absurd

Author, test, debug, and operate Absurd durable workflows. Use when working with WorkflowContext, tasks-orchestrator, parallelTasks, issue-lifecycle, multi-lens-review, Absurd queues, checkpoints, events, retries, idempotency, worker recovery, absurd-sdk, or uvx absurdctl.

Quality

84%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

76%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A highly actionable, command-dense operational playbook with clear sequencing and one well-placed reference. The main gaps are a missing post-change validation/feedback loop for destructive operations (capping workflow clarity) and some repeated playbook content that could be trimmed.

Suggestions

Add an explicit verify-after-change step for destructive/batch commands (e.g., after `migrate` run `schema-version` to confirm, after `cancel-task`/`retry-task` re-run `dump-task` to confirm the new state) to form a validate -> fix -> retry feedback loop.

Collapse the "Good copy-paste playbooks" section or mark it as condensed cross-references to the commands already detailed above, to remove repetition and tighten token use.

Consider moving the schema/migration setup into the authoring-and-recovery reference (or a dedicated ops reference) and keeping SKILL.md focused on the debug/inspection flow.

Dimension	Reasoning	Score
Conciseness	Dense with executable commands and a lean mental model that earns its place with Absurd-specific definitions, but the "Good copy-paste playbooks" section repeats commands already shown in "Default debugging workflow" and "Common actions" — minor trimmable repetition that keeps it just below fully lean.	4 / 5
Actionability	Extensive copy-paste-ready `uvx absurdctl` commands with concrete flags (-P key=value, -P key:=json, --params, --payload, --spawn-new) plus executable rg patterns, covering the common inspection and mutation cases fully.	5 / 5
Workflow Clarity	Debugging flows are clearly numbered (1-2-3-4) and there is a safe-operating-rules section, but the destructive/batch operations (init, migrate, drop-queue, cancel, retry, spawn, emit) lack an explicit validate-after-change feedback loop, so the destructive-operation cap at 3 applies.	3 / 5
Progressive Disclosure	One clearly-signaled one-level-deep reference ("read [authoring and recovery](references/authoring-and-recovery.md) before editing") pointing to a real file, with a well-sectioned overview body; the inlined operational playbook is justified by the skill's command-heavy nature but keeps it just short of a fully split structure.	4 / 5
	Total	16 / 20 Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description that clearly states both capabilities and a rich set of use-when triggers around a distinctive product. The main weakness is that many trigger terms are internal API names rather than language a user would naturally say.

Suggestions

Lead the trigger list with the most natural user phrases (queues, durable tasks, retries, events, 'uvx absurdctl') and group the internal API identifiers (WorkflowContext, tasks-orchestrator, parallelTasks) separately so the natural triggers stand out.

Consider adding a plain-language synonym such as "durable background jobs" or "workflow orchestration" that a user might say before knowing the Absurd-specific terminology.

Dimension	Reasoning	Score
Specificity	Names the domain plus four concrete lifecycle actions — "Author, test, debug, and operate Absurd durable workflows" — giving comprehensive coverage of what the skill does.	5 / 5
Completeness	Explicitly answers both what ("Author, test, debug, and operate Absurd durable workflows") and when ("Use when working with ... or uvx absurdctl") with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Strong natural terms ("queues", "events", "retries", "worker recovery", "uvx absurdctl") but the bulk of the trigger list is internal API identifiers (WorkflowContext, tasks-orchestrator, parallelTasks) users would not naturally say, leaving it just short of fully comprehensive natural coverage.	4 / 5
Distinctiveness Conflict Risk	The unique "Absurd" product name combined with distinctive triggers ("uvx absurdctl", "absurd-sdk", "WorkflowContext") gives a clear niche with minimal overlap with other skills.	5 / 5
	Total	19 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: getlarge/themoltnet
Path: .agents/skills/absurd/SKILL.md
Commit: 5daa9ca

Reviewed: ~15 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.