openspec-continue-change

Continue working on an OpenSpec change by creating the next artifact. Use when the user wants to progress their change, create the next artifact, or continue their workflow.

Quality

78%

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 ./eval/local/skills/benchmarks/dependency/openspec/openspec-continue-change/SKILL.md

Quality

Content

75%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 lean and action-oriented, anchored by concrete openspec CLI commands, explicit JSON field parsing, and a clear status-driven decision tree with verification. The main gaps are an abstract artifact-write step and the absence of a validate→fix→retry feedback loop, which together keep it just short of the top anchors.

Suggestions

Replace the abstract 'Write to the output path specified' with a concrete write mechanism or short example so the artifact-creation step is copy-paste ready.

Add an explicit validate→fix→retry feedback loop after writing an artifact (e.g., re-run openspec status and remediate if the artifact is not recognized as done) to lift workflow clarity toward 5.

Consider moving the spec-driven artifact patterns into a short references file and signaling it from the body, which would separate schema-specific detail from the core workflow.

Dimension	Reasoning	Score
Conciseness	The body uses concrete CLI commands and parses specific JSON fields without explaining concepts Claude already knows, though the 'Artifact Creation Guidelines' section and the repeated context/rules guardrail (stated in step 3 and again in Guardrails) are minor trimmable redundancy.	4 / 5
Actionability	Provides concrete, executable bash commands and specific JSON field-by-field parsing guidance with clear decision branches, but the actual artifact-writing step ('Write to the output path specified') is described abstractly rather than with a concrete write command or example.	4 / 5
Workflow Clarity	A clear numbered sequence with three explicit status branches and a verification checkpoint ('Verify the artifact file exists after writing') plus STOP markers, though it lacks a full validate→fix→retry error-recovery feedback loop and the blocked branch offers no retry path.	4 / 5
Progressive Disclosure	Well-organized with clear section headers (Input, Steps, Output, Artifact Creation Guidelines, Guardrails) in a self-contained file with no nested references; the inlined spec-driven pattern block is a minor organization gap that in a larger system could warrant its own schema reference.	4 / 5
	Total	16 / 20 Passed

Description

82%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 clearly answers both what and when with an explicit 'Use when' clause and is tightly scoped to the OpenSpec niche, keeping conflict risk low. Specificity is the weakest area: the actions cluster around the single concept of 'creating the next artifact' rather than enumerating multiple concrete capabilities.

Suggestions

Enumerate concrete artifact types the skill creates (e.g., 'proposals, specs, design docs, and task lists') to lift specificity beyond the single 'creating the next artifact' action.

Broaden trigger-term coverage with natural synonyms users might say, such as 'pick up my change', 'continue my OpenSpec work', or 'start the next spec artifact'.

Dimension	Reasoning	Score
Specificity	Names the OpenSpec domain and one concrete action ('creating the next artifact'), but the remaining verbs ('progress their change', 'continue their workflow') are somewhat generic and circular rather than multiple distinct specific actions.	3 / 5
Completeness	Explicitly states what it does ('Continue working on an OpenSpec change by creating the next artifact') and provides an explicit 'Use when' clause with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural phrases a user would say ('progress their change', 'create the next artifact', 'continue their workflow'), but synonym coverage is limited and the triggers repeat the same artifact/continue concept.	4 / 5
Distinctiveness Conflict Risk	Scoped to a specific named system (OpenSpec change workflow), giving it a clear niche with distinct triggers and minimal overlap with unrelated skills.	5 / 5
	Total	17 / 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: rpamis/comet
Path: eval/local/skills/benchmarks/dependency/openspec/openspec-continue-change/SKILL.md
Commit: f329b48

Reviewed: about 24 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.