All Skills

Start-of-session routine — load context, check state, suggest next task. Use at the beginning of a fresh session or after a context reset.

Create a committed per-feature spec under `docs/specs/YYYY-MM-DD-<slug>/{spec,tasks}.md` with frontmatter (status, created, owner, pr, tags). Promotes an ephemeral `.claude/plans/<name>.md` into a persistent, searchable artifact. Use when starting a feature that's larger than a one-shot PR.

Track and report token usage and estimated cost per session, agent, and phase

Composite skill — land a safe first PR in an unfamiliar repo without rediscovery loops or guessing at conventions. Chains onboard-new-repo (architecture + scripts + CI scan) → context-pack (relevant files + standards + ADRs for the scoped change) → scope-and-execute (narrow the task) → test-driven-development (write failing test first) → pr-to-release (open the PR). Use the first time you contribute to a repo OR when an unfamiliar contributor needs a guided first change.

Persist decisions, preferences, and project state across sessions using structured memory types

Optimize context window usage — compact stale data, compress via summarization, preserve active state

Sync Claude Code AI tooling (skills, MCP servers, rules) across Warp, Cursor, and VSCode. Idempotent — safe to re-run. Use when onboarding a new editor, after adding MCP servers, or when standards files change.

Deep research on a topic using web search, docs, and codebase analysis

Capture an Architecture Decision Record — what was decided, why, what alternatives were considered, and when to revisit. Writes a numbered ADR file to docs/adr/ in the active repo, with consistent formatting that downstream skills (improve-codebase-architecture, refactor-plan) can read. Use right after deciding something non-obvious so the reasoning isn't lost.

Multiple AI agent sessions working on the same repository cause chaos. Session A is on branch feature/auth. Session B switches to main to check something. Session A's next tool call fails because the branch disappeared. Or worse: Session B force-pushes over Session A's work.

End-to-end performance audit composite — baseline the slow metric, profile to find the real hotspot, implement the smallest targeted fix, re-benchmark to confirm improvement, capture in ADR. Use when users report slowness, CI shows runtime regression, or before a release. Never optimize without profiling first.

Composite skill — configure a fresh or under-configured repo for the release-branch workflow in one pass. Creates the `release` branch on origin, seeds `CHANGELOG.md` (Keep-a-Changelog format), drops in `.claude/dep-sweep-config.json` + `.claude/branch-hygiene-config.json` + a `release-cadence.md` standard stub, opens a `chore/repo-bootstrap` PR to main. Use instead of manually setting these up before the first `/pr-to-release` — without this, none of the release-branch composites can fire. Idempotent: skips any artifact that already exists. Replaces ad-hoc "set up the new repo" scripts.

Evaluate retrieval quality from the local RAG index

Regenerate the cross-repo roadmap aggregate in your Claude memory directory by walking every curated repo's `docs/specs/**` frontmatter. Run at session start for cross-repo orientation or after any `spec-new`/`spec-ship` in any repo.

Audit and prune a bloated test suite down to the minimum tests that hit the coverage threshold and guard real behavior. Replaces many shallow unit tests with fewer well-scoped integration tests. Use when test count is disproportionate to app size.

Run mutation testing against a project's test suite to verify the tests actually catch failures when source code is broken. Use after major test changes, before declaring a suite "good", or when coverage % looks healthy but you suspect tests aren't catching real bugs.

Composite skill — runs the postmortem chain after any production incident (`/hotfix`, rollback, or prod outage acknowledged). Chains adt-research (root-cause learning) → adr-write (decision capture) → generate-tests (regression test) → security-sweep (conditional, only if root cause is auth/input/secret-related) → knowledge-loop (memory + RAG curation) → handoff. Stops the silent-postmortem failure mode where a hotfix ships and the lessons evaporate. Auto-queues after `/hotfix` Phase 10 completes; also fires when user says "postmortem", "what did we learn", "write up the incident".

Decision guide for when to proactively use Claude Code slash commands — /think, /model, /compact, /clear. Use when choosing whether to invoke a command before or during a task, or when a complexity-classifier hook has flagged a task as high or critical. Pairs with the complexity-classifier UserPromptSubmit hook.

Keep sessions focused and efficient — prune stale outputs, preserve active state, recommend compaction

Mega-composite — full greenfield feature development from idea to live. Chains research-and-decide (validate the idea + capture decision) → scope-and-execute (analysis + plan + implement) → design-build (if UI involved) → fix-the-suite (if tests need work) → merge-confidently → ship-it → knowledge-loop. The single command for "build feature X end-to-end."

Daily live-trend scan for any active brand — surfaces timely topics, launches, news, and community pain points in the brand's niche, scored for relevance and timeliness, deduplicated against a rolling log, and written as candidate topics the social calendar can pull.

SEO topic research on fb.ai — find keyword clusters for a topic, deep-analyze their SERPs, and turn the winners into a scheduled content plan. Hands the resulting article briefs to article-publisher. Run on demand.

Structure a hard business decision — frame the choice, score options against weighted criteria, run a pre-mortem and stress-test, and produce a recommendation + decision record for any active brand

Download a video from YouTube, Instagram, TikTok, Twitter/X, Facebook, Vimeo (and 1000+ yt-dlp sites) to local disk, and optionally transcribe it. Standalone utility for repurposing and analysis — not part of the static publishing pipeline.

Daily overdue-invoice chaser. Pulls receivables from Xero, escalates reminder tone over time per the brand's finance playbook, drafts/sends Gmail reminders, tracks chase state in Notion, and posts a daily Slack digest. Runs daily on cron schedule.

Weekly diff of competitor websites, pricing pages, blogs, careers pages, and exec movements. Classifies and scores every change, archives to Notion, alerts Slack on high-signal events. Runs weekly on Monday morning cron schedule.

Write a freelance-marketplace bid for a chosen gig — detects the client's required "secret word", maps the job to a service the brand sells, and drafts a tailored cover letter plus a 60-second VSL (video sales letter) script, written back onto the gig's Notion row. On-demand per gig. The Write phase of the Inbound Gig Engine.

Daily and weekly paid ads analysis — Google Ads, Meta Ads, GA4 funnel analysis with structured JSON email briefs for any active brand

Read, create, inspect, render, and verify PDF files where visual layout matters. Use Poppler rendering plus Python tools such as reportlab, pdfplumber, and pypdf for generation and extraction.

Run a full pipeline for a task. Orchestrates roles through stages (standalone or HOTL-integrated).

Show active or recent Claude Code jobs in this repository, or detailed status for a specific job id. Args: [job-id], --wait, --timeout-ms <ms>, --poll-interval-ms <ms>, --all. Use for tracked-job inspection, not setup or result retrieval.

Use when building Phone.

Discounted cash flow valuation with sensitivity analysis

Read Slack context, route to the right Slack workflow, and prepare or perform Slack writes that match the user's intent.

Use when the user asks Codex to inspect Aient telemetry, search logs, explain traces, create/list Aient API keys, or use the Aient MCP server.

Operate and troubleshoot CircleCI using the CircleCI CLI. Use when users ask to authenticate CLI access, inspect pipeline/workflow/job status, validate configuration locally, rerun pipelines/jobs, trigger pipelines, or gather actionable diagnostics from CLI outputs.