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

—

Does it follow best practices?

Impact

87%

1.06x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Quality

Content

72%

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 procedural skill with concrete commands and templates and good organization, but it has some redundancy across sections and is missing an explicit verification checkpoint in its batch task loop.

Suggestions

Consolidate the Guardrails and Fluid Workflow Integration sections into the relevant steps to remove repetition and tighten the token budget.

Add an explicit verification step per task (e.g., 'run tests or build before marking - [x]') so the batch task loop has a real validation checkpoint, lifting workflow clarity to level 3.

Dimension	Reasoning	Score
Conciseness	The body is mostly action-oriented and avoids explaining concepts Claude already knows, but the Guardrails and Fluid Workflow Integration sections restate guidance already covered in the numbered steps, so it could be tightened to remove redundancy.	2 / 3
Actionability	It provides copy-paste-ready, executable CLI commands (openspec status/instructions/list with --json), concrete JSON fields to parse, an explicit checkbox syntax (- [ ] to - [x]), and ready-made output templates, matching the 'fully executable commands; copy-paste ready' anchor.	3 / 3
Workflow Clarity	The 7-step sequence is clear with state handling (blocked/all_done) and pause conditions, but for a batch task loop it lacks an explicit verification step (e.g., run tests / confirm changes work) before marking each task complete, so validation is implicit and workflow clarity is capped at 2 per the batch-operations guideline.	2 / 3
Progressive Disclosure	No bundle files exist and none are needed; the content is a self-contained procedural workflow organized into clear sections (Steps, Output templates, Guardrails, Fluid Workflow) with no nested references, so it scores 3 on well-organized structure without requiring external file splitting.	3 / 3
	Total	10 / 12 Passed

Description

67%

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 clear and complete with an explicit 'Use when' trigger, but it names only a single action and its trigger phrasing overlaps with related OpenSpec skills, leaving it in the middle of the scale on specificity, trigger quality, and distinctiveness.

Suggestions

Expand the action list beyond 'implement tasks' to concrete specifics (e.g., 'read context files, make code changes, mark tasks complete, track progress') to lift specificity to level 3.

Add more natural user phrasings (e.g., 'apply a change', 'work on tasks', 'pick up where I left off on a change') to broaden trigger-term coverage.

Differentiate from continue-change by scoping the trigger to starting/applying (e.g., 'Use when starting to apply or work through tasks of an OpenSpec change') to reduce conflict risk.

Dimension	Reasoning	Score
Specificity	It names a concrete domain and a single concrete action ("Implement tasks from an OpenSpec change") but lists only one action rather than multiple specific actions, so it stops at the 'names domain and some actions' anchor rather than reaching the multi-action level 3.	2 / 3
Completeness	It explicitly answers both 'what' ('Implement tasks from an OpenSpec change') and 'when' with an explicit 'Use when the user wants to start implementing, continue implementation, or work through tasks' trigger clause, matching the level-3 anchor.	3 / 3
Trigger Term Quality	The 'Use when' clause supplies relevant phrases ('start implementing, continue implementation, work through tasks'), but these are tied to the jargon term 'OpenSpec change' and miss common natural variations a user might say, fitting the 'some relevant keywords but missing common variations' anchor.	2 / 3
Distinctiveness Conflict Risk	'OpenSpec change' gives it a specific niche, but the trigger 'continue implementation' overlaps with sibling skills like openspec-continue-change (referenced in the body), so it could still trigger for the wrong skill.	2 / 3
	Total	9 / 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
Commit: 053fcb5

Reviewed: 12 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.