graph

Deterministic orchestration graph runtime - declarative DAG pipelines with journal-based crash recovery

Quality

68%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/graph/SKILL.md

Quality

Content

82%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 tight, highly actionable skill with copy-paste commands, a complete minimal descriptor schema, explicit exit codes, and a well-sequenced workflow that includes real validation (approval gates and fail-closed journal integrity). The main opportunity is tightening the dense Capability Boundary section and adding an explicit validate->fix->retry loop for authoring/resume errors.

Dimension	Reasoning	Score
Conciseness	The body is dense and assumes Claude's competence (no padding about what a DAG or journal is); it is efficient with only minor instances that could be trimmed, fitting the 'efficient; minor over-explanation' anchor rather than the fully lean 5.	4 / 5
Actionability	Copy-paste-ready CLI commands ('omc graph run <descriptor.json> [--runs-root <dir>]'), a complete minimal descriptor schema with concrete command/agent/approval node examples, and normative exit codes cover the common cases, matching the 'fully executable' anchor.	5 / 5
Workflow Clarity	A clear 5-step workflow with checkpoints (approval-node detection, interactive vs Bash routing, exit-code feedback, resume semantics) is present; the batch/destructive cap at 3 does not apply because validation is present (approval gates, fail-closed journal handling), but it lacks the explicit validate->fix->retry loop of a 5.	4 / 5
Progressive Disclosure	Sections are well-organized (Usage, When To Use, Workflow, Descriptor Schema, Capability Boundary) with a clearly signaled one-level reference to src/graph/schema.ts for the authoritative schema; no bundle files exist, and the inline content is reasonably scoped, fitting the 'good structure; references mostly clear' anchor.	4 / 5
	Total	17 / 20 Passed

Description

53%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 conveys a clear and specific 'what' for a deterministic DAG orchestration runtime, but it omits any 'when to use' / trigger guidance, which caps completeness and limits activation quality. Adding a concrete 'Use when...' clause with natural trigger terms would raise multiple dimensions.

Suggestions

Append an explicit trigger clause, e.g. 'Use when running repeatable multi-step DAG pipelines that must survive interruption and resume from a journal.'

Add natural trigger terms and synonyms users would say ('pipeline', 'workflow', 'multi-step pipeline', 'resumable run') to improve trigger term quality and distinctiveness.

List a couple more concrete actions (e.g. 'author descriptors, run command/agent/approval nodes, resume after crash') to move specificity from 1-2 actions toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('orchestration graph runtime') and two concrete capabilities ('declarative DAG pipelines', 'journal-based crash recovery'), matching the 'names domain and 1-2 concrete actions' anchor; it is not a 4 because it does not enumerate several specific actions.	3 / 5
Completeness	The 'what' is clear (deterministic DAG runtime with crash recovery) but there is no 'when' / 'Use when...' trigger clause; per the judging guidelines a missing trigger clause caps completeness at 3.	3 / 5
Trigger Term Quality	Relevant keywords like 'orchestration', 'DAG', 'pipelines', and 'crash recovery' are present, but common variations/synonyms a user might naturally say (e.g. 'workflow', 'pipeline runner') are missing, fitting the 'some relevant keywords but missing variations' anchor.	3 / 5
Distinctiveness Conflict Risk	The niche is distinct (deterministic DAG orchestration with journal-based recovery) with minimal overlap risk; not a 5 because the absence of explicit trigger phrases weakens the distinctiveness of activation.	4 / 5
	Total	13 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: Yeachan-Heo/oh-my-claudecode
Path: skills/graph/SKILL.md
Commit: dc7ba1d

Reviewed: 3 days 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.