openspec-apply-change

Implement tasks from an OpenSpec change. Use when the user wants to start implementing, continue implementation, or work through tasks.

1.06x

Quality

70%

Does it follow best practices?

Impact

87%

1.06x

Average score across 3 eval scenarios

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.codex/skills/openspec-apply-change/SKILL.md

The canonical home for this skill is openspec-apply-change in fengshao1227/ccg-workflow

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable with concrete commands and clear sequencing, and it avoids teaching concepts Claude already knows. Its main gaps are a missing verification gate in the task loop and mild redundancy between the Guardrails and Steps sections.

Suggestions

Add an explicit verification step in the task loop (e.g. run tests or re-run `openspec status` to confirm progress) before marking a task complete, since this is a batch code-edit workflow.

Remove Guardrails entries that restate the Steps (read context files first, keep changes minimal, pause on ambiguity) and keep only genuinely additive guardrails to reduce redundancy.

Consider extracting the three large output templates into a referenced file so the main body stays a lean overview, improving progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence with no conceptual padding, but the Guardrails section repeats guidance already stated in the steps (read context files, keep changes minimal, pause on ambiguity), which could be tightened.	2 / 3
Actionability	It provides concrete, copy-ready CLI commands (e.g. `openspec status --change "<name>" --json`, `openspec instructions apply --change "<name>" --json`), explicit checkbox syntax (`- [ ]` -> `- [x]`), and full output templates, matching the fully-executable level-3 anchor.	3 / 3
Workflow Clarity	The 7-step sequence is clear with state handling (blocked/all_done/proceed) and pause conditions, but for a batch code-edit workflow there is no explicit verification checkpoint before marking each task complete, capping it below level 3 per the destructive/batch guidance.	2 / 3
Progressive Disclosure	The skill is self-contained with well-organized sections and no nested references, but it is a single monolithic file with large inline output templates and no file-split structure, fitting level 2 rather than the well-signaled multi-file level 3.	2 / 3
	Total	9 / 12 Passed

Description

75%

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 cleanly states a distinct purpose with an explicit trigger clause, covering both what and when. It is held back from a higher ceiling only by limited action breadth and somewhat generic trigger phrasing.

Dimension	Reasoning	Score
Specificity	It names the domain and a concrete action ("Implement tasks from an OpenSpec change") but lists only a single action rather than a comprehensive set, matching the 'names domain and some actions' anchor rather than the multiple-actions level 3.	2 / 3
Completeness	It answers both what ("Implement tasks from an OpenSpec change") and when via an explicit "Use when..." clause with concrete triggers, matching the level-3 anchor.	3 / 3
Trigger Term Quality	Triggers like "start implementing, continue implementation, work through tasks" are reasonably natural but lean generic and omit common concrete variations a user might say, fitting the 'some relevant keywords but missing common variations' anchor.	2 / 3
Distinctiveness Conflict Risk	The OpenSpec-change framing carves a clear niche with distinct triggers unlikely to fire for unrelated skills, matching the level-3 anchor; it is not above 3 because that is the scale ceiling.	3 / 3
	Total	10 / 12 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: arm/mlia
Path: .codex/skills/openspec-apply-change/SKILL.md
Commit: 746b755

Reviewed: about 12 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.