forge-bots
Skill2 starsChanged 5 days agoMITView on GitHub
Use when building a Discord, Slack or Telegram bot in code; n8n bots: forge-n8n.
1 other project uses a version of this, 1 of them edited.
Adopted by
Most recently taken up by
- ForgeyClap/claude-forgeedited, first seen Oct 11, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 1
- ForgeyClap/claude-forge★ 226% same
Wrote their own version · 0
None found.
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 repository99 other files it gives its agents.
- docs/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- brainstormingSkill
- claude-md-improverSkill
- dispatching-parallel-agentsSkill
- executing-plansSkill
- finishing-a-development-branchSkill
- forge-a11ySkill
- forge-agent-reportSkill
- forge-agentSkill
- forge-apiSkill
- forge-authSkill
- forge-autoresearchSkill
- forge-brainstormSkill
- forge-cliSkill
- forge-cmsSkill
- forge-code-reviewSkill
- forge-contextSkill
- forge-councilSkill
- forge-craftSkill
- forge-databaseSkill
- forge-dataSkill
- forge-debugSkill
- forge-deeplearnSkill
- forge-devopsSkill
- forge-docdriftSkill
- forge-doctorSkill
- forge-ecc-adapterSkill
- forge-ecommerceSkill
- forge-electronSkill
- forge-extensionSkill
- forge-figmaSkill
- forge-fullstackSkill
- forge-gameSkill
- forge-graded-verifySkill
- forge-guardianSkill
- forge-heartbeatSkill
- forge-i18n-docsSkill
- forge-intakeSkill
- forge-integrationSkill
- forge-long-form-writingSkill
- forge-mcp-clientsSkill
- forge-memorySkill
- forge-migrationSkill
- forge-mindmapSkill
- forge-mlopsSkill
- forge-mobileSkill
- forge-n8nSkill
- forge-nightshiftSkill
- forge-observabilitySkill
- forge-paymentsSkill
- forge-plan-largeSkill
- forge-prdSkill
- forge-predictionSkill
- forge-projectbrainSkill
- forge-prompt-coachSkill
- forge-qualitySkill
- forge-ragSkill
- forge-registrySkill
- forge-releaseSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 3 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 11
Use for: Discord, Slack and Telegram bots: per-platform event verification, fast ack, dedupe, minimal scopes, send-side retries.
- Very specific: line 12
Not for: the shared OAuth/secret/webhook backbone (lead it through forge-integration).
- Very specific: line 39
Every inbound webhook/interaction verifies the platform's auth on the raw body (Discord Ed25519 + PONG.
- Distinctive: line 44
No token / signing secret / PII in logs.
- Distinctive: line 45
No unsolicited DM / broadcast / mass-mention.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Forge playbook — Chat / messaging bots (Discord · Slack · Telegram)
When to use
- Use for: Discord, Slack and Telegram bots: per-platform event verification, fast ack, dedupe, minimal scopes, send-side retries.
- Not for: the shared OAuth/secret/webhook backbone (lead it through
forge-integration); bots that run through n8n (forge-n8n). - Domain framing, team roles and honesty rule:
references/overview.md.
Hard rules (non-negotiable)
- Verify every inbound event — per platform, on the raw body, before acting.
- Fast ack, background work.
- Idempotent handling — dedupe on the platform id.
- Minimal scopes / intents / permissions.
- Retries + dead-letter on the send side.
- Safe logging — no token/PII leak.
- Ignore the bot's own messages (no self-loop).
- Outreach drafted only.
Full text of every rule: references/hard-rules.md. The shared webhook rule set (sequence, response codes, dedupe with a uniqueness guarantee, persist before ack, dead letter) is .claude/skills/forge-integration/references/webhooks.md; this playbook adds only the per-platform details.
Team (conditional)
Lead: integration-boss (a bot is an external-system/webhook integration; use build-boss if the bot is one slice of a larger app). Full roster: references/team-and-tools.md.
Skills / commands / MCP
Skills, commands, MCP and opt-in dependencies: references/team-and-tools.md.
Fan-out & flow
L1/L2 for a single-platform bot with a few commands; L3 for multi-platform or many interactions + background jobs. Serial: register app + minimal scopes/intents → raw-body signature/secret verification → fast ack + dedupe → command routing → background processing + outbound retries → dead-letter. Parallel: independent command handlers ∥ per-platform adapters (independent once the verified-event contract is fixed — the verified, deduped event is the contract).
Domain gates
- Every inbound webhook/interaction verifies the platform's auth on the raw body (Discord Ed25519 + PONG; Slack HMAC
v0+ ≤5-min replay window; Telegram secret-token header); unsigned/expired/forged events are rejected. - Ack returned within the platform deadline (Slack/Discord ~3s, Discord defers long work); heavy logic runs in the background.
- Redelivered events deduped on
interaction.id/event_id/update_idwith a uniqueness guarantee. - Outbound calls honor rate limits (429 +
Retry-After), retry with bounded backoff, and dead-letter permanent failures — no silent drop. - Scopes/intents/permissions minimal; no privileged Discord intents or broad Slack scopes without justification + approval.
- No token / signing secret / PII in logs; secrets in env.
- No unsolicited DM / broadcast / mass-mention; any outreach is drafted-only until owner approves.
Ship-readiness (unique)
Evidence checklist before handoff: references/ship-readiness.md.
Safety, approval and honesty
- Approval / safety: no unsolicited DMs, mass-mentions or broadcasts without explicit owner approval; outreach drafted only.
- Approval / safety: privileged Discord intents or broad Slack scopes only when truly needed and owner-approved.
- Approval / safety: bot token and signing secrets in env; logs redacted.
- Honest failure: never claim a bot is "live"/"verified" unless a signed event was accepted and a forged one rejected.
- Honest failure: no platform sandbox/test app to exercise real events: say so (not-run).
- Untrusted content: see
references/untrusted-content.md. - Shared gates for every playbook (honesty, owner approval, secrets, reviews):
.claude/docs/forge-reference/playbook-template.md.
References
references/overview.md— domain framing paragraph(s) from under the title.references/hard-rules.md— full text of every hard rule.references/team-and-tools.md— full team roster, skills, commands, MCP and opt-in runtimes.references/ship-readiness.md— full ship-readiness evidence checklist.references/untrusted-content.md— Untrusted-content note..claude/skills/forge-integration/references/webhooks.md— the shared Forge webhook rule set.
Provenance
the self-loop rule is an idea from n8n-io/skills (skills/n8n-ai-nodes-official/SKILL.md, pinned SHA 27b6b9f429ac0be90cae764512dbc579d7107e95, Apache-2.0; idea only, no text reused); the persist-before-ack rule is a Forge addition. The webhook link points at the shared section, whose own provenance (hookdeck/webhook-skills, MIT) is inside that file. Excluded: all upstream code and workflow JSON.
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.

