KB: skymirror
← All workspaces4101 results — page 9 of 83
| Title | Domain | Type | Severity | Source | Freshness | Updated |
|---|---|---|---|---|---|---|
| [Tool usage] SKILL: Decision Matrix | claude/commands/SKILL | api_note | medium | SKILL.md | 88 | 2026-03-20 02:00:44 |
|
Body:
| Workspace | Command |
|-----------|---------|
| `/var/www/reportmaker` | `php artisan kb:query "$TOPIC" --limit=5` |
| `/var/www/skymirror` | `php artisan kb:query "$TOPIC" --limit=5` |
| `/var/www/magitek-ops` | `vendor/bin/kb query "$TOPIC" --limit=5 --project-root=$(pwd)` |
| Any other | Check for `artisan`, fall back to `vendor/bin/kb` |
|
||||||
| [Workflow] SKILL: Step 3: Use results as background context | claude/commands/SKILL | pattern | medium | SKILL.md | 88 | 2026-03-20 02:00:44 |
|
Body:
Read the KB output before starting work. This gives you:
- Known gotchas and bugs for this domain
- Relevant expert files to read
- Patterns and lessons from previous work
|
||||||
| [Guardrail] SKILL: Step 2: Run KB query | claude/commands/SKILL | gotcha | critical | SKILL.md | 88 | 2026-03-20 02:00:44 |
|
Body:
```bash
# Non-Laravel workspaces (magitek-ops, or any without artisan):
$PROJECT_ROOT/vendor/bin/kb query "$TOPIC" --limit=5 --project-root="$PROJECT_ROOT"
# Laravel workspaces (reportmaker, skymirror) — free-text search:
php $PROJECT_ROOT/artisan kb:query "$TOPIC" --limit=5
# Laravel workspaces — structured lookup (specific file/domain/masterplan):
# php $PROJECT_ROOT/artisan kb:context domain:$DOMAIN --limit=5
# php $PROJECT_ROOT/artisan kb:context file:$FILE_PATH --limit=5
```
**Workspace...
|
||||||
| [Workflow] SKILL: Step 1: Detect workspace root | claude/commands/SKILL | pattern | medium | SKILL.md | 88 | 2026-03-20 02:00:44 |
|
Body:
```bash
# Use the current working directory as project root
PROJECT_ROOT=$(pwd)
```
|
||||||
| [Workflow] SKILL: At Task Start: Run KB Query | claude/commands/SKILL | pattern | medium | SKILL.md | 88 | 2026-03-20 02:00:44 |
|
Body:
Before starting work, extract the main topic/domain from the task and run a KB search.
|
||||||
| [Workflow] SKILL: Instructions | claude/commands/SKILL | pattern | medium | SKILL.md | 88 | 2026-03-20 02:00:44 |
|
Body:
1. Resolve the project root (the current working directory) and run:
```bash
.claude/switch-mcp.sh css
```
If `.claude/switch-mcp.sh` does not exist in the current project, check `/var/www/reportmaker/.claude/switch-mcp.sh` as fallback.
2. Inform the user that CSS MCP will be enabled on next restart.
3. Ask the user if they want to restart now with `/restart` or `/exit`.
|
||||||
| [Workflow] SKILL: Instructions | claude/commands/SKILL | pattern | medium | SKILL.md | 88 | 2026-03-20 02:00:44 |
|
Body:
1. Resolve the project root (the current working directory) and run:
```bash
.claude/accessibility-disable.sh
```
If `.claude/accessibility-disable.sh` does not exist, use `.claude/switch-mcp.sh none` as fallback.
2. Inform the user that Accessibility Scanner will be disabled on next restart.
3. Ask the user if they want to restart now with `/restart` or `/exit`.
|
||||||
| [Workflow] SKILL: Instructions | claude/commands/SKILL | pattern | medium | SKILL.md | 88 | 2026-03-20 02:00:44 |
|
Body:
1. Resolve the project root (the current working directory) and run:
```bash
.claude/lighthouse-disable.sh
```
If `.claude/lighthouse-disable.sh` does not exist, use `.claude/switch-mcp.sh none` as fallback.
