gitlab-discussion
GitLab discussion operations via API. ALWAYS use this skill when user wants to: (1) view threaded discussions on MRs/issues, (2) create new discussion threads, (3) reply to discussions, (4) resolve/unresolve discussions.
What this skill does
# Discussion Skill
Threaded discussion management for GitLab using `glab api` raw endpoint calls.
## Quick Reference
| Operation | Command Pattern | Risk |
|-----------|-----------------|:----:|
| List MR discussions | `glab api projects/:id/merge_requests/:iid/discussions` | - |
| List issue discussions | `glab api projects/:id/issues/:iid/discussions` | - |
| Get discussion | `glab api projects/:id/merge_requests/:iid/discussions/:id` | - |
| Create discussion | `glab api projects/:id/merge_requests/:iid/discussions -X POST -f ...` | ⚠️ |
| Reply to discussion | `glab api projects/:id/.../discussions/:id/notes -X POST -f ...` | ⚠️ |
| Resolve discussion | `glab api projects/:id/.../discussions/:id -X PUT -f resolved=true` | ⚠️ |
| Delete note | `glab api projects/:id/.../discussions/:id/notes/:nid -X DELETE` | ⚠️⚠️ |
**Risk Legend**: - Safe | ⚠️ Caution | ⚠️⚠️ Warning | ⚠️⚠️⚠️ Danger
## When to Use This Skill
**ALWAYS use when:**
- User mentions "discussion", "thread", "conversation"
- User wants to add code review comments
- User mentions "resolve", "unresolve" discussions
- User wants to reply to existing comments/threads
- User wants line-specific comments on MRs
**NEVER use when:**
- User wants simple notes/comments (use `glab mr note` or `glab issue note`)
- User wants to review MR changes (use gitlab-mr)
- User wants to search comments (use gitlab-search with `notes` scope)
## API Prerequisites
**Required Token Scopes:** `api`
**Permissions:**
- Read discussions: Reporter+ (for private repos)
- Create discussions: Reporter+
- Resolve discussions: Developer+ (or MR author)
## Available Commands
### List MR Discussions
```bash
# List all discussions on MR
glab api projects/123/merge_requests/1/discussions --method GET
# With pagination
glab api projects/123/merge_requests/1/discussions --paginate
# Using project path
glab api "projects/$(echo 'mygroup/myproject' | jq -Rr @uri)/merge_requests/1/discussions"
```
### List Issue Discussions
```bash
# List all discussions on issue
glab api projects/123/issues/42/discussions --method GET
# With pagination
glab api projects/123/issues/42/discussions --paginate
```
### Get Specific Discussion
```bash
# Get MR discussion by ID
glab api projects/123/merge_requests/1/discussions/abc123 --method GET
# Get issue discussion by ID
glab api projects/123/issues/42/discussions/def456 --method GET
```
### Create Discussion on MR
```bash
# Create general discussion
glab api projects/123/merge_requests/1/discussions --method POST \
-f body="This looks good overall, but I have some suggestions."
# Create discussion on specific line (diff note)
glab api projects/123/merge_requests/1/discussions --method POST \
-f body="This could be simplified using a helper function." \
-f position[base_sha]="abc123" \
-f position[head_sha]="def456" \
-f position[start_sha]="abc123" \
-f position[position_type]="text" \
-f position[new_path]="src/app.py" \
-f position[new_line]=42
# Create discussion on old line (removed code)
glab api projects/123/merge_requests/1/discussions --method POST \
-f body="Why was this removed?" \
-f position[base_sha]="abc123" \
-f position[head_sha]="def456" \
-f position[start_sha]="abc123" \
-f position[position_type]="text" \
-f position[old_path]="src/old.py" \
-f position[old_line]=15
# Create suggestion
glab api projects/123/merge_requests/1/discussions --method POST \
-f body='```suggestion
def improved_function():
return "better implementation"
```'
```
### Create Discussion on Issue
```bash
# Create discussion
glab api projects/123/issues/42/discussions --method POST \
-f body="I think we should reconsider this approach."
```
### Reply to Discussion
```bash
# Reply to MR discussion
glab api projects/123/merge_requests/1/discussions/abc123/notes --method POST \
-f body="Good point, I'll fix this."
# Reply to issue discussion
glab api projects/123/issues/42/discussions/def456/notes --method POST \
-f body="I agree with the above."
```
### Resolve/Unresolve Discussion
```bash
# Resolve MR discussion
glab api projects/123/merge_requests/1/discussions/abc123 --method PUT \
-f resolved=true
# Unresolve MR discussion
glab api projects/123/merge_requests/1/discussions/abc123 --method PUT \
-f resolved=false
```
### Update Note
```bash
# Update note in discussion
glab api projects/123/merge_requests/1/discussions/abc123/notes/789 --method PUT \
-f body="Updated comment text"
```
### Delete Note
```bash
# Delete note from discussion
glab api projects/123/merge_requests/1/discussions/abc123/notes/789 --method DELETE
```
## Position Object for Diff Notes
For line-specific comments on MRs, you need to provide position information:
| Field | Required | Description |
|-------|:--------:|-------------|
| `base_sha` | Yes | SHA of the base commit (target branch) |
| `head_sha` | Yes | SHA of the head commit (source branch) |
| `start_sha` | Yes | SHA of the start commit |
| `position_type` | Yes | `text` for code, `image` for images |
| `new_path` | For new/modified | Path in new version |
| `new_line` | For new/modified | Line number in new version |
| `old_path` | For deleted | Path in old version |
| `old_line` | For deleted | Line number in old version |
### Get SHAs for Position
```bash
# Get MR details to find SHAs
mr_info=$(glab api projects/123/merge_requests/1)
base_sha=$(echo "$mr_info" | jq -r '.diff_refs.base_sha')
head_sha=$(echo "$mr_info" | jq -r '.diff_refs.head_sha')
start_sha=$(echo "$mr_info" | jq -r '.diff_refs.start_sha')
echo "Base: $base_sha"
echo "Head: $head_sha"
echo "Start: $start_sha"
```
## Common Workflows
### Workflow 1: Review MR with Comments
```bash
project_id=123
mr_iid=1
# Get diff refs
mr_info=$(glab api projects/$project_id/merge_requests/$mr_iid)
base_sha=$(echo "$mr_info" | jq -r '.diff_refs.base_sha')
head_sha=$(echo "$mr_info" | jq -r '.diff_refs.head_sha')
start_sha=$(echo "$mr_info" | jq -r '.diff_refs.start_sha')
# Add comment on line 42 of new file
glab api projects/$project_id/merge_requests/$mr_iid/discussions --method POST \
-f body="Consider adding error handling here." \
-f position[base_sha]="$base_sha" \
-f position[head_sha]="$head_sha" \
-f position[start_sha]="$start_sha" \
-f position[position_type]="text" \
-f position[new_path]="src/handler.py" \
-f position[new_line]=42
```
### Workflow 2: Resolve All Discussions
```bash
# Get all unresolved discussions
glab api projects/123/merge_requests/1/discussions --paginate | \
jq -r '.[] | select(.notes[0].resolvable == true and .notes[0].resolved == false) | .id' | \
while read discussion_id; do
echo "Resolving: $discussion_id"
glab api projects/123/merge_requests/1/discussions/$discussion_id --method PUT \
-f resolved=true
done
```
### Workflow 3: List Unresolved Discussions
```bash
# Show unresolved discussions with content
glab api projects/123/merge_requests/1/discussions --paginate | \
jq -r '.[] | select(.notes[0].resolvable == true and .notes[0].resolved == false) | "[\(.id)] \(.notes[0].author.username): \(.notes[0].body | split("\n")[0])"'
```
### Workflow 4: Add Suggestion
```bash
project_id=123
mr_iid=1
mr_info=$(glab api projects/$project_id/merge_requests/$mr_iid)
base_sha=$(echo "$mr_info" | jq -r '.diff_refs.base_sha')
head_sha=$(echo "$mr_info" | jq -r '.diff_refs.head_sha')
start_sha=$(echo "$mr_info" | jq -r '.diff_refs.start_sha')
# Create suggestion (multi-line needs proper escaping)
glab api projects/$project_id/merge_requests/$mr_iid/discussions --method POST \
-f body='```suggestion
const result = await fetchData();
return result.data;
```' \
-f position[base_sha]="$base_sha" \
-f position[head_sha]="$head_sha" \
-f position[start_sha]="$start_sha" \
-f position[position_type]="text" \
-f position[new_path]="src/api.js" \
-f position[new_line]=25
```
### Workflow 5: Summarize Discussion Activity
```bash
# Count discussions by staRelated in Backend & APIs
jfrog
IncludedInteract with the JFrog Platform via the JFrog CLI and REST/GraphQL APIs. Use this skill when the user wants to manage Artifactory repositories, upload or download artifacts, manage builds, configure permissions, manage users and groups, work with access tokens, configure JFrog CLI servers, search artifacts, manage properties, set up replication, manage JFrog Projects, run security audits or scans, look up CVE details, query exposures scan results from JFrog Advanced Security, manage release bundles and lifecycle operations, aggregate or export platform data, or perform any JFrog Platform administration task. Also use when the user mentions jf, jfrog, artifactory, xray, distribution, evidence, apptrust, onemodel, graphql, workers, mission control, curation, advanced security, exposures, or any JFrog product name.
