Git
v1.0.0

eval-marker

by @volekerb0 pulls
URLopenbooklet.com/s/eval-marker
Pinnedopenbooklet.com/s/[email protected]
APIGET /api/v1/skills/eval-marker

Use this skill at the start of every task in this repository, whatever the task is (fixing a bug, adding a feature, reviewing a diff, answering a question). It applies to all work in the repo.

15 skills from this repovolekerb/hivemill
eval-markerviewing
acceptance-templateroles/plugins/pm/pm-skills/skills/acceptance-template/SKILL.md

Make every acceptance item a runnable command with an expected result, quote wording exactly, and add a RISKS section. Use when writing or amending a task's spec or acceptance.

Audit at goal end (lead)roles/plugins/lead/factory-lead/skills/audit-round/SKILL.md

5. **Audit at goal end.** When `factory task ready --goal G` is empty and every build task is done or cancelled, do not close the goal yourself. Create an audit task and spawn the pm: `factory task add --goal G --team <team> --role pm --title "Audit G-xxx (round n)" --spec -` (spec: the audit checkl

close-goalroles/plugins/director/factory-director/skills/close-goal/SKILL.md

Director steps to sign off, close and reopen a goal after the pm audit. Use when a lead says a goal's build tasks are done, or a done goal must be reopened.

cycle-proceduresroles/plugins/director/factory-director/skills/cycle-procedures/SKILL.md

Detail text moved out of director.md to fit the role budget (staffing, judging leads, reporting, scout reports, escalations). Use when running the director cycle steps on staffing several teams, chasing status, scoring leads, housekeeping, reporting to the boss, or recording decisions.

Delivery (director)roles/plugins/director/factory-director/skills/delivery/SKILL.md

Purpose: every active goal is delivered on time (D1-D5 in director.md). Owner order M7486, verbatim: "i want goals to be conpleted. Director shall find out and be accoontable for the delivery in time. It has all resources management and can spawn any agents needed to accomplish work either coding or

fix-looproles/plugins/lead/factory-lead/skills/fix-loop/SKILL.md

Run retries, stalls and the third attempt on a task. Use when a reviewer or QA FAIL or a judge reject comes back, when respawning a coder, when a task reaches attempt 2 or attempt 3, when a worker is lost, stopped or stalled, or when the findings are only nits.

go-changeroles/plugins/coder/coder-skills/skills/go-change/SKILL.md

Checklist for writing idiomatic, safe, stdlib-only Go under go/ with tests and the local toolchain. Use when a task's spec names Go, touches go/, or adds a Go test, fuzz target or parser.

Goal audit checklist (pm)roles/plugins/pm/pm-skills/skills/audit-checklist/SKILL.md
guard-changeroles/plugins/coder/coder-skills/skills/guard-change/SKILL.md

Procedure for changing a guard so the PR fixes the whole bypass class and loosens nothing unplanned. Use when editing roles/hooks/*, a deny rule in roles/settings/*.json, a CLI refusal, or when retrying a PR after a reviewer or QA bypass finding.

Multi-angle review (gated PRs only)roles/plugins/reviewer/reviewer-skills/skills/multi-angle-review/SKILL.md

Three read-only angle agents (correctness, guard/security, spec-fit) plus one verifier per angle. The output is input to your verdict, never the verdict.

owner-decisionsroles/plugins/director/factory-director/skills/owner-decisions/SKILL.md

Decide what the director settles itself, what goes to the owner and what defaults after 2 daytime hours (owner standing rule M833). Use when an owner question, approval, cap or default comes up, or before sending anything to the boss for the owner.

restriction-checkroles/plugins/director/factory-director/skills/restriction-check/SKILL.md

List every automated writer of a target before proposing a restriction, and say how each is affected. Use when proposing or approving branch protection, deny rules, caps, permission narrowing or any other repo or infra restriction.

spec-changeroles/plugins/lead/factory-lead/skills/spec-change/SKILL.md

Change a running worker's spec, acceptance or scope safely through the task DB. Use when a running worker's spec, acceptance or scope must change.

worker-briefroles/plugins/lead/factory-lead/skills/worker-brief/SKILL.md

Checklist to run before every worker spawn so the brief is complete and safe. Use when about to spawn a pm, coder, qa, reviewer, judge or cleaner, or when writing or editing a worker's task spec.

Auto-indexed from volekerb/hivemill

Are you the author? Claim this skill to take ownership and manage it.

Related Skills

@openbooklet

graceful-error-recovery

Use this skill when a tool call, command, or API request fails. Diagnose the root cause systematically before retrying or changing approach. Do not retry the same failing call without first understanding why it failed.

1.1K0
@openbooklet

audience-aware-communication

Use this skill when writing any explanation, documentation, or response that will be read by someone else. Match vocabulary, depth, and format to the audience's expertise level before writing.

1.1K0
@openbooklet

Refactoring Expert

Expert in systematic code refactoring, code smell detection, and structural optimization. Use PROACTIVELY when encountering duplicated code, long methods, complex conditionals, or any code quality issues. Detects code smells and applies proven refactoring techniques without changing external behavior.

600
@openbooklet

Research Expert

Specialized research expert for parallel information gathering. Use for focused research tasks with clear objectives and structured output requirements.

600
@openbooklet

clarify-ambiguous-requests

Use this skill when the user's request is ambiguous, under-specified, or could be interpreted in multiple ways. If proceeding with a wrong assumption would waste significant work, always ask exactly one focused clarifying question before doing anything.

1.1K0
@openbooklet

structured-step-by-step-reasoning

Use this skill for any problem that involves multiple steps, tradeoffs, or non-trivial logic. Think out loud before answering to improve accuracy and transparency. Apply whenever the answer is not immediately obvious.

1.1K0