2. Inform the user that Lighthouse will be disabled on next restart.
3. Ask the user if they want to restart now with `/restart` or `/exit`.
|
||||||
| [Workflow] SKILL: Instructions | claude/commands/SKILL | pattern | medium | SKILL.md | 88 | 2026-03-20 02:00:44 |
|
Body:
1. Resolve the project root (the current working directory) and run:
```bash
.claude/switch-mcp.sh accessibility
```
If `.claude/switch-mcp.sh` does not exist in the current project, check `/var/www/reportmaker/.claude/switch-mcp.sh` as fallback.
2. Inform the user that Accessibility Scanner will be enabled on next restart.
3. Ask the user if they want to restart now with `/restart` or `/exit`.
|
||||||
| [Guardrail] SKILL: User Notification (MANDATORY) | claude/commands/SKILL | gotcha | high | SKILL.md | 88 | 2026-03-20 02:00:43 |
|
Body:
After logging, ALWAYS tell the user in your response:
> **MCP-feedback ({server}):** [kort beskrivelse]. GAP-NNN logget. Prioritet: {P}.
Dashboard: https://syncrovanis.magitek.no/gaps
|
||||||
| [Guardrail] SKILL: Third-Party MCP Tool Misuse -> _discovery-logging | claude/commands/SKILL | gotcha | medium | SKILL.md | 88 | 2026-03-20 02:00:43 |
|
Body:
If you discover that you (or another agent) used a **third-party** MCP tool incorrectly
(wrong Serena command, bad Playwright selector, incorrect Context7 query, etc.),
that is an **agent knowledge gap**, not an MCP server gap.
Log it via `_discovery-logging` as a **gotcha** in the relevant workspace's
`coordination/experts/` — so future agents learn the correct usage pattern.
|
||||||
| [Tool usage] SKILL: What NOT to Log | claude/commands/SKILL | api_note | medium | SKILL.md | 88 | 2026-03-20 02:00:43 |
|
Body:
- SSH/bash for things that genuinely belong on the OS level (systemctl, package mgmt)
- One-off operations that will never recur
- MCP already supports it but agent forgot — just use MCP next time
- **Any issue with third-party MCP servers** — we don't own them, don't log them
|
||||||
| [Tool usage] SKILL: Entry Types | claude/commands/SKILL | api_note | medium | SKILL.md | 88 | 2026-03-20 02:00:43 |
|
Body:
- **gap** — MCP server lacks functionality, agent had to use slower method
- **error** — MCP call failed (exception, timeout, wrong response)
- **perf** — MCP worked but was inefficient (many calls for what should be one)
- **ux** — MCP "succeeded" but behaved unexpectedly: confusing response, silent failure, missing context
|
||||||
| [Tool usage] SKILL: How to Log — SQLite via gap-cli.sh | claude/commands/SKILL | api_note | medium | SKILL.md | 88 | 2026-03-20 02:00:43 |
|
Body:
**Step 1: Search for duplicates**
```bash
~/.claude/lib/gap-cli.sh search --workspace mcp-servers --query "short description of issue"
```
**Step 2a: If duplicate found — add occurrence:**
```bash
~/.claude/lib/gap-cli.sh occurrence --workspace mcp-servers --gap-id GAP-NNN --note "Seen again: {context}"
```
**Step 2b: If new — add gap:**
```bash
~/.claude/lib/gap-cli.sh add \
--workspace mcp-servers \
--title "Short title" \
--priority {high|medium|low} \
--component...
