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

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.agent/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 solid, executable CLI workflow with a well-sequenced process and concrete commands throughout. It falls just short of top marks because of light redundancy, template-based (non-code) artifact creation, and weak error-recovery feedback loops.

Suggestions

Add an explicit error-recovery loop after the 'verify the artifact file exists' step — e.g., if the file is missing or instructions JSON parse fails, re-run the command or surface the error before proceeding.

De-duplicate the IMPORTANT note about context/rules being constraints (it appears in both the step body and Guardrails); state it once in Guardrails and reference it.

Consider moving the spec-driven artifact-pattern reference (proposal/specs/design/tasks) into a separate reference file and signaling it from SKILL.md to improve progressive disclosure and trim the main body.

Dimension	Reasoning	Score
Conciseness	The body is efficient and assumes Claude's competence (no generic-concept padding), but carries minor redundancy — the IMPORTANT context/rules note appears twice and the artifact-patterns section is long — so it is not fully lean at a 5.	4 / 5
Actionability	Concrete, executable CLI commands (`openspec list/status/instructions`) with documented JSON fields provide mostly copy-paste-ready guidance, but the core artifact-creation step is template-filling guidance rather than executable code, leaving a minor gap.	4 / 5
Workflow Clarity	A clear 4-step branched sequence with STOP checkpoints, a Guardrails checklist, and a 'verify the artifact file exists' validation step is present, but explicit error-recovery (fix→retry) loops are thin, stopping short of a 5.	4 / 5
Progressive Disclosure	No bundle files exist; the skill is a single well-sectioned file with clear headers and no nested references, which is appropriate for a CLI workflow, though the spec-driven artifact-patterns section could conceivably live in a reference file.	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-constructed with a clear what/when structure and an explicit 'Use when...' clause containing multiple natural triggers. Its only weakness is limited action specificity — it restates one action rather than enumerating several — and a slightly generic trigger that weakens distinctiveness.

Dimension	Reasoning	Score
Specificity	Names the domain ('OpenSpec change') and one concrete action ('creating the next artifact'), but only restates that single action rather than listing several, matching the '1-2 concrete actions, not comprehensive' anchor.	3 / 5
Completeness	Explicitly answers what ('Continue working on an OpenSpec change by creating the next artifact') and when ('Use when the user wants to progress their change...') with concrete trigger phrases, satisfying the top anchor.	5 / 5
Trigger Term Quality	Includes natural phrases users would say ('progress their change', 'create the next artifact', 'continue their workflow'), giving good keyword coverage, though it lacks the comprehensive synonym/extension spread of a 5.	4 / 5
Distinctiveness Conflict Risk	The 'OpenSpec change' framing carves a clear niche, but the generic trigger 'continue their workflow' carries minor overlap risk with general workflow-continuation skills, keeping it just below a 5.	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: Draculabo/AntigravityManager
Path: .agent/skills/openspec-continue-change/SKILL.md
Commit: e29cfdc

Reviewed: 1 day 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.