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

82%

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

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, actionable workflow with concrete CLI commands, explicit JSON field semantics, and clear sequencing with validation checkpoints. Main gaps are minor conciseness trims and the absence of an explicit error-recovery retry loop.

Suggestions

Add an explicit validate→fix→retry feedback loop for artifact creation failures (e.g., re-run `openspec status` and re-read deps if a created artifact fails to verify), which would lift workflow_clarity toward 5.

Tighten the store-selection paragraph by leading with the sticky `--store <id>` rule and folding the worked example into a one-line aside.

Consider extracting the JSON field reference for `instructions` output into a short table to improve scanability and progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is dense and instructional with concrete commands and JSON field lists, and it does not explain concepts Claude already knows. A few sections (notably the store-selection paragraph) could be tightened, keeping it at anchor 4 rather than 5.	4 / 5
Actionability	Provides fully executable, copy-paste-ready commands (`openspec status --change "<name>" --json`, `openspec instructions <artifact-id> ...`) plus documented JSON field semantics and resolved output paths, matching anchor 5's fully-executable bar.	5 / 5
Workflow Clarity	Steps are clearly sequenced (Select → status → act → show progress) with explicit STOP points and verification (verify file exists, re-read deps from disk). Not 5 because there is no explicit error-recovery retry loop, only implicit guardrails.	4 / 5
Progressive Disclosure	Well-organized into clear sections (Store selection, Input, Steps, Output, Guidelines, Guardrails) with no external file references needed since the CLI is the source of truth. It exceeds the under-50-line simple-skill exception in length, so it lands at anchor 4 rather than 5.	4 / 5
	Total	17 / 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 is well-scoped to the OpenSpec change-continuation niche with explicit what-and-when guidance and natural trigger phrases. Its only weakness is specificity: it describes a single concrete action rather than a comprehensive capability list.

Suggestions

Broaden the capability list beyond a single action, e.g. 'create the next artifact, resume planning, or advance an in-progress change' to lift specificity toward anchor 5.

Add a synonym or two for discoverability (e.g. 'resume an OpenSpec change' alongside 'progress their change').

Dimension	Reasoning	Score
Specificity	Names the OpenSpec domain and one concrete action ("creating the next artifact"), but does not enumerate a comprehensive set of capabilities. It sits at anchor 3 (domain + 1-2 concrete actions) rather than 4 because coverage is essentially a single action.	3 / 5
Completeness	Explicitly states what it does ("Continue working on an OpenSpec change by creating the next artifact") and when to use it ("Use when the user wants to progress their change, create the next artifact, or continue their workflow") with concrete trigger phrases, matching anchor 5.	5 / 5
Trigger Term Quality	Includes natural workflow phrases a user would say ("progress their change", "create the next artifact", "continue their workflow") with good verb coverage. Not a 5 because it lacks synonyms and file/extension variants.	4 / 5
Distinctiveness Conflict Risk	Scoped to the OpenSpec-change niche with specific triggers ("progress their change", "continue their workflow"), giving it a clear niche with minimal conflict risk as in anchor 5.	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: Fission-AI/OpenSpec
Path: skills/openspec-continue-change/SKILL.md
Commit: 6926ccb

Reviewed: about 16 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.