|
||||||
| [Tool usage] SKILL: Which MCP Servers? (Custom Only) | claude/commands/SKILL | api_note | medium | SKILL.md | 88 | 2026-03-20 02:00:43 |
|
Body:
| Tool Prefix | MCP Server | Workspace | Server value |
|-------------|------------|-----------|--------------|
| `mcp__reportmaker__` | reportmaker | mcp-servers | reportmaker |
| `mcp__suitecrm__` | suitecrm | mcp-servers | suitecrm |
**DO NOT log feedback for third-party servers:**
`serena`, `playwright`, `mysql`, `lighthouse`, `accessibility`, `xdebug`, `context7`
— we don't build or maintain these. Skip silently.
|
||||||
| [Tool usage] SKILL: When to Trigger (Automatic) | claude/commands/SKILL | api_note | medium | SKILL.md | 88 | 2026-03-20 02:00:43 |
|
Body:
Trigger BEFORE completing a task when ANY agent:
- Used a fallback (SSH, bash, grep, shell, manual workaround) for something a **custom** MCP tool SHOULD support
- Got a failed MCP call (error response, exception, wrong data) from a **custom** server
- Needed multiple MCP calls for something that should be a single operation on a **custom** server
- Used a custom MCP tool incorrectly due to misleading docs/behavior and had to retry
|
||||||
| [Tool usage] SKILL: MCP Feedback Skill — Custom Servers Only | claude/commands/SKILL | api_note | medium | SKILL.md | 88 | 2026-03-20 02:00:43 |
|
Body:
Logs gaps for MCP servers **we build and maintain** to the SQLite GAP tracker.
Third-party MCP servers (Serena, Playwright, MySQL, Context7, etc.) are NOT logged — we can't fix them.
|
||||||
| [Workflow] SKILL: Instructions | claude/commands/SKILL | pattern | medium | SKILL.md | 88 | 2026-03-20 02:00:43 |
|
Body:
1. Resolve the project root (the current working directory) and run:
```bash
.claude/css-disable.sh
```
If `.claude/css-disable.sh` does not exist, use `.claude/switch-mcp.sh none` as fallback.
2. Inform the user that CSS MCP will be disabled on next restart.
3. Ask the user if they want to restart now with `/restart` or `/exit`.
|
||||||
| [Workflow] syncrovanis: VIKTIG: Vent på instruksjon | claude/commands/syncrovanis | pattern | medium | syncrovanis.md | 88 | 2026-03-20 02:00:43 |
|
Body:
**IKKE** begynn å jobbe basert på window-tittelen eller rolle-konteksten alene.
**IKKE** les filer, analyser kode, eller foreslå løsninger ennå.
Rollen er nå satt. Still dette ene spørsmålet og vent:
> **Hva skal vi jobbe med i Syncrovanis?**
Vent på brukerens svar før du gjør noe som helst.
---
You are now the **syncrovanis-specialist**.
Read and follow ALL instructions from `~/.claude/agents/syncrovanis-specialist.md`
|
||||||
| [Workflow] syncrovanis-log: Syncrovanis Log Viewer | claude/commands/syncrovanis-log | pattern | medium | syncrovanis-log.md | 88 | 2026-03-20 02:00:43 |
|
Body:
Vis Syncrovanis onboarding-logger fra gjeldende workspace.
Argumenter: `[session|today|all]` (default: siste 20 entries)
```bash
LOG_FILE="$HOME/.claude/logs/syncrovanis.jsonl"
CTX_DIR="$HOME/.claude/logs/syncrovanis-context"
WS=$(basename "$PWD")
MODE="${1:-recent}"
if [ ! -f "$LOG_FILE" ]; then
echo "Ingen logg funnet: $LOG_FILE"
exit 0
fi
python3 -c "
import json, sys, os, glob
from datetime import datetime
from pathlib import Path
from collections import defaultdict
ws =...
|
||||||
| [Workflow] syncrovanis-audit: ── Parse timestamps ────────────────────────────────────────────────────────── | claude/commands/syncrovanis-audit | pattern | medium | syncrovanis-audit.md | 88 | 2026-03-20 02:00:43 |
|
Body:
def parse_ts(e):
ts = e.get("ts", "")
if not ts:
return None
try:
return datetime.fromisoformat(ts.replace("Z", "+00:00"))
except ValueError:
return None
for e in entries:
e["_dt"] = parse_ts(e)
total = len(entries)
dated = [e for e in entries if e["_dt"]]
dates = sorted(e["_dt"] for e in dated)
date_min = dates[0].strftime("%Y-%m-%d") if dates else "?"
date_max = dates[-1].strftime("%Y-%m-%d") if dates else "?"
