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

76%

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 ./.claude/skills/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 content is a well-structured, actionable workflow that leans on concrete CLI commands and explicit branching logic rather than abstract description. It is held back from top marks only by minor redundancy and the absence of a content-level validation feedback loop and a worked artifact example.

Suggestions

Consolidate the duplicated 'context/rules are constraints, not content' guidance into a single Guardrail and remove the partial restatement in Step 3 to tighten conciseness.

Add a brief validate->fix->retry loop for artifact content (e.g., re-run `openspec status` to confirm the artifact moved from 'ready' to 'done') to strengthen workflow clarity.

Include one short worked example of a created artifact (e.g., a minimal proposal.md skeleton) to make the authoring step fully copy-paste ready.

Dimension	Reasoning	Score
Conciseness	The body is efficient and assumes Claude's competence (it never explains what OpenSpec or an artifact is) and leads with executable commands, but the 'context/rules are constraints not content' point is made twice and the Artifact Creation Guidelines partially restate Step 3, so minor trimming is possible.	4 / 5
Actionability	It provides concrete, copy-paste-ready shell commands (`openspec list --json`, `openspec status --change`, `openspec instructions`) with field-by-field JSON parsing guidance, but actual artifact authoring is delegated to the CLI's `template`/`instruction` output rather than shown with a worked example.	4 / 5
Workflow Clarity	The four-step sequence is clearly ordered with explicit STOP points, status-based branching, and a 'verify the artifact file exists' checkpoint plus a Guardrails checklist, but there is no validate->fix->retry feedback loop for artifact content.	4 / 5
Progressive Disclosure	With no bundle files present, the self-contained body is organized into clearly labeled sections (Input, Steps, Output, Artifact Creation Guidelines, Guardrails) with no nested references; minor redundancy between Steps and the Guidelines keeps it just short of optimal.	4 / 5
	Total	16 / 20 Passed

Description

78%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-formed: it clearly states what the skill does and when to use it with concrete triggers anchored to a specific OpenSpec niche. Its main limitation is specificity, since it leans on a single concrete action plus workflow-continuance phrasing rather than enumerating several distinct capabilities.

Suggestions

Add one or two more concrete capabilities (e.g., 'reads completed artifacts for context and writes the next one to the specified output path') to lift specificity from a single action to several.

Reinforce the OpenSpec framing inside the 'Use when...' trigger (e.g., 'Use when the user wants to continue an OpenSpec change...') to reduce overlap with generic continue/workflow skills.

Consider natural synonyms such as 'resume', 'next step', or 'pick up' to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('OpenSpec change') and one concrete action ('creating the next artifact'), but the remaining phrases ('progress their change', 'continue their workflow') restate the workflow rather than adding distinct concrete actions, so coverage is not comprehensive.	3 / 5
Completeness	It explicitly answers both 'what' ('Continue working on an OpenSpec change by creating the next artifact') and 'when' with concrete trigger phrases in a dedicated 'Use when...' clause.	5 / 5
Trigger Term Quality	The 'Use when...' clause surfaces natural phrases a user would say ('progress their change', 'create the next artifact', 'continue their workflow'), giving good keyword coverage, though broader synonyms are absent.	4 / 5
Distinctiveness Conflict Risk	The 'OpenSpec change' niche is distinct and unlikely to trigger for unrelated skills, but the generic 'continue their workflow' phrasing in the trigger creates minor overlap risk with general continue/workflow skills.	4 / 5
	Total	16 / 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: dwmkerr/livedown
Path: .claude/skills/openspec-continue-change/SKILL.md
Commit: db0bd53

Reviewed: 4 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.