observability slo architect
by Kaymue
Design SLOs/SLIs for any service. Generates Prometheus rules, Grafana dashboards, burn-rate alerts. Google's 2%/50% model.
New: Skill bounties are live. Post a request, fund the bounty, and creators compete for 7 days to build it -> See open bounties
THE AGENSI STORE
2118 skills found
by Kaymue
Design SLOs/SLIs for any service. Generates Prometheus rules, Grafana dashboards, burn-rate alerts. Google's 2%/50% model.
by Kaymue
Audit prompts and MCP tools for prompt injection. 47 attack patterns, OWASP LLM Top 10, generates adversarial tests. CVSS-scored.
A DevSecOps engineer that stands up and tunes static analysis (Semgrep, SonarQube, CodeQL) for high-signal findings — picks the right tool for the stack, writes the config and rulesets, wires a sane CI gate, and tunes out the false positives that get scanners muted.
A professional technical editor's review for your docs. Catches missing context, unclear writing, and unverifiable claims in READMEs, API docs, and changelogs before they ship — with a PASS/REVISE verdict and a prioritized fix list.
by ilia
Turn any data into hundreds of on-brand product cards, banners and stories — local, deterministic, no watermarks
by SkillForge
Calm, on-brand replies to any customer review — 5-star to angry 1-star — using a proven service-recovery framework.
by Al1as
A forensic diagnostic tool to expose hidden risks and structural flaws in business and technical commitments.
by SkillForge
A pre-submission audit tool to prevent developer community posts from being removed, buried, or flagged as spam.
Check your app, site, and ad copy for the AI disclosures US regulators and ad platforms now expect: undisclosed AI chatbots, unlabeled AI-generated media, AI-origin ad copy with no disclosure line, and sponsored content with no material-connection language. Read-only, every finding explained in plain English. US and ad-platform focused.
by Shandra
Tests AI agents, prompts, and agent skills against edge cases, unsafe behavior, output failures, permission risks, escalation gaps, memory leaks, and marketplace-quality weaknesses.
Generates 13-section production specs for printable and digital social media content planners in any business niche.
by Shippers
Convert a plain-English user flow plus a route/component map into a runnable Playwright, Cypress, or Detox test file wit
by Shandra
Creates intelligent upsell, cross-sell, accessory, bundle, premium alternative, budget alternative, and product pairing recommendations that increase AOV responsibly.
by SkillForge
Hand Claude a product and a goal; get a complete, ready-to-run campaign — strategy, the calendar, all the copy, and the creatives.
by Shandra
Creates structured preschool curriculum scope and sequence plans by month, week, trimester, semester, or year, covering letters, numbers, themes, motor skills, SEL, art, music, and simple science.
by Timoranjes
Build production-grade React Native apps with native primitives, optimized lists, and type-safe navigation.
Transform your expertise into scoped, sellable, and deliverable paid audit offers with checklists and reports.
A cold buyer simulator that audits digital product listings for friction, confusion, and generic claims.
by Kaymue
Cut observability cost 60-80%. Migrate Datadog/New Relic to Prometheus + Grafana + Loki. Cost calc, dashboard converter, runbook.
by Kaymue
Production Stripe billing in one shot. Subscriptions, metered usage, webhooks, customer portal, tax, fraud. 12 patterns, TS+Python.
by Kaymue
Audit AI/LLM spend across OpenAI, Anthropic, AWS Bedrock, Azure. Find waste, project runway, FinOps report. Free scripts.
by SkillForge
Prevent flaky Windows automation by enforcing robust UI identity, conditional waits, and safety guards.
Check an invoice or estimate before you send it: missing document number, dates, or payment terms, totals that do not add up, tax gaps, missing remittance details, and slow terms with no late fee. Read-only, plain-English findings. Not accounting advice.
Write the delegation brief that lets a background or async agent succeed unattended — precise goal, hard constraints, testable acceptance criteria, a verification plan, and stop-and-escalate rules. Turns "go fix the flaky tests" into a spec an agent can actually execute.