skills

Autopilot brief for a long, unattended Copilot CLI run — draft a sharp `/autopilot` objective (the goal its continuation loop drives toward until the agent calls task_complete) paired with a standing charter re-fed on an `/every` reminder so the run doesn't drift on the how. Use when starting a long autopilot or `/goal` run against a plan doc, when writing or sharpening an autopilot objective, or when keeping an unattended run from drifting over many context compactions.

Fallback for restoring gh CLI authentication inside an agent shell on macOS, and for generating the ~/.ssh/codespaces.auto key gh expects. Use when `gh auth status` reports invalid token, the login keychain isn't visible to the agent process, gh returns a stale token after `gh auth refresh`, or `gh codespace ssh` fails with "Permission denied (publickey)". The preferred fix for the keychain visibility problem is restarting the tmux server under a GUI Terminal session (see remote-agent-stack's tmux-keychain-bootstrap LaunchAgent) — use this skill only when that isn't an option.

Class-level playbook for integrating an app against the GitHub REST + GraphQL APIs — query-complexity ("Resource limits exceeded") fan-out limits, OAuth-App vs GitHub-App scope behavior, read:enterprise / SAML-SSO null-node redaction, pagination correctness, REST rate limits, and turning raw API errors into actionable UX. Use when building or debugging anything that calls api.github.com / api.github.ghe.com (GraphQL or REST), enumerating enterprises/orgs/repos, wiring GitHub sign-in (OAuth App, GitHub App, device-code flow), or seeing GraphQL "Resource limits for this query exceeded", null enterprise/org nodes, or scope/SSO errors.

Compact the current conversation into a structured handoff document for another agent to pick up where this one left off. Use when the user says "hand off to <name>", "do a handoff", "summarize this session for another agent", or wants to pass work to a different Copilot CLI session. If a recipient is named (e.g., "hand off to juliett"), the skill auto-delivers via the mailbox skill after writing the doc.

Preventive playbook for keeping secrets (tokens, API keys, PATs, passwords, private keys, signed URLs, session cookies) out of the chat transcript AND out of git. Covers the "never ask, never echo, never paste" rule for the conversation itself (because chat is sent to the cloud and persisted), plus the pre-commit / pre-push / repo-config layers that stop credentials from reaching GitHub. Use when handling anything credential-shaped — reading a token, configuring a service, writing a script that authenticates, asking the user to authenticate, or about to commit/push code that touches auth.

Autonomous per-session skill reflection — reviews recent work and creates/patches skills WITHOUT asking, mirroring Hermes Agent's background_review.py. Use when invoked by the daily sweep schedule, dispatched as an end-of-task subagent, or when the user says "review for skills" / "learn from this session". Distinct from skill-curator (which consolidates the library on a 7-day cadence); skill-review is the creation/patching loop.

Develop and ship one change at a time through an E2E-first loop — write a durable design doc to the repo's docs/ and rubber-duck it, author deterministic CI guards that encode and enforce the design (drift-proofing future agents), build, then prove it works with a real end-to-end run before review. "Real" scales to the project — a token-burning live model/backend call for agent work, or exercising the running app/UI with screenshot inspection for app and web work. Once it works, run dual-review — handed the full design-and-guard review packet each round, alongside project context (AGENTS.md, README, roadmap) — as its own review-and-fix loop until both reviewers are clean, then one final E2E; only an E2E failure restarts the loop. Use when making essentially any non-trivial code change you intend to ship — the default development loop for app, web, service, agent, pipeline, and SDK work, not just high-risk runtime changes; only docs-only edits and trivial one-liners take the lighter path.

Turn a codebase's prose architecture invariants (constitution/AGENTS.md hard rules, design-spec acceptance criteria, capability matrices) into deterministic, CI-enforced conformance tests — "architecture fitness functions" — so agents can't quietly break global invariants while every local test stays green. Covers the named invariant register, structural (build-time) vs behavioral (runtime) checks, the deterministic-not-LLM enforcement rule, grounding tests in real runtime code, and verifying drift is genuine before flagging it. Use when an agent-written or fast-moving codebase is drifting from its intended architecture, when you want to formalize "the architecture we actually want" and stop regressions in CI, or when reviewing whether a refactor preserved a system's global contracts.

Guardrails for agent-initiated, externally-visible GitHub writes — filing issues, opening pull requests, posting comments, and pushing to repos the user does not own. Use when about to create or mutate anything visible to other people on GitHub (especially upstream/third-party repos), or when an offered menu option bundles such an action.

Run a high-signal dual-reviewer code review (latest Claude Opus + latest GPT in parallel) with structural merge, hallucination guards, and iterate-until-clean loop. Use when reviewing any non-trivial diff where you want two independent senior reviewers before merging.

Explain and ask in plain language for the reader's actual context — no unexplained jargon, no assumption of codebase/internal knowledge, context before the point, and a tighter restatement on request. Use when teaching, walking the user through a system, summarizing work, or asking the user a clarifying question.

Query a local macOS Photos library with osxphotos and import screenshots or image files into a Photos album using the local import helper. Use when you need to read Photos metadata, verify an album exists, or save app-test screenshots into Photos for iPhone/iCloud review.

Audit the GitHub Copilot memory store, roll durable facts into skills, and delete migrated/duplicate memories to cut always-loaded context. Use when curating Copilot memories, when the memory list at github.com/settings/copilot/memory has grown large, when memories duplicate existing skills, or when running the weekly automated memory-curation job.

Hand off a file or message from one Copilot CLI session to another running in a different tmux pane, addressed by tmux session name (e.g., "send this to juliett"). Use when you've produced a deliverable in this session that another named agent should pick up — generated handoff doc, code review output, research summary, screenshot. Durable file queue under ~/.copilot/mailbox/<recipient>/, best-effort tmux send-keys wakeup with verification poll, macOS notification fallback, and a resume-hook for the user's `ca` script. macOS + tmux + the `ca` agent-naming convention required.

Screenshot or click a macOS app that's behind your foreground window without stealing focus, moving the cursor, or interrupting the user. Covers occluded-window screenshots via CGWindowListCreateImage, native-control clicks via Accessibility (AX) and CGEventPostToPid, the briefly-raise-then-restore fallback for WKWebView/Tauri/Electron content, locked/display-state limits, and the honest limits of each. Use when verifying a GUI end-to-end while sharing a Mac with the user.

Read websites that need a login. Use when a URL is behind SSO/MFA/auth that the agent can't do itself — internal repos, wikis, dashboards, vendor portals. User logs in once, agent browses after.

Create a new personal skill in dfrysinger/skills, enforcing HARDLINE authoring standards (frontmatter, naming, structure, size caps). Use when the user says "make this a skill", "create a skill for X", or when an agent recognizes a reusable procedure worth saving (per the auto-create trigger in copilot-instructions.md). For modifying an existing skill, use /skill-manage instead.

Periodic self-learning curator that reviews dfrysinger/skills, consolidates narrow siblings into umbrella skills, and archives unused ones. Default dry-run. Use when invoked by the weekly schedule, when the user says "curate skills" / "clean up skills" / "skill cleanup", or as the first step after noticing many narrow agent-created skills.

Patch, archive, restore, pin, or extend an existing personal skill in dfrysinger/skills. Use when the user wants to modify a skill, when skill-curator proposes a consolidation, or when a skill needs a new supporting file. For brand-new skills use skill-create instead.

Recover lost or displaced Git work after accidental reset, checkout, rebase, stash, or branch mistakes by using reflog, dangling commits, and targeted restore. Use when uncommitted or recently committed changes appear lost and the goal is safe recovery without rewriting unrelated history.