Explore AI Agent Skills & Claude Prompts

Performs maintenance reflection: curates memory (reasoning-bank entries, tree nodes, pattern signatures), applies active forgetting to low-utility items, grooms aspirations, and detects stuck goals that may need unblock conversion or archival. Use whenever the loop hits the maintenance cadence, the reasoning bank exceeds healthy size, the knowledge tree accumulates low-confidence nodes, or goals have stalled without progress. Invoked via /reflect --curate-memory or /reflect --curate-aspirations.

aspirations-all-blocked

Handles the all-goals-blocked state inside the aspirations loop (phases B0-B7): scans the coordination board, generates constraint-aware aspirations, runs the idle playbook, triggers evolution, kicks off research, performs reflection, and applies exponential backoff. Use whenever the goal selector returns zero executable goals AND selection_reason starts with "all_blocked" — the orchestrator invokes this automatically. Internal-only sub-skill of /aspirations; not user-invocable.

reflect-on-self

Runs deep self-model reflection: synthesizes patterns across recent outcomes, extracts strategies into the archive, updates the Level 2 self-model, and calibrates confidence scores. Use whenever the loop hits the self-reflection cadence, sq-012 fires ("does this outcome change my core purpose?"), cumulative learning warrants rewriting self.md, or /reflect dispatches with --extract-patterns / --calibration-check. Produces self-model updates, not outcome-level insights.

aspirations-complete-review

Reviews aspirations approaching completion: sweeps remaining goals for outstanding work, checks motivation fulfillment, runs the maturity gate (Phase 7.4 intent satisfaction), decides archival or continuation, and creates replacement aspirations. Use whenever an aspiration reaches high completion_ratio, the zombie scan (aspirations-precheck Phase 0.5.0a) surfaces high-completion-stale-blocked aspirations, or an aspiration's last executable goal finishes.

priority-review

Shows the priority dashboard (all active aspirations ranked by aggregate goal score) and lets the user interactively reorder priorities to update the aspiration queue. Use whenever the user says "what are you working on next", "re-rank my priorities", "show me the priority dashboard", "show the queue", or invokes /priority-review directly. Closes the feedback loop between autonomous goal selection and user strategic direction. Valid in any mode including reader.

aspirations-precheck

Runs pre-selection checks at the start of every aspirations-loop iteration: completion runners, aspiration health, guardrail checks, blocker resolution re-probe, zombie-aspiration scan (Phase 0.5.0a), and recurring-goal surfacing. Use whenever the aspirations loop starts a new iteration and needs to tidy state before /aspirations-select runs. Internal sub-skill — invoked only from inside the orchestrator, never by the user.

schedule Updated 22 days ago

aspirations-graceful-stop

Handles the graceful-stop path for the aspirations loop: recovers in-flight iteration checkpoints, completes pending verify/state-update obligations, and runs the deferred stop sequence D1-D7. Use whenever {agent}/session/stop-requested is detected at Phase -1.4 of the aspirations loop, or the loop needs to exit cleanly without dropping in-flight work. Internal handler — only /aspirations invokes it; the user-facing /stop command writes stop-requested which this handler then reads.

schedule Updated 22 days ago

aspirations-verify

Phase 5 of the aspirations loop: verifies a just-executed goal using hypothesis outcomes, unified outcome/check evaluation, Q1/Q2/Q3 verification escalation, streak tracking, and dependent-goal unblocking. Use whenever /aspirations-execute finishes and the loop must confirm the goal actually met its verification criteria before state-update fires. Internal sub-skill — never invoke outside the aspirations loop; assumes the just-executed goal is still in working context.

review-hypotheses

Resolves open hypotheses whose horizons have elapsed, extracts lessons from each outcome, calculates per-category accuracy stats, and generates a calibration report. Use whenever the aspirations loop hits the hypothesis-review cadence, the user says "how accurate are my predictions" or "review my hypotheses", or enough hypotheses have reached their horizon to warrant a batch resolve. Modes: --resolve, --learn, --accuracy-report, --full-cycle, --category-comparison.

reflect

Orchestrates Reflexion-based learning: dispatches to /reflect-on-outcome (hypothesis ABC chains, execution patterns, batch micro-hypotheses), /reflect-on-self (pattern synthesis, Level 2 self-model, calibration), or /reflect-maintain (memory curation, active forgetting, aspiration grooming) based on --mode. Use whenever the aspirations loop hits a reflection cadence, a hypothesis resolves, the user asks to "reflect on recent work", or after major outcomes that warrant pattern extraction.

verify-learning-staleness

Scans verify-learning/SKILL.md for stale Check:/Bash: assertions whose targets (paths, phase headers, grep patterns) no longer exist in the codebase. Four lanes: L1 path references, L2 Phase/Step references inside SKILL.md targets, L3 grep-target patterns, L3b `Grep Phase X for `pattern`` variant. Skips negative assertions ("MUST NOT exist", "test ! -f", "absent") and external paths (meta/, world/). Use whenever the agent suspects verification-checklist drift — after major SKILL.md refactors, after extracting inline pseudocode into scripts, after renaming phases, OR via the recurring goal under asp-115 (g-115-219) that fires weekly. Sister to felt-sense-checkin Phase 5b (which calls the same scanner at 75-goal cadence) — this skill is the on-demand entry point.

aspirations-learning-gate

Enforces learning obligations inside the aspirations loop: the learning gate, retrieval gate, meta-learning signal, periodic reflection cadence, conclusion audit, and batch reflection. Use whenever a goal completes and the loop must verify that encoding, retrieval, and reflection actually happened before moving to the next goal. Catches sessions that ship commits without producing tree encodings or hypothesis resolutions. Internal sub-skill — never invoke directly.