for a topic.

Quick dump for the current hyperfixation so it doesn't derail today's work but also isn't lost. Captures the idea, tags it, files it into the Obsidian vault for later return. Optimized for speed — no clarifying questions unless absolutely needed. Use when user says "capture this idea", "hyperfixation dump", "interest capture", "stash this", "don't let me forget", or invokes /interest-capture.

Scan all open issues in a Jira project and identify likely duplicates using semantic comparison. Produces a markdown report listing each suspected duplicate pair with a probability score and reasoning. Read-only — never modifies, links, or transitions tickets. Default project key is read from memory (`reference_jira_default_project.md`); accepts an override project key. Use when user says "find duplicates", "duplicate check", "dedupe issues", "find duplicate tickets", or invokes /issue-dup-find with or without a project key.

Estimate story points for a Jira ticket using historical data and multi-persona scrum poker. Use when user says "estimate this ticket", "how many points", "story point estimate", "estimate [TICKET-KEY]", or invokes /issue-estimate-sp. Read-only — never modifies the ticket.

Analyze a Jira ticket by gathering full context from Jira and Confluence, following linked tickets, then running a clarity-council to identify gaps and ambiguities. Produces an actionable breakdown plan. All actions are read-only. Use when user says "break down this feature", "analyze this ticket", "feature breakdown", or provides a Jira ticket key for analysis.

Suggest Jira components for one ticket or sweep all open tickets in a project. Gathers context from Jira, Confluence, and GitLab, proposes a conservative set of existing components (or recommends new ones), and confirms with the user before any modification. Bulk mode default project key is read from memory (`reference_jira_default_project.md`); max 250 tickets, highest key first. Use when user says "suggest components", "tag components", "fix components", "categorize tickets", or invokes /issue-suggest-component with or without a ticket key.

Triage a bug or issue by gathering context (Jira ticket or free-form description), mapping the suspected code area via codebase-explain, hypothesizing root causes via clarity-council, and producing a structured triage report with ranked root-cause candidates and proposed solution paths. Read-only by default; the user may opt in at the end to publish the report as a Jira comment. Use when user says "triage this", "triage [TICKET-KEY]", "what's causing this bug", "help me find the root cause", or invokes /issue-triage with a ticket key or issue description.

Dump what happened in a meeting; skill separates facts from feelings, flags action items, and notes social ambiguities to follow up on (instead of ruminate on). Useful for masking-heavy meetings where the cognitive cost is paid afterward. Use when user says "meeting decompression", "process this meeting", "what just happened", "decompress", "after meeting", or invokes /meeting-decompression.

Create and edit Obsidian Bases (.base files) with views, filters, formulas, and summaries. Use when working with .base files, creating database-like views of notes, or when the user mentions Bases, table views, card views, filters, or formulas in Obsidian.

Create and edit Obsidian Canvas files (.canvas) following the JSON Canvas spec — nodes, edges, groups, and connections. Use when working with .canvas files, creating visual canvases, mind maps, or flowcharts in Obsidian.

Build interactive charts in Obsidian notes using the Charts plugin (phibr0/obsidian-charts). Renders Chart.js bar/line/pie/doughnut/radar/polarArea via `chart` codeblocks, can pull data straight from a markdown table by block ID (cross-file supported), and can render from a Dataview query via `window.renderChart`. Use when the user wants to chart, plot, graph, or visualize data sitting in their Obsidian notes — including tables, frontmatter values, Dataview/Dataviewjs results, or hand-written series — or mentions "obsidian charts", "chart codeblock", "renderChart", or "chart from table".

Interact with Obsidian vaults using the Obsidian CLI to read, create, search, and manage notes, tasks, properties, and more. Also supports plugin and theme development with commands to reload plugins, run JavaScript, capture errors, take screenshots, and inspect the DOM. Use when the user asks to interact with their Obsidian vault, manage notes, search vault content, perform vault operations from the command line, or develop and debug Obsidian plugins and themes.

Create and edit Obsidian Flavored Markdown with wikilinks, embeds, callouts, properties, and other Obsidian-specific syntax. Use when working with .md files in Obsidian, or when the user mentions wikilinks, callouts, frontmatter, tags, embeds, or Obsidian notes.

Search, create, and manage notes in the Obsidian vault with wikilinks and index notes. Use when user wants to find, create, or organize notes in Obsidian.

Paste a message that stung; get a calibrated read on whether it's actually critical or neutral-but-terse. Separates evidence from interpretation to counter rejection-sensitive dysphoria. Use when user says "did they mean it that way", "is this criticism", "am I reading this wrong", "rejection check", "this stung", "rsd check", or invokes /rejection-sensitivity-check.

Create a detailed refactor plan with tiny commits via user interview, then file it as a GitHub issue. Use when user wants to plan a refactor, create a refactoring RFC, or break a refactor into safe incremental steps.

Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.

Convert the start-of-sprint canvas into a planning markdown report — sprint goal summary, committed scope, capacity vs commitment (split into carry-over from previous sprint vs new commit), key observations, and risks. Assumes all unclosed items from the previous sprint's end snapshot are carried into this sprint and surfaces them as a dedicated section with WIP-saturation risk. Reuses sprint-snapshot's `_sprint.md`, `_team-rules.md`, current `start.canvas`, and previous sprint's `end.canvas`. Auto-runs a clarity-council session (statistics-expert + scrum-master + product-owner) for the observations/risks block. Output is date-stamped (`sprint-plan-YYYY-MM-DD.md`) — same-day re-runs silently refresh today's file, prior days are preserved as historical record; a `sprint-plan-latest.md` pointer always wikilinks the newest. Use when user says "sprint plan", "sprint planning report", "convert sprint plan to markdown", or invokes /sprint-plan.

End-of-sprint stakeholder report comparing the start.canvas (planning) to end.canvas (sprint close). Produces a markdown report fitting the standard SM template (Scrum Master, Sprint Accomplishments, Feature Demos, Customer Meetings, Status, Sprint Commitment, PI Confidence, Impediments). Applies team-specific overhead, wedge-balancing, and in-review overhead rules. Auto-runs a clarity-council session (statistics-expert + scrum-master + product-owner) for accomplishments/status/impediments synthesis. Use when user says "sprint review", "end of sprint report", "sprint stakeholder report", "sprint close report", or invokes /sprint-review.

End-of-week scrum-of-scrums report comparing two sprint snapshots and surfacing key findings, observations, trouble areas, and trends. Auto-detects which two snapshots to compare (most-recent two by snapshot_at) with `--from`/`--to` overrides for re-planning churn comparisons (e.g. compare `week 1` vs a mid-week `week 1.5`). Applies team-specific overhead, wedge-balancing, and in-review overhead rules from `_team-rules.md`. Auto-runs a clarity-council session (statistics-expert + scrum-master + product-owner). Use when user says "scrum of scrums", "sos report", "weekly sprint report", "sprint progress report", or invokes /sprint-sos-report.