convergence-monitoring
SolidMonitor iterative improvement loops for convergence. Three signals — shrinking diff, pass-rate plateau, velocity — drive a Stop/Continue/Investigate decision at each inter-wave checkpoint. Distinct from /evolve (retrospective) and session-reviewer (wave output review): convergence-monitoring answers "are we making progress?" not "was the last wave correct?". Primary consumer: /autoresearch loops and wave-executor inter-wave checkpoints.
Install
Quality Score: 90/100
Skill Content
Details
- Author
- Kanevry
- Repository
- Kanevry/session-orchestrator
- Created
- 1 months ago
- Last Updated
- yesterday
- Language
- JavaScript
- License
- MIT
Integrates with
Similar Skills
Semantically similar based on skill content — not just same category
converge-control
Operate a Converge playbook end-to-end — start runs, monitor progress, narrow failures with `--select`, inspect runtime state, validate definitions, surgically reset subtrees, and stop stuck or orphaned runs. Use this skill whenever the user says "run my playbook", "execute this", "monitor the run", "converge failed", "the run is stuck", "retry failures", "babysit this playbook", "what's the status?", "show me the gantt", or asks how to use `converge run` / `--select` / `inspect` / `doctor` / `clean` / `stop`. Also use it for `HTTP 401` / `Invalid API key` failures on the first task — those are environment-not-playbook problems — and for any post-run cleanup work. Hand off to `converge-planning` if the user wants to design or restructure the playbook itself.
skill-monitor
Analyze skill effectiveness across sessions. Computes per-skill metrics (action rate, friction, outcomes), identifies degrading skills, and generates improvement recommendations. Requires session-scan data in metrics.jsonl.
converge-development
Use when the user wants to develop, debug, or improve the converge framework itself — running an example as a test bed, running the self-improvement loop, observing framework behavior, diagnosing framework bugs, and editing source under packages/. Triggers on phrases like "debug converge", "fix the framework", "run the self-improvement loop", "autonomous framework improvement", "why does the runner do X", "improve the journal", "add a feature to the CLI", "use this example to find bugs in converge".
converge-planning
Design a Converge playbook end-to-end: extract the goal, gather requirements, decompose it into deliverable tasks, decide what's a static child vs. a dynamically spawned template, factor reusable "how-to" into skills, and write the TASK.md + playbook.yml contracts with deterministic shell-level checks. Use this skill whenever the user says "plan a project", "design a playbook", "decompose this goal into tasks", "scaffold a Converge workflow", "onboard this codebase to Converge", "restructure work into a playbook", or asks how to author TASK.md / playbook.yml / SKILL.md files. Also use it before invoking `converge add` or `/converge-control` when no playbook exists yet — planning is the prerequisite for execution.
convergence-loop
A universal gate-reinforcement meta-skill that replaces the "single-pass = done" pattern with a converging loop of up to N rounds. Can be applied to any gate, checkpoint, or verification step. Only declares "truly passed" after FAIL→FIX→re-verify repeats until convergence (all items pass). Escalates to structural redesign if not converged within N rounds. Triggers on: "convergence-loop", "how many rounds do we need", "suspicious of single-pass", "not sure if it really passed", or equivalent phrasing.