# ── Section helpers...
|
||||||
| [Tool usage] solo: How to detect: | claude/commands/solo | api_note | medium | solo.md | 88 | 2026-03-20 02:00:43 |
|
Body:
```bash
if [ -f artisan ]; then
basename "$(pwd)"
elif [ "$(basename $(pwd))" = "syncrovanis" ]; then
echo "syncrovanis"
else
echo "unknown"
fi
```
**After detection:** Load the variant file and follow ALL its instructions. Do NOT use this file for actual work.
|
||||||
| [Tool usage] solo: Workspace Detection (MANDATORY FIRST STEP) | claude/commands/solo | api_note | medium | solo.md | 88 | 2026-03-20 02:00:43 |
|
Body:
```
IF cwd = /var/www/reportmaker (or contains artisan + "reportmaker" in path):
→ Read and follow ALL instructions from ~/.claude/agents/solo-reportmaker.md
ELSE IF cwd = /var/www/skymirror (or contains artisan + "skymirror" in path):
→ Read and follow ALL instructions from ~/.claude/agents/solo-reportmaker.md
(SkyMirror uses same SOLO structure as ReportMaker)
ELSE IF cwd = /var/www/syncrovanis (or contains "syncrovanis" in path):
→ Read and follow ALL instructions from...
|
||||||
| [Workflow] solo: SOLO Mode — Router | claude/commands/solo | pattern | medium | solo.md | 88 | 2026-03-20 02:00:43 |
|
Body:
This command detects your workspace and loads the correct specialized SOLO variant.
|
||||||
| [Tool usage] solo-light: Workspace Detection (MANDATORY FIRST STEP) | claude/commands/solo-light | api_note | medium | solo-light.md | 88 | 2026-03-20 02:00:43 |
|
Body:
```
IF cwd = /var/www/reportmaker (or contains artisan + "reportmaker" in path):
→ Read and follow ALL instructions from ~/.claude/agents/solo-light-reportmaker.md
ELSE IF cwd = /var/www/skymirror (or contains artisan + "skymirror" in path):
→ Read and follow ALL instructions from ~/.claude/agents/solo-light-reportmaker.md
ELSE IF cwd = /var/www/syncrovanis (or contains "syncrovanis" in path):
→ Read and follow ALL instructions from ~/.claude/agents/solo-light-syncrovanis.md
ELSE...
|
||||||
| [Workflow] solo-light: SOLO Light Mode — Router | claude/commands/solo-light | pattern | medium | solo-light.md | 88 | 2026-03-20 02:00:43 |
|
Body:
This command detects your workspace and loads the correct specialized variant.
|
||||||
| [Tool usage] solo-dev-light: Workspace Detection (MANDATORY FIRST STEP) | claude/commands/solo-dev-light | api_note | medium | solo-dev-light.md | 88 | 2026-03-20 02:00:43 |
|
Body:
```
IF cwd = /var/www/reportmaker (or contains artisan + "reportmaker" in path):
→ Read and follow ALL instructions from ~/.claude/agents/solo-dev-light-reportmaker.md
ELSE IF cwd = /var/www/skymirror (or contains artisan + "skymirror" in path):
→ Read and follow ALL instructions from ~/.claude/agents/solo-dev-light-reportmaker.md
ELSE IF cwd = /var/www/syncrovanis (or contains "syncrovanis" in path):
→ Read and follow ALL instructions from...
|
||||||
| [Workflow] solo-dev-light: Developer Light Mode — Router | claude/commands/solo-dev-light | pattern | medium | solo-dev-light.md | 88 | 2026-03-20 02:00:43 |
|
Body:
This command detects your workspace and loads the correct specialized variant.
