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

67%

Does it follow best practices?

Impact

87%

1.06x

Average score across 3 eval scenarios

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./.github/skills/openspec-apply-change/SKILL.md

Quality

Content

77%

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

This is a well-structured, actionable skill with clear workflow sequencing and good error handling/pause conditions. Its main weakness is moderate verbosity—some information is repeated across sections (contextFiles explanation, schema references) and the inline output templates add length. The skill effectively guides Claude through a complex multi-step implementation loop with appropriate checkpoints.

Suggestions

Consolidate the schema-specific contextFiles explanation into a single mention rather than repeating it in steps 2, 4, and guardrails.

Consider moving the three output format templates to a referenced file to reduce inline bulk, or combine them into a more compact format specification.

Dimension	Reasoning	Score
Conciseness	The skill is reasonably efficient but includes some redundant explanations (e.g., explaining what contextFiles might contain for different schemas multiple times, restating pause conditions). The output format examples are useful but add length. Some sections like 'Fluid Workflow Integration' could be tighter.	2 / 3
Actionability	Provides concrete CLI commands (`openspec status --change "<name>" --json`, `openspec instructions apply --change "<name>" --json`, `openspec list --json`), specific JSON fields to parse, exact checkbox syntax for marking tasks complete (`- [ ]` → `- [x]`), and clear output format templates. Guidance is specific and executable.	3 / 3
Workflow Clarity	The multi-step workflow is clearly sequenced (select → status → instructions → read context → show progress → implement loop → completion). It includes explicit validation/pause checkpoints (blocked state handling, unclear tasks, design issues, errors), feedback loops (continue until done or blocked), and clear state-dependent branching.	3 / 3
Progressive Disclosure	The content is well-structured with clear sections and headers, but it's a monolithic document with no references to supporting files. The three output format examples (implementation, completion, pause) are inline and add bulk. With no bundle files provided, there's no external structure to leverage, but the skill could benefit from separating output templates or guardrails into referenced files.	2 / 3
	Total	10 / 12 Passed

Description

57%

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 benefits from having an explicit 'Use when' clause and mentioning the specific 'OpenSpec' domain, but it is severely lacking in specificity about what concrete actions the skill performs. The vague language ('implement tasks', 'work through tasks') makes it hard to distinguish from other implementation-related skills and gives Claude little information about what this skill actually does.

Suggestions

Add specific concrete actions the skill performs, e.g., 'Reads OpenSpec change definitions, generates code implementations, tracks task completion status, and validates implementations against spec requirements.'

Include more natural trigger terms and variations users might say, such as 'openspec', 'spec tasks', 'change implementation', 'spec changes', or file extensions/formats associated with OpenSpec.

Clarify what 'OpenSpec' is briefly to help distinguish this skill from generic task implementation skills, e.g., 'Implements code changes defined in OpenSpec specification files (.openspec).'

Dimension	Reasoning	Score
Specificity	The description uses vague language like 'implement tasks' and 'work through tasks' without specifying what kind of tasks, what domain, or what concrete actions are performed. 'OpenSpec change' is mentioned but no specific capabilities are listed.	1 / 3
Completeness	The description answers both 'what' (implement tasks from an OpenSpec change) and 'when' (when the user wants to start implementing, continue implementation, or work through tasks) with explicit trigger guidance using a 'Use when' clause.	3 / 3
Trigger Term Quality	Includes some relevant terms like 'implementing', 'continue implementation', and 'work through tasks' that users might say. However, 'OpenSpec' is a specific term that helps with matching, though common variations or synonyms are missing. The trigger terms are somewhat narrow.	2 / 3
Distinctiveness Conflict Risk	The mention of 'OpenSpec' provides some distinctiveness, but 'implement tasks' and 'work through tasks' are very generic phrases that could overlap with many other implