notify
Skill1 starsChanged 7 months agoMITView on GitHub
Post a structured notification to a configured Slack or Microsoft Teams webhook. Used by deploy / coverage / security skills (or CI pipelines) to broadcast results without hardcoding webhook URLs in scripts. Webhook URLs come from `.claude/sf-project.json` (or env override).
- Sends data out
13 other projects use a version of this.
Adopted by
Most recently taken up by
- udecode/platetheir own version, first seen Nov 8, 2026
- thenickz/opencode-notifytheir own version, first seen Oct 20, 2026
- xpoes123/claude-skillstheir own version, first seen Oct 20, 2026
- microsoft/IssueLenstheir own version, first seen Oct 19, 2026
- superbereza/lobster-powerstheir own version, first seen Oct 11, 2026
- jonhill90/skillstheir own version, first seen Sep 30, 2026
Other versions13 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 13
- udecode/plate★ 17ksame name
- zjunlp/Mechanist★ 75same name
- jonhill90/skills★ 8same name
- yangwhale/CloseCrab★ 5same name
- jord0-cmd/jord0.skills★ 1same name
- JordanHood/claude-skills★ 0same name
- microsoft/IssueLens★ 0same name
- Odonno/doc2skill★ 0same name
- possibilities/agentguidance★ 0same name
- Sossenbinder/claude_skills★ 0same name
3 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository53 other files it gives its agents.
- templates/CLAUDE.mdCLAUDE.md
- adrSkill
- agent-deploySkill
- agent-discoverSkill
- agent-eval-trendSkill
- agent-exchange-listSkill
- agent-specSkill
- agent-testSkill
- agent-vs-flow-vs-apexSkill
- before-vs-after-triggerSkill
- code-reviewSkill
- complexitySkill
- coverage-trendSkill
- dead-codeSkill
- dependency-graphSkill
- deploySkill
- destructive-changesSkill
- diff-deploySkill
- erdSkill
- field-impactSkill
- flaky-test-finderSkill
- flow-auditSkill
- flow-vs-apexSkill
- fls-auditSkill
- gateway-configSkill
- generate-docsSkill
- limit-usageSkill
- lwc-vs-reactSkill
- mcp-tool-vs-restSkill
- onboardSkill
- org-diffSkill
- org-exploreSkill
- package-versionSkill
- pattern-packSkill
- perf-reviewSkill
- permset-auditSkill
- pr-prepareSkill
- queueable-vs-batchSkill
- quick-deploySkill
- react-initSkill
- release-notesSkill
- scratch-orgSkill
- security-scanSkill
- sequence-diagramSkill
- sf-initSkill
- sharing-reviewSkill
- slack-agentSkill
- soql-analyzerSkill
- test-coverageSkill
- test-dataSkill
- test-planSkill
- trust-evalSkill
- trust-layer-auditSkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.
0
Common
Most of the 12 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 123
Sensitive content scrub: Never include test data, customer PII, or auth tokens in the message.
“Common” is measured: kept by at least 6 in 10 of the 12 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
You are posting a notification to a team chat webhook. The webhook URL lives in the project config under notifications.webhooks; this skill never accepts a URL as an argument (so it's safe in shell history).
Read Project Config First
source "${CLAUDE_PLUGIN_ROOT}/hooks/lib/config.sh"
SLACK_URL="$(sf_config_get '.notifications.webhooks.slack // empty' "$ENV")"
TEAMS_URL="$(sf_config_get '.notifications.webhooks.teams // empty' "$ENV")"Config Schema (in sf-project.json)
{
"notifications": {
"webhooks": {
"slack": "https://hooks.slack.com/services/T.../B.../X...",
"teams": "https://outlook.office.com/webhook/..."
},
"channels": {
"deploy": ["slack"],
"coverage": ["slack", "teams"],
"security": ["slack"],
"release": ["slack", "teams"]
}
}
}The channels map says which event types go to which platforms. If empty, all configured platforms receive every event.
/argo:sf-init (Phase 1) does not prompt for these by default — they're sensitive. Recommend adding to a per-env override file (.claude/sf-project.prod.json) so dev/QA don't post to the team channel during testing.
Input
$ARGUMENTS: required.
<event-type> <payload-json>— e.g.,deploy '{"status":"Succeeded","org":"Prod","componentCount":12,"deployId":"0Af..."}'--channel slack|teams|all— override the configured channel routing--dry-run— print the message that would be sent without posting
Event types and rendering
| Event | Slack rendering | Teams rendering |
deploy | :rocket: *Deploy <status>* to <org> — <componentCount> components — <deployId> + actions block linking to deploy log | Adaptive Card with the same fields |
coverage | :bar_chart: *Coverage <delta>* — overall <percent>% — <regressions count> classes regressed | Adaptive Card |
security | :rotating_light: *Security scan* — <criticalCount> critical, <warningCount> warning | Adaptive Card |
release | :package: *<version> released* — <highlightCount> features, <fixCount> fixes — <releaseNotesUrl> | Adaptive Card |
custom | <text> (raw) | <text> |
Steps
1. Validate inputs
- Event type must be one of the supported list
- Payload must be valid JSON
2. Render messages
For Slack (Block Kit):
{
"blocks": [
{ "type": "section", "text": { "type": "mrkdwn", "text": "<rendered text>" } },
{ "type": "context", "elements": [{ "type": "mrkdwn", "text": "<project.name> · <org>" }] }
]
}For Teams (Adaptive Card):
{
"type": "message",
"attachments": [
{
"contentType": "application/vnd.microsoft.card.adaptive",
"content": { "type": "AdaptiveCard", "body": [...], "version": "1.4" }
}
]
}3. Post
curl -fsS -X POST -H 'Content-Type: application/json' --data "$BODY" "$WEBHOOK_URL"Capture HTTP status. Slack returns ok (200); Teams returns 1 (200).
4. Output
Default:
[notify] Posted deploy notification to slack (HTTP 200)
[notify] Posted deploy notification to teams (HTTP 200)--dry-run:
[notify] Would POST to slack: <URL truncated>
{"blocks": [...]}CI mode: emit {"posted": ["slack", "teams"], "errors": []}.
Exit codes
- 0 — all configured channels accepted the post (or
--dry-run) - 1 — at least one channel rejected (HTTP 4xx/5xx)
- 2 — invocation error (no webhook configured, invalid event type)
Rules
- Never log webhook URLs. They're effectively credentials. Truncate when echoing in dry-run
- Never accept a webhook URL via $ARGUMENTS. Force users to put it in config
- Don't fail loudly in CI. A failed notification shouldn't break a deploy. Exit 1 with a message; the caller decides whether to retry
- Truncate long payloads. Slack/Teams cap message size; if a release note is >4 KB, truncate with a "see full notes at
<URL>" footer - Sensitive content scrub. Never include test data, customer PII, or auth tokens in the message. The skill blocks if the rendered text contains anything matching common token patterns
Consumers
- CI deploy pipeline:
/argo:notify deploy "$DEPLOY_RESULT_JSON" /argo:test-coverageposts acoverageevent when run with--notify/argo:security-scanposts asecurityevent when run with--notify- Release process:
/argo:release-notes+/argo:notify release ...
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