cupynumeric-migration-readiness
IncludedPre-migration readiness assessor for porting NumPy to cuPyNumeric. Use BEFORE substantial porting work begins when the user asks whether code will scale on GPU, whether they should migrate to cuPyNumeric, which NumPy patterns transfer cleanly, what must be refactored before porting, or mentions pre-port assessment, scaling analysis, or refactor planning. Inspect the user's source code, look up NumPy usage, cross-reference the cuPyNumeric API support manifest, and distinguish distributed-scaling-friendly patterns from blockers such as unsupported APIs, scalar synchronization, host round-trips, Python/object-heavy control flow, shape/data-dependent branching, and in-place mutation hazards. Produce a verdict of READY, LIGHT REFACTOR, SIGNIFICANT REFACTOR, or NOT RECOMMENDED, with concrete refactor pointers.
alibabacloud-data-agent-skill
IncludedInvoke Alibaba Cloud Apsara Data Agent for Analytics via CLI to perform natural language-driven data analysis on enterprise databases. Data Agent for Analytics is an intelligent data analysis agent developed by Alibaba Cloud Database team for enterprise users. It automatically completes requirement analysis, data understanding, analysis insights, and report generation based on natural language descriptions. This tool supports: discovering data resources (instances/databases/tables) managed in DMS, initiating query or deep analysis sessions, real-time progress tracking, and retrieving analysis conclusions and generated reports. Use this Skill when users need to query databases, analyze data trends, generate data reports, ask questions in natural language, or mention "Data Agent", "data analysis", "database query", "SQL analysis", "data insights".
token-optimizer
IncludedReduce OpenClaw token usage and API costs through smart model routing, heartbeat optimization, budget tracking, and native 2026.2.15 features (session pruning, bootstrap size limits, cache TTL alignment). Use when token costs are high, API rate limits are being hit, or hosting multiple agents at scale. The 4 executable scripts (context_optimizer, model_router, heartbeat_optimizer, token_tracker) are local-only — no network requests, no subprocess calls, no system modifications. Reference files (PROVIDERS.md, config-patches.json) document optional multi-provider strategies that require external API keys and network access if you choose to use them. See SECURITY.md for full breakdown.
resend-cli
IncludedUse this skill when the task is specifically about operating Resend from an AI agent, terminal session, or CI job via the official resend CLI: installing/authenticating the CLI, sending/listing/updating/cancelling emails, batch sends, domains and DNS, webhooks and local listeners, inbound receiving, contacts, topics, segments, broadcasts, templates, API keys, profiles, or debugging Resend CLI/API failures. Trigger on mentions of Resend CLI, `resend`, `resend doctor`, `resend emails send`, `resend domains`, `resend webhooks listen`, `resend emails receiving`, or agent-friendly terminal automation.
alibabacloud-odps-maxframe-coding
IncludedUse this skill for MaxFrame SDK development and documentation navigation on Alibaba Cloud MaxCompute (ODPS). Helps answer MaxFrame API, concept, official example, and supported pandas API questions; create data processing programs; read/write MaxCompute tables; debug jobs (remote or local); and build custom DPE runtime images. Trigger when users mention MaxFrame, MaxCompute with MaxFrame, ODPS table processing, DPE runtime, MaxFrame docs/examples, DataFrame/Tensor operations, or GPU runtime setup. Works for both English and Chinese queries about Alibaba Cloud data processing with MaxFrame.