메뉴
Use this skill when bootstrapping memory in a freshly cloned repo or when upgrading from a pre-memory plugin version — to initialize the .ai-skills-memory/ skeleton in the current project (directory structure, .gitignore rules, learnings.md template, .committed/ allowlist). Idempotent — safe to re-run on a project that already has memory wired.
Use this skill when bootstrapping scheduled knowledge-base sync for a repo that has no knowledge/.knowledge-sync.yml yet — to run one-time setup that detects the knowledge_root from CLAUDE.md/AGENTS.md, maps doc areas to source globs, records opt-in external sources (Linear/Notion/WebFetch, all disabled by default), captures a baseline last_scanned_sha, sets the per-area update policy, generates or seeds knowledge/CONVENTIONS.md, provisions the L4 memory dir, and offers to register the daily routine. Routes ongoing recurring sync operations to /knowledge-sync.
Use this skill when running the recurring (daily) knowledge-base rescan for a repo that already has knowledge/.knowledge-sync.yml — the main-thread dispatcher that reads the config, computes the git delta since last_scanned_sha, maps changed paths to affected doc areas, early-exits cheaply when nothing changed, then fans out one Agent(content-writer) per affected area, applies the propose/direct update policy, advances the baseline only on success, and writes an L4 run log — all with the G1 untrusted-content choke-point, secret-scan, deny-list, and budget controls woven in. For first-time setup use /knowledge-sync-init.
Use this skill when reviewing how the plugin behaved across recent runs, after a release to confirm reliability, before filing a plugin bug report, or when planning the next plugin improvement cycle — to collect and analyze past Claude Code session logs for the ai-skills plugin and surface agent, subagent, skill, command, and hook errors, timeouts, unexpected exits, and other anomalies that point at plugin defects. Defaults to the last 7 days of sessions for the current project. Produces an extended Markdown report on disk plus a brief on-screen summary.
Use this skill when bootstrapping a target repository to be ai-skills-aware — on the first run of any ai-skills workflow in a fresh repo, when adopting the ai-skills plugin in an existing repo, or after upgrading to a plugin version that adds new memory paths or templates, including when the user does not say "init" but asks to "set up" or "onboard" the repo — to detect codebase type, create CLAUDE.md + AGENTS.md scaffolding, initialize the .ai-skills-memory/ directory tree from L1 templates, and configure .gitignore. Idempotent — safe to re-run. Accepts `--codebase-type <type>` and `--overwrite`. Not for re-initializing only memory — use `/memory-init` instead.
Use this skill when a local container won't start, a service is unreachable from the host, a local docker-compose stack is misbehaving, or as the Docker-layer diagnosis step of a local bugfix flow — including when the user describes the symptom without naming Docker — to run a Docker-specific local diagnostic that collects container status, logs, networking, and resource usage and diagnoses issues, applying the SRE or DevOps role for investigation. For multi-scope environment analysis (Docker + Kubernetes + CI runner + drift snapshot + optional auto-fix) use `/env-analyze` instead.
Use this skill when investigating a production incident, when an alert fires (latency spike, error rate, pod crashloop), when a customer-reported issue needs prod telemetry, or as the diagnosis step of an incident-response or production-bugfix flow — including when the user describes a prod symptom without asking to "analyze" — to analyze the production environment by collecting Kubernetes pod status, managed database health, logs, metrics, and networking and diagnosing issues, supporting GCP, Azure, and AWS via the `cloud-platforms` skill and applying the SRE or DevOps role.
| name | memory-init |
| description | Use this skill when bootstrapping memory in a freshly cloned repo or when upgrading from a pre-memory plugin version — to initialize the .ai-skills-memory/ skeleton in the current project (directory structure, .gitignore rules, learnings.md template, .committed/ allowlist). Idempotent — safe to re-run on a project that already has memory wired. |
| context | fork |
| argument-hint |
Create the .ai-skills-memory/ directory tree from plugin/memory/templates/. Idempotent. Layer model and write rules: plugin/docs/concepts/memory.md.
.ai-skills-memory/ (first run on a fresh checkout)/plugin-doctor reports "no memory tree present"Not needed when running /ai-skills-init — that workflow runs memory-init as one of its steps.
<repo> = the cwd where the user runs the command)..ai-skills-memory/:
<repo>/.ai-skills-memory/
├── .gitignore (from plugin/memory/templates/ai-skills-memory.gitignore)
├── learnings.md (empty header template)
├── runs.jsonl (touch-create, append-only)
├── errors.log (touch-create, append-only)
├── redactions.log (touch-create, append-only)
├── sessions/ (per-session subdirs created by hooks)
├── ralph/ (per-RALF-run subdirs)
├── pending-flush/ (PreCompact flush markers)
├── designs/ (/feature-design output summaries)
├── env-reports/ (/env-analyze baselines)
├── refactor/ (/refactor logs)
├── migrate/ (/migrate plans)
├── spikes/ (/spike reports)
├── security-audits/ (/security-audit findings)
├── docs/ (/docs-pack generation summaries)
├── knowledge-sync/ (/knowledge-sync per-run logs + run-lock)
└── .committed/
├── README.md (from plugin/memory/templates/committed-readme.md)
├── .allowlist-extensions.txt (project-extension allowlist, empty by default)
├── conventions.md (from plugin/memory/templates/conventions-schema.md, empty body)
└── learnings.md (committed-learnings template, empty body)
.ai-skills-memory/ rule to <repo>/.gitignore if not already present..committed/ paths outside the allowlist — pre-tool-use-committed-write.py hook enforces this; the skill must not bypass.memory-discipline.md rule 2.cd to a writable directory or run with elevated permissions..ai-skills-memory/ corrupted (bad JSON, bad allowlist): flag corrupted files but do not delete or rewrite them. Suggest user inspect and back up before re-running.| Layer | When | Shape |
|---|---|---|
| L4 | On first init | .ai-skills-memory/init-summary.md — timestamp + version + paths created |
${CLAUDE_PLUGIN_ROOT}/memory/templates/ (7 files: ai-skills-memory.gitignore, committed-allowlist.txt, committed-readme.md, conventions-schema.md, eval-baseline.schema.json, learnings-schema.md, untrusted-content-wrapper.md). PII pattern file lives separately at ${CLAUDE_PLUGIN_ROOT}/hooks/scripts/pii-patterns.txt because the secret-scan + memory-curator hooks load it directly./ai-skills-init (full bootstrap including memory), used standalone for upgradesmemory-discipline (write rules per layer), memory-validation (entry validation)pre-tool-use-committed-write.py validates .committed/ writes against allowlistplugin/docs/concepts/memory.md documents the L0–L5 layers. This skill creates L3 dirs (sessions/, ralph/) and L4 files (learnings.md, runs.jsonl, etc.) inside .ai-skills-memory/.