← All creators

Pulseboard-ai

Organization

Agent skills that reconcile reported status against Jira, GitHub, Slack and the PRD

5 indexed · 0 Featured · 0 stars · avg score 71
Prolific

Categories

Indexed Skills (5)

AI & Automation Listed

agent-done-chain

Verifies whether an AI agent's "task complete" claim is actually true, by checking it against eight evidence-based tests before you trust it. Use whenever an autonomous agent, sub-agent, or agentic coding tool reports a task, ticket, PR, or job as done, and you need to confirm that before relying on it, merging it, deploying it, or reporting it upward. Not a code reviewer — this checks whether the CLAIM matches the EVIDENCE, not whether the code is good.

0 Updated 1 weeks ago
Pulseboard-ai
DevOps & Infrastructure Listed

reconcile-dependencies

Finds phantom dependencies — the ones nobody declared — by comparing what the PRD says a feature depends on against what tickets, PRs, and Slack actually reference, and flags knowledge gaps where a dependency's owner has left. Use whenever the user asks what depends on what, wants a dependency map or risk review, says a dependency "came out of nowhere", is planning a quarter or release across teams, or mentions someone leaving and not knowing who owns a system — even if they only paste a PRD and a ticket list.

0 Updated 1 weeks ago
Pulseboard-ai
AI & Automation Listed

reconcile-status

Reconciles a program's reported status against what Jira, GitHub, Slack and the PRD actually show, by walking every feature through the 8-link Done Chain and returning a discrepancy table with evidence per cell. Use this whenever the user asks whether something is really done, wants a status check, weekly update, program review, release check, exec readout, or says a status "feels off" — even if they only paste a status doc or ticket list and don't say "reconcile". Also use when asked to verify a green status, audit a sprint, or find drift.

0 Updated 1 weeks ago
Pulseboard-ai
AI & Automation Listed

release-readiness

Checks a release against what was committed in planning — for every committed feature walks the Done Chain, flags uncommitted work that slipped into the release branch, checks release stakeholders were told, and returns a GO / NO-GO with a reason per feature instead of a score. Use whenever the user asks if a release is ready, wants a go/no-go, a release checklist, a cut decision, a launch readiness review, or asks "can we ship Friday" — even if they only paste a release plan or a PR list. Not a build-hygiene checklist (tests, lint, changelog); this is commitment-vs-delivery.

0 Updated 1 weeks ago
Pulseboard-ai
AI & Automation Listed

resolve-blocker

Turns one blocker or discrepancy into a resolution plan and a one-page decision memo for leadership — classifies the blocker, checks the precedent log, maps stakeholders, drafts options with the eng SME, pre-wires 1:1s, applies an escalation gate, and closes the loop. Use whenever the user says something is blocked, stuck, slipping, needs a decision, needs to go to leadership, needs consensus, or hands you a row from reconcile-status — even if they just describe the situation and don't ask for a memo. Also use in leader mode when a user receives an escalation and wants it checked before deciding.

0 Updated 1 weeks ago
Pulseboard-ai

Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.