periodic-retreat
Skill1 starsChanged 18 days agoMITView on GitHub
Quarterly personal and project strategic retreat facilitator. Conducts multi-scale deep audits of project health, architecture debt, dead-code purges via automated scan, founder vitality & purpose alignment, and binary next-quarter OKRs with Monday launchpads across the agency ecosystem. Generates quarterly-retreat.md.
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 4 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 38
Every invocation resolves to exactly one mode.
- Distinctive: line 57
Do NOT use this skill when:
- Very specific: line 97
Run git churn heatmap to detect god-file hotspots: git log --since="90 days ago" --name-only --format="" | sort | uniq -c | sort -nr | head …
- Very specific: line 105
Automated Sweep: Run AST dead-code detector (knip or unused export scan) to surface 0-reference files, unused types, and dead assets.
- Distinctive: line 107
Purge Register: Document all deleted files and net line savings in the Purge Register table.
- Distinctive: line 135
Before concluding the retreat:
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
🏔️ Periodic Retreat — Quarterly Strategic Review & Architecture Purge
Facilitates a structured, multi-scale quarterly strategic retreat for developers, architects, and agency principals. Audits project vitality, systematically identifies and purges architectural debt, evaluates alignment against TELOS and the Wheel of Life, and crafts high-leverage OKRs for the upcoming quarter.
Modes
Every invocation resolves to exactly one mode. Load only the matched reference:
| Mode | Trigger phrases | Behavior | Reference |
retreat-framework | "periodic-retreat retreat-framework", "retreat-framework" | Quarterly Retreat Framework Reference | references/retreat-framework.md |
retreat-protocol | "periodic-retreat retreat-protocol", "retreat-protocol" | Strategic Retreat Facilitation & Debt Purge Protocol | references/retreat-protocol.md |
audit | "periodic-retreat audit", "retreat readiness audit", "audit project health", "decision verification audit" | Verify the evidence a retreat will deliberate on is current; verify past decisions shipped artifacts; score health signals | references/audit.md |
When to Use
Trigger Conditions
Execute this skill when:
- Quarterly / Milestone Transition: Ending Q1/Q2/Q3/Q4 or wrapping up a major agency project milestone.
- Architecture Debt Accumulation: Subsystems have become bloated with legacy shims, unused dependencies, or obsolete documentation.
- Strategic Re-alignment: Re-evaluating current operating state against the principal's ideal TELOS state.
- Deprecation & Purge Cycles: Systematically sunsetting zombie repos, dead configs, or outdated agent rules.
- Wisdom Compounding & Retrospective Synthesis: Synthesizing milestone learnings into durable Muse Memory wiki frames (
~/.memory/wiki/) and active constraints in~/.memory/USER.md(bun skills/reflection-maintenance/periodic-retreat/scripts/wisdom-updater.ts --synthesize).
Anti-Triggers
Do NOT use this skill when:
- Conducting daily or weekly standup reflections (use
coach). - Debugging a localized performance bottleneck or test failure.
Quick Reference
The 4 Retreat Phases
┌─────────────────────────┐ ┌─────────────────────────┐
│ Phase 1: Retrospective │ ──▶ │ Phase 2: Debt Purge │
│ Truth-telling audit, │ │ Automated knip scan & │
│ wins, stalls, churn map │ │ zombie dependency purge │
└─────────────────────────┘ └─────────────────────────┘
│
▼
┌─────────────────────────┐ ┌─────────────────────────┐
│ Phase 4: Monday OKRs │ ◀── │ Phase 3: Vitality Sync │
│ 3 binary OKRs & Week 1 │ │ Founder energy, ADE │
│ sprint launchpad │ │ framework & boundaries │
└─────────────────────────┘ └─────────────────────────┘Retreat Deliverable Sections
- Retrospective Scorecard: Quantitative review of prior quarter commitments + git churn heatmap.
- The Purge Register: List of deleted files, removed dependencies, and deprecated scripts.
- Founder Vitality & Purpose Audit: Energy drain audit, ADE triage (Automate/Delegate/Eliminate), and bandwidth boundaries.
