workflow-authoring

Reference for writing a Workflow tool script (script API and gotchas, pipeline-vs-barrier rules, quality patterns, worked examples). Load before authoring a script for a workflow the user already opted into; it does not itself authorize running one.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

88%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.

The body is a lean, executable reference that assumes Claude's competence and supplies concrete code plus explicit validation/feedback-loop guidance for batch fan-out. Its main gap is progressive disclosure: all content lives in one inline file with no external reference split for the longer example/pattern sections.

Suggestions

Move the worked examples (composing patterns, loop-until-dry, adversarial verify) into a one-level-deep references file (e.g. EXAMPLES.md) and link to it from a concise overview, improving progressive disclosure.

Tighten the pipeline-vs-barrier "NOT justified by" bullet list and the composing-patterns inline comments to reduce editorial verbosity.

Consider extracting the full script-body-hooks option table into a short REFERENCE.md so SKILL.md stays a navigable overview.

Dimension	Reasoning	Score
Conciseness	Dense and competence-assuming with no basic-concept padding, but the pipeline-vs-barrier justification bullets and the composing-patterns example carry some editorial commentary that could be trimmed.	4 / 5
Actionability	Provides fully executable, copy-paste-ready JavaScript for the common cases — the meta block, pipeline/parallel usage, loop-until-count, loop-until-dry, and adversarial verify — alongside concrete API hook signatures and option lists.	5 / 5
Workflow Clarity	Patterns include explicit validation checkpoints and feedback loops — round-counter loop bounds against the 1000-agent cap, .filter(Boolean) and null-on-failure handling, "No silent caps: log() what was dropped", and journal.jsonl diagnosis — so batch operations are not left unvalidated.	5 / 5
Progressive Disclosure	Well-organized into clear sections with no nested references and coherent navigation, but at 213 lines everything is inlined with no one-level-deep reference files for the worked examples or pattern catalog, which leaves minor organization gaps.	4 / 5
	Total	18 / 20 Passed

Description

87%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.

The description is specific, explicit about both what it covers and when to load it, and clearly scoped to the Workflow tool with a useful authorization boundary. It is slightly light on natural synonyms (orchestration, fan-out, subagents) which keeps trigger coverage just below comprehensive.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete sub-topics — "script API and gotchas, pipeline-vs-barrier rules, quality patterns, worked examples" — giving multiple specific concrete areas, though phrased as reference topics rather than performed actions.	4 / 5
Completeness	Explicitly answers both what ("Reference for writing a Workflow tool script...") and when ("Load before authoring a script for a workflow the user already opted into"), with a concrete trigger phrase plus a boundary guard.	5 / 5
Trigger Term Quality	Includes natural terms a user would say ("writing a Workflow tool script", "authoring a script for a workflow") with good coverage, but misses common synonyms like orchestration, fan-out, or subagents.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche tied to the specific Workflow tool with distinct triggers and an explicit boundary note ("it does not itself authorize running one"), giving minimal conflict risk.	5 / 5
	Total	18 / 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: letta-ai/letta-code
Path: src/skills/builtin/workflow-authoring/SKILL.md
Commit: f3709eb

Reviewed: 7 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.