agent-teams-command
Use when work has genuinely independent streams or distinct builder, evaluator, domain, and integration roles that require…
Use when planning or closing a daily knowledge-compounding cycle across input, cognition, wiki, behavior, creativity, output, and feedback.
$ npx -y skills add Mark393295827/third-brain-v7-skills --skill daily-okr --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/daily-okrContext preview
The summary Claude sees to decide when to auto-load this skill.
Use when planning or closing a daily knowledge-compounding cycle across input, cognition, wiki, behavior, creativity, output, and feedback.
name: daily-okr description: Use when planning or closing a daily knowledge-compounding cycle across input, cognition, wiki, behavior, creativity, output, and feedback. metadata: version: "8.1.0" updated: "2026-08-18" profile: "stateful" assumes: "A daily note or equivalent state record is writable and the user can choose one priority." conflicts_with: "Invented completion, seven unrelated priorities, or activity counts without evidence."
<skill_contract> <input>Date, one priority objective, available time, active project, current inputs, and prior-day evidence.</input> <output>A seven-KR daily cycle linking input, cognition, wiki, behavior, creativity, output, and feedback.</output> <done>Each claimed KR has a durable receipt, and today's feedback changes one explicit next-day action or knowledge state.</done> <non_goals>Seven unrelated priorities, invented completion, activity counting without evidence, or treating scheduled notes as execution.</non_goals>
Run one daily objective through seven linked Key Results. The cycle compounds only when evidence from today changes tomorrow's behavior or knowledge state.
Provide: date, one objective, available time, active project, knowledge inputs, and yesterday's evidence. Optional: a scheduled knowledge-loop note; treat it as input, not proof of execution.
<intake>
1. Load the current daily state and any scheduled-loop proposal. 2. Choose one objective tied to an active project or explicit learning goal. 3. Set a total time budget and a minimum viable day. 4. Carry forward only unresolved items with an owner or decision value.
</intake>
<unknowns_gate>
If priority, available time, or completion evidence is missing, return `NEEDS_INPUT` with one narrow probe. If the day is constrained, select the minimum cycle rather than fabricating seven completed results.
</unknowns_gate>
<execute>
Create seven causally linked KRs:
1. **Input:** capture one high-value source or observation. 2. **Cognition:** extract one mechanism, contradiction, or decision implication. 3. **Wiki:** write or improve one durable note with provenance. 4. **Behavior:** execute one minimum behavior linked to the objective. 5. **Creativity:** produce one alternative or falsifiable experiment. 6. **Output:** ship one reviewable artifact or project increment. 7. **Feedback:** record evidence, error, and tomorrow's adjustment.
Each KR needs an artifact or receipt. Keep unfinished work visible; do not convert a scheduled trigger into a success claim.
</execute>
<evaluate>
At close, mark each KR `done`, `partial`, `blocked`, or `skipped` from evidence. Check that at least one input became a durable wiki change and one observation changed a future action. Remove vanity metrics and report the bottleneck.
</evaluate>
<state_contract>
Persist `{run_id, status, attempt, budget, evidence, unknowns, last_error, next_action}` plus date, objective, seven KR statuses, artifact links, bottleneck, and tomorrow adjustment. Append receipts; never rewrite historical completion evidence.
</state_contract>
Return `status`, `result` (objective plus seven KR states), `evidence` (artifact links or receipts), `unknowns`, and `next_action` for the next cycle.
</skill_contract>
Verification-first Agent Skills for Codex OS, with optional compatibility adapters for Claude Code, Gemini, Cursor, and Windsurf.
Use when work has genuinely independent streams or distinct builder, evaluator, domain, and integration roles that require…
Use when designing or refactoring a model-native engineering workflow with bounded autonomy, probes, custom evaluation, durable…
Use when property-service operations need an AI plus ontology plus DMAIC design for work orders, dispatch, quotes, evidence, CTQ…
Use when a personal or team operating system needs a bounded redesign using Four-C, closed-loop controls, 70/30 allocation, 3B…
Use when a goal must be converted into a repeatable behavior, cue, SOP, review cadence, and identity-aligned reinforcement.
Use when source material must be transformed into a compact, evidence-aware model for learning, decisions, or an Obsidian concept…