- Next-Quarter Binary OKRs: 3 Objectives with 3 verifiable Key Results each + Monday Launchpad sprint tickets.
Procedure
Load and follow references/retreat-protocol.md during facilitation:
Step 1 — Retrospective Audit (Look Back & Churn Map)
- Ingest previous quarter's roadmap, commits, and project files.
- Run git churn heatmap to detect god-file hotspots:
git log --since="90 days ago" --name-only --format="" | sort | uniq -c | sort -nr | head -n 10 - Answer bluntly:
- What shipped to production and generated real value?
- What languished in draft/stall state for $\ge 30$ days and why?
- Which assumptions proved flat wrong?
Step 2 — Architecture & Codebase Debt Purge
- Automated Sweep: Run AST dead-code detector (
knipor unused export scan) to surface 0-reference files, unused types, and dead assets. - Zombie Eviction: Cross-reference
package.jsonagainst repo imports; remove unimported packages. - Purge Register: Document all deleted files and net line savings in the Purge Register table. A retreat cannot conclude without code deletion or documented deprecation PR.
Step 3 — Founder Vitality & Purpose Alignment
- Conduct Energy Drain Audit: Identify the top 3 recurring operational frictions draining cognitive bandwidth.
- Apply the ADE Framework: Automate with subagents, Delegate to agency Council Leads (Sol, Jasper, Crew, Nexus), or Eliminate low-margin offerings.
- Lock deep-work boundaries: Ensure minimum 20% reserved for architecture breakthroughs.
Step 4 — Next-Quarter Binary OKRs & Monday Launchpad
- Define Objective 1 (Product/Revenue), Objective 2 (Architecture/Hardening), and Objective 3 (Ecosystem/Capabilities).
- Enforce the Binary Key Result Contract: Every result must have an executable CLI verification command (e.g.
bun test,bun run lint). - Generate the Monday Launchpad Packet: 3 pre-scoped Week 1 sprint tickets with assigned Council Leads.
Step 5 — Emit Retreat Artifact (quarterly-retreat.md)
Save the structured strategic retreat summary into project docs or .memory/retreats/quarterly-retreat-<timestamp>.md.
Pitfalls
- Passive Planning: Writing aspirational goals ("improve UI speed") instead of concrete criteria ("achieve 99/100 Lighthouse score on /pricing").
- Skipping the Purge: Accumulating new features without deleting obsolete code leads to cognitive decay.
- Overcommitting: Assigning more than 3 core objectives for a single quarter.
- Monday Morning Inertia: Leaving the retreat with great philosophy but no concrete tickets for Monday morning.
Verification
Before concluding the retreat:
- Git churn heatmap generated and reviewed for modular decoupling.
- All legacy or zombie modules targeted for deprecation have explicit deletion actions in the Purge Register.
- Founder Vitality Audit completed with ADE (Automate/Delegate/Eliminate) assignments.
- Next-quarter OKRs contain exactly 3 objectives with binary, CLI-testable Key Results.
- Monday Launchpad packet contains 3 ready-to-run sprint tickets with assigned Council Leads.
quarterly-retreat.mdis persisted with timestamped sign-off.
In this repository49 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- llms.txtllms.txt
- accountsSkill
- analyticsSkill
- automationSkill
- brandSkill
- client-commsSkill
- contentSkill
- crmSkill
- databaseSkill
- designSkill
- devopsSkill
- growthSkill
- gtmSkill
- incident-responseSkill
- mobileSkill
- opsSkill
- paidadsSkill
- qa-launchSkill
- researchSkill
- retainSkill
- sales-enablementSkill
- seoSkill
- smmSkill
- telegramSkill
- webdevSkill
- context-anchorSkill
- coupling-routerSkill
- evidence-ledgerSkill
- relaySkill
- secretarySkill
- gitSkill
- new-projectSkill
- updateagentsSkill
- updatedocsSkill
- animateSkill
- designscopeSkill
- refactorSkill
- auditSkill
- code-reviewSkill
- dead-letterSkill
- gauntlet-loopSkill
- humanizeSkill
- muse-securitySkill
- puaSkill
- clean-system-cacheSkill
- coachSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