|
||||||
| [Tool usage] solo-dev-full: Workspace Detection (MANDATORY FIRST STEP) | claude/commands/solo-dev-full | api_note | medium | solo-dev-full.md | 88 | 2026-03-20 02:00:43 |
|
Body:
```
IF cwd = /var/www/reportmaker (or contains artisan + "reportmaker" in path):
→ Read and follow ALL instructions from ~/.claude/agents/solo-dev-full-reportmaker.md
ELSE IF cwd = /var/www/skymirror (or contains artisan + "skymirror" in path):
→ Read and follow ALL instructions from ~/.claude/agents/solo-dev-full-reportmaker.md
ELSE IF cwd = /var/www/syncrovanis (or contains "syncrovanis" in path):
→ Read and follow ALL instructions from...
|
||||||
| [Workflow] solo-dev-full: Developer Full Mode — Router | claude/commands/solo-dev-full | pattern | medium | solo-dev-full.md | 88 | 2026-03-20 02:00:43 |
|
Body:
This command detects your workspace and loads the correct specialized variant.
|
||||||
| [Tool usage] solo-bug-light: Workspace Detection (MANDATORY FIRST STEP) | claude/commands/solo-bug-light | api_note | medium | solo-bug-light.md | 88 | 2026-03-20 02:00:43 |
|
Body:
```
IF cwd = /var/www/reportmaker (or contains artisan + "reportmaker" in path):
→ Read and follow ALL instructions from ~/.claude/agents/solo-bug-light-reportmaker.md
ELSE IF cwd = /var/www/skymirror (or contains artisan + "skymirror" in path):
→ Read and follow ALL instructions from ~/.claude/agents/solo-bug-light-reportmaker.md
ELSE IF cwd = /var/www/syncrovanis (or contains "syncrovanis" in path):
→ Read and follow ALL instructions from...
|
||||||
| [Workflow] solo-bug-light: Troubleshooter Light Mode — Router | claude/commands/solo-bug-light | pattern | medium | solo-bug-light.md | 88 | 2026-03-20 02:00:43 |
|
Body:
This command detects your workspace and loads the correct specialized variant.
|
||||||
| [Tool usage] session-chat-audit: SIKKERHETSREGLER | claude/commands/session-chat-audit | api_note | medium | session-chat-audit.md | 88 | 2026-03-20 02:00:43 |
|
Body:
- Les ALLTID target-filen for du redigerer den
- Bruk Edit-tool, ALDRI Write-tool for eksisterende filer (unntatt nye gaps-filer)
- ALDRI rediger agent-filer, orchestrator-parts, eller Syncrovanis-kode direkte
- ALDRI rediger Syncrovanis Python/template-kode — kun bruk gap_reader API via python3 -c
- ALDRI rediger filer i /var/www/mcp-servers/ utenom via gap_reader API
Returner en kort oppsummering per tier:
TIER 1: {N} items implementert (fil → endring)
TIER 2: {N} items logget (workspace →...
|
||||||
| [Guardrail] session-chat-audit: KLASSIFISERINGSREGLER | claude/commands/session-chat-audit | gotcha | medium | session-chat-audit.md | 88 | 2026-03-20 02:00:43 |
|
Body:
- k-items (expert-fil gotchas) → Tier 1
- u-items som nevner 'knowledge', 'gotcha', 'korreksjon' → Tier 1
- u-items som nevner 'agent-regel', 'hard gate', 'blokkering', 'forby', 'prosess' → Tier 3
- m-items (MCP-usage) → Tier 3
- s-items (Syncrovanis) → Tier 2
- g-items (MCP-selfbuild) → Tier 2
|
||||||
| [Tool usage] session-chat-audit: TIER 3 — Logg til maintenance backlog | claude/commands/session-chat-audit | api_note | medium | session-chat-audit.md | 88 | 2026-03-20 02:00:43 |
|
Body:
For u-items som er agent-regler/prosess, og alle m-items (MCP-usage):
- Append til `coordination/maintenance/BACKLOG.md` i workspace
- Finn neste ledige M-ID: `grep -oP 'M-\K\d+' coordination/maintenance/BACKLOG.md | sort -n | tail -1`
- Format: `- [ ] M-{neste-ID}: [AUDIT-{NNNN}] {beskrivelse} · Prioritet: {pri} · Kilde: {audit-filsti}`
|
||||||
| [Guardrail] session-chat-audit: TIER 2 — Skriv gaps via gap-cli.sh | claude/commands/session-chat-audit | gotcha | high | session-chat-audit.md | 88 | 2026-03-20 02:00:43 |
|
Body:
Bruk ALLTID `gap-cli.sh` — ALDRI inline python3 -c eller SQL mot knowledge.db.
**For HVER s-item (Syncrovanis) og g-item (MCP-selfbuild):**
```bash
# Steg 1: Soek duplikater
~/.claude/lib/gap-cli.sh search --workspace {syncrovanis|mcp-servers} --query "KORT_SOEKEORD"
# Steg 2a: Duplikat funnet — legg til occurrence
~/.claude/lib/gap-cli.sh occurrence --workspace {ws} --gap-id GAP-NNN --note "AUDIT-{NNNN} {s/g-ID}"
# Steg 2b: Nytt funn — legg til gap
~/.claude/lib/gap-cli.sh add \
...
|
||||||
| [Guardrail] session-chat-audit: TIER 1 — Implementer direkte (kun knowledge/gotchas) | claude/commands/session-chat-audit | gotcha | medium | session-chat-audit.md | 88 | 2026-03-20 02:00:43 |
|
Body:
For k-items og knowledge-relaterte u-items:
- Les target-filen forst med Read-tool
- Bruk Edit-tool for a legge til gotcha/korreksjon i riktig seksjon
- ALDRI endre struktur, kun legg til tekst
|
||||||
| [Workflow] session-chat-audit: Deleger implementering til fersk subagent | claude/commands/session-chat-audit | pattern | medium | session-chat-audit.md | 88 | 2026-03-20 02:00:43 |
|
Body:
> **Hvorfor subagent?** Ved slutten av sesjonen har du kontekst-tretthet.
> En fersk Sonnet-agent folger instruksene presist og gjor korrekte edits.
Spawn EN subagent som gjor ALT (tier 1 direkte + tier 2/3 logging):
```
Agent(
subagent_type="generic-light",
model="sonnet",
description="Implement audit findings (3-tier)",
prompt="Du er en implementerings-agent. Gjor ALLE disse endringene basert pa tre-tier-modellen.
AUDIT-RAPPORTER (les disse for full kontekst):
{liste med absolutte...
|
||||||
| [Guardrail] session-chat-audit: Tre-tier implementeringsmodell | claude/commands/session-chat-audit | gotcha | medium | session-chat-audit.md | 88 | 2026-03-20 02:00:43 |
|
Body:
Nar brukeren sier "ja", kjores ALT automatisk uten flere valg:
**Tier 1 — Direkte (trygt):** Knowledge/gotcha-tillegg i ekspert-filer (k-items, u-items som er rene knowledge-oppdateringer).
Disse er trygge fordi de bare legger til tekst i eksisterende seksjoner.
**Tier 2 — Gaps via unified API:** Funn som tilhorer andre systemer logges via `add_gap_multi()`:
- **Syncrovanis (s-items)** → `add_gap_multi(workspace='syncrovanis', ...)`
- **MCP-selfbuild (g-items)** →...
