一键在 Manus 中运行任何 Skill

inspecting-automation-cycles

星标48

分支3

更新时间2026年7月6日 09:10

TraceDecay Dev: Use when auditing TraceDecay automation loops, skipped runs, memory-curator/session-reflector/skill-writer output, apply policy, or run artifacts.

安装

用 Codex 或 Claude 帮你安装复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。

在 Manus 中运行

来源

ScriptedAlchemy

ScriptedAlchemy/tracedecay

打开 GitHub 仓库查看创作者相关仓库

下载

在 Manus 中运行

TraceDecay Dev: Inspecting Automation Cycles

TraceDecay automation is a loop, not a single artifact: config schedules jobs, runs produce artifacts, dashboards expose outcomes/telemetry, and usage analytics prove whether generated output was adopted.

Workflow

Start with tracedecay automation config get to identify enabled tasks, schedules, locks, profile paths, and apply policy.
List recent runs with tracedecay automation runs list --limit 100; group by task and status before opening individual artifacts.
For failures or suspicious skips, open the relevant artifact with tracedecay_automation_run_artifact_view or tracedecay tool automation_run_artifact_view --args ....
Inspect model-managed memory outcomes plus configured managed-skill review queues: tracedecay automation facts list, dashboard telemetry, and tracedecay_skill_list --state pending.
Check adoption evidence: tracedecay analytics diagnostics --all --no-sync, tracedecay sessions search "mcp__tracedecay" --provider all, and managed skill usage counts.

Reading Results

Signal	Meaning	Next step
`scheduler_interval_not_elapsed`	Healthy throttling	Count only, do not fix.
`scheduler_lock_active`	Another run owns the loop	Check age before calling stale.
`no_new_session_activity`	Nothing new to process	Verify transcript ingest if surprising.
`validation_gate` artifact	Mutation passed validation	Inspect apply-policy state or dashboard artifact.
Many fact proposal records	Inspect validation/apply telemetry	Use `tracedecay:project-memory`.
Active managed skills with zero use	Adoption telemetry gap	Use `tracedecay:diagnosing-analytics`.

Guardrails

Prefer read-only inspection. Do not mutate fact records.
Do not approve, reject, delete, or apply managed-skill drafts unless the user explicitly asked for mutation.
Do not treat skipped runs as failures until grouped by skip reason and age.
Avoid parallel tracedecay_skill_view calls against one profile while automation may write usage ledgers. If a usage read reports a truncated JSON or EOF parse error, retry once after tracedecay_skill_list succeeds.
Do not read .tracedecay databases directly; use CLI, dashboard APIs, or MCP tools.

Deliverable

Report task/status counts, the exact run or artifact ids inspected, apply-policy state, adoption gaps, and the next concrete command for any mutation the user should choose.

同仓库更多 Skills

同仓库

tracedecay

ScriptedAlchemy/tracedecay

Prefer tracedecay tools for codebase exploration, graph queries, and memory recall.

2026-07-1248

dogfooding-tracedecay

ScriptedAlchemy/tracedecay

Use when installing a TraceDecay checkout for live local development, refreshing the globally available binary without a release, or validating agents and the daemon against unmerged TraceDecay changes.

2026-07-1248

dogfooding-tracedecay

ScriptedAlchemy/tracedecay

2026-07-1248

inspecting-managed-skills

ScriptedAlchemy/tracedecay

Use when listing or reading agent-managed automation skills, viewing automation run artifacts, or inspecting skills owned by the standard Hermes user install without mutating them.

2026-07-1048

managing-session-context

ScriptedAlchemy/tracedecay

Use when you need LCM, session search, transcript search, raw past-session replay, scoped/time grep, summary-DAG drill-down, branch/worktree/commit history, workflow recovery, or compaction recovery; and when driving host LCM lifecycle preflight/compress/boundary/repair.

2026-07-1048

editing-safely

ScriptedAlchemy/tracedecay

Use before writing a new function or helper (it may already exist), and before any rename, signature, or field change — the graph lists every call site.

2026-07-1048

name	inspecting-automation-cycles
description	TraceDecay Dev: Use when auditing TraceDecay automation loops, skipped runs, memory-curator/session-reflector/skill-writer output, apply policy, or run artifacts.

TraceDecay Dev: Inspecting Automation Cycles

Workflow

Start with tracedecay automation config get to identify enabled tasks, schedules, locks, profile paths, and apply policy.
List recent runs with tracedecay automation runs list --limit 100; group by task and status before opening individual artifacts.
For failures or suspicious skips, open the relevant artifact with tracedecay_automation_run_artifact_view or tracedecay tool automation_run_artifact_view --args ....
Inspect model-managed memory outcomes plus configured managed-skill review queues: tracedecay automation facts list, dashboard telemetry, and tracedecay_skill_list --state pending.
Check adoption evidence: tracedecay analytics diagnostics --all --no-sync, tracedecay sessions search "mcp__tracedecay" --provider all, and managed skill usage counts.

Reading Results

Signal	Meaning	Next step
`scheduler_interval_not_elapsed`	Healthy throttling	Count only, do not fix.
`scheduler_lock_active`	Another run owns the loop	Check age before calling stale.
`no_new_session_activity`	Nothing new to process	Verify transcript ingest if surprising.
`validation_gate` artifact	Mutation passed validation	Inspect apply-policy state or dashboard artifact.
Many fact proposal records	Inspect validation/apply telemetry	Use `tracedecay:project-memory`.
Active managed skills with zero use	Adoption telemetry gap	Use `tracedecay:diagnosing-analytics`.

Guardrails

Prefer read-only inspection. Do not mutate fact records.
Do not approve, reject, delete, or apply managed-skill drafts unless the user explicitly asked for mutation.
Do not treat skipped runs as failures until grouped by skip reason and age.
Avoid parallel tracedecay_skill_view calls against one profile while automation may write usage ledgers. If a usage read reports a truncated JSON or EOF parse error, retry once after tracedecay_skill_list succeeds.
Do not read .tracedecay databases directly; use CLI, dashboard APIs, or MCP tools.

Deliverable

Report task/status counts, the exact run or artifact ids inspected, apply-policy state, adoption gaps, and the next concrete command for any mutation the user should choose.