petekp/resume-orientation
skills/claude-code-audit-workspace/iteration-1/eval-1-direct-audit-request/with_skill/outputs/audit/drafts/skills/resume-orientation/SKILL.md
Render a 4-line human orientation card (Goal / Last commit / Next / Blocker) as the FIRST visible assistant output on any resumed session. Fires when the first user prompt is "resume", "resume handoff", "continue from handoff", or any /circuit:handoff resume invocation. Exists because the continuity system stores state perfectly for machines but leaves the human disoriented after breaks — at least two 2026-04 sessions ended with the user explicitly saying "I've forgotten what we're doing". The card is mandatory, precedes any tool use, and never exceeds 4 lines.
$ install --global
skillsauthnpx skillsauth add petekp/claude-skills resume-orientationInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 29, 2026, 9:43 AM89.7s1 file scanned
SKILL.md
- name:
- resume-orientation
- description:
- Render a 4-line human orientation card (Goal / Last commit / Next / Blocker) as the FIRST visible assistant output on any resumed session. Fires when the first user prompt is "resume", "resume handoff", "continue from handoff", or any /circuit:handoff resume invocation. Exists because the continuity system stores state perfectly for machines but leaves the human disoriented after breaks — at least two 2026-04 sessions ended with the user explicitly saying "I've forgotten what we're doing". The card is mandatory, precedes any tool use, and never exceeds 4 lines.
Resume Orientation
Why this skill exists
Your /circuit:handoff system stores every fact the machine needs to resume. It does not re-orient the human operator. The audit found 14% of sessions start with "resume" and 8% of those end with the user explicitly saying they've lost track of what's happening.
This skill enforces a tiny, non-negotiable behavior: on resume, the FIRST visible assistant text is a 4-line card, delivered before any tool use.
When this skill fires
Trigger on any of these first-user-prompt patterns (case-insensitive):
- Starts with
resume,resume handoff,continue from handoff - Contains
/circuit:handoff resumeinvocation - Contains
resume. i confirm and sign off on the plan. - Any
/circuit:handoffinvocation withARGUMENTS: resume
Do NOT fire for mid-session "resume" where the user is continuing work mid-turn.
The card format
Exactly 4 lines. No preamble. No "Welcome back!" No emojis. Deliver before any tool use.
Goal: <one line pulled from continuity record's narrative.goal>
Last commit: <short sha> — <subject line from git log>
Next: <first concrete action from record.next or continuity payload>
Blocker: <none | one-line blocker if any exists in debt_markdown>
If a field is unavailable in the continuity record, fill with <unknown> and continue. Do NOT skip the card to "look things up first" — look things up AFTER delivering the card.
Implementation contract
- Read
.circuit/control-plane/continuity-records/continuity-*.json(most recent) via Bash. - Read git log for the last commit sha + subject (cheap:
git log -1 --oneline). - Render the 4-line card. Emit as plain text. Nothing else in that first turn's preamble.
- Then proceed with whatever /circuit:handoff resume would have done normally — bootstrap the run, set up the working tree, etc.
Example
User: resume
Assistant (first visible output):
Goal: Slice 64 methodology-trim-arc CHEAP-TRIM — awaiting Codex challenger pass on §2.1 plan-lint rule #23
Last commit: fa96a0b — slice-64: methodology-trim-arc CHEAP-TRIM
Next: dispatch Codex cross-model challenger review per Hard Invariant #6
Blocker: none
Then Claude proceeds with the resume workflow. The user has oriented themselves in the ~3 seconds it took to read those 4 lines.
Anti-patterns
- Don't expand the card "just this once" because the state is unusual. 4 lines is the contract. If it doesn't fit in 4 lines, the continuity record is the problem — surface it in
Blocker:and fix the record separately. - Don't narrate what you're about to do in the card. It's a state briefing, not an agenda.
- Don't emit tool calls before the card. The whole point is the human sees orientation before watching Claude work.
Related Skills
petekp/circuit-surface-test
tools
VerifiedTrustedCommunity
Comprehensively manually test the Circuit plugin's user-facing surface in either Claude Code or Codex. Use this skill whenever the user asks to "manually test Circuit", "QA the Circuit plugin", "exercise the Circuit surface", "run the Circuit checklist", "smoke test Circuit", "find regressions in Circuit", "test the Claude Circuit plugin", "test the Codex Circuit plugin", or when preparing a Circuit release for marketplace publication. Argument is the host package to test — `claude` or `codex`. Produces a Markdown report with per-command pass/fail, exploratory findings ranked by severity, run-folder evidence links, and a concise terminal summary. Use even if the user does not say the word "test" — phrases like "go through every Circuit command" or "make sure Circuit still works end-to-end" should also trigger.
38SKILL.mdUpdated May 20, 2026
petekp/write-goal
development
VerifiedTrustedCommunity
Turn the prompt supplied with this skill into a concise, auditable Codex Goal or explain why a Goal is not the right fit. Use when the user asks to draft, formulate, rewrite, tighten, or create a `/goal` from a plain-language task, especially for multi-step work that needs a durable objective, evidence-based completion, constraints, iteration policy, and a default adversarial review loop.
37SKILL.mdUpdated May 31, 2026
petekp/catch-up
development
VerifiedTrustedCommunity
Give the human a fast, plain-English catch-up on what changed in the project: what the agents did, why, and what decisions need their input. Use this whenever the user asks to "catch me up", "what changed", "where are we", "recap", "brief me", "give me the rundown", "what did you do", "summarize the session", "fill me in", or otherwise signals they have been away and want to get back up to speed quickly. Built for someone steering several agent-driven projects at once who does not read the code closely but needs to grasp the core ideas, the choices made, and the open decisions well enough to steer. Trigger even if they do not use these exact words: any request to get oriented on recent progress should use this skill.
37SKILL.mdUpdated May 31, 2026
petekp/unix-macos-engineer
tools
VerifiedTrustedCommunity
Expert Unix and macOS systems engineer for shell scripting, system administration, command-line tools, launchd, Homebrew, networking, and low-level system tasks. Use when the user asks about Unix commands, shell scripts, macOS system configuration, process management, or troubleshooting system issues.
35SKILL.mdUpdated Apr 29, 2026