|
||||||
| [Workflow] session-chat-audit: Implementeringsvalg — forenklet | claude/commands/session-chat-audit | pattern | medium | session-chat-audit.md | 88 | 2026-03-20 02:00:43 |
|
Body:
Vis dette etter rapportpresentasjonen:
**Implementer funn? (ja/nei)** Default: ja
- **ja** → Tier 1 implementeres direkte, Tier 2+3 logges til riktige workspaces
- **nei** → Hopp over, ga videre til commit
**Vent pa brukerens svar.**
|
||||||
| [Tool usage] session-chat-audit: Utbedringer | claude/commands/session-chat-audit | api_note | medium | session-chat-audit.md | 88 | 2026-03-20 02:00:43 |
|
Body:
| # | Type | Beskrivelse | Prioritet | Komponent |
|---|------|-------------|-----------|-----------|
| s{N} | ... | ... | ... | L0/L1/L2/L3/KB/state |
---
FORMATERINGSREGLER:
- Bruk ## headers, **bold**, og markdown-tabeller — ALDRI code blocks for presentasjonen
- Prefix items med u1, g1, k1, m1, s1 etc. slik at brukeren kan cherry-picke
- Utelat tomme seksjoner (f.eks. hvis MCP-audit sier 'ingen funn', vis bare en linje)
- Vis oppsummeringen fra rapporten — den er skrevet for mennesker
-...
|
||||||
| [Workflow] session-chat-audit: Falske negativer | claude/commands/session-chat-audit | pattern | medium | session-chat-audit.md | 88 | 2026-03-20 02:00:43 |
|
Body:
| # | Prompt | Hva manglet | Komponent |
|---|--------|-------------|-----------|
| s{N} | ... | ... | L0/L1/L2/L3/KB |
|
||||||
| [Workflow] session-chat-audit: Falske positiver | claude/commands/session-chat-audit | pattern | medium | session-chat-audit.md | 88 | 2026-03-20 02:00:43 |
|
Body:
| # | Prompt | Levert kontekst | Hvorfor irrelevant |
|---|--------|-----------------|-------------------|
| s1 | ... | ... | ... |
|
||||||
| [Workflow] session-chat-audit: Svakheter | claude/commands/session-chat-audit | pattern | medium | session-chat-audit.md | 88 | 2026-03-20 02:00:43 |
|
Body:
{Liste fra rapporten}
|
||||||
| [Workflow] session-chat-audit: Styrker | claude/commands/session-chat-audit | pattern | medium | session-chat-audit.md | 88 | 2026-03-20 02:00:43 |
|
Body:
{Liste fra rapporten}
|
||||||
| [Workflow] session-chat-audit: Syncrovanis Kontekstleveranse — Score {X}/5 | claude/commands/session-chat-audit | pattern | medium | session-chat-audit.md | 88 | 2026-03-20 02:00:43 |
|
Body:
{Kopier sesjonsoversikt og sammendrag fra rapporten}
|
||||||
| [Workflow] session-chat-audit: CLAUDE.md-endringer | claude/commands/session-chat-audit | pattern | medium | session-chat-audit.md | 88 | 2026-03-20 02:00:43 |
|
Body:
| # | Workspace | Endring |
|---|-----------|---------|
| k{N} | ... | ... |
---
|
||||||
| [Workflow] session-chat-audit: Memories | claude/commands/session-chat-audit | pattern | medium | session-chat-audit.md | 88 | 2026-03-20 02:00:43 |
|
Body:
| # | Type | Innhold |
|---|------|---------|
| k{N} | ... | ... |
|
||||||
| [Workflow] session-chat-audit: Ekspertfil-oppdateringer | claude/commands/session-chat-audit | pattern | medium | session-chat-audit.md | 88 | 2026-03-20 02:00:43 |
|
Body:
| # | Expert-fil | Type | Innhold |
|---|-----------|------|---------|
| k1 | ... | ... | ... |
|
||||||
| [Tool usage] session-chat-audit: Tapte muligheter | claude/commands/session-chat-audit | api_note | medium | session-chat-audit.md | 88 | 2026-03-20 02:00:43 |
|
Body:
| # | Situasjon | MCP-server | Tool |
|---|-----------|-----------|------|
| m{N} | ... | ... | ... |
---
|
||||||
Ingestion History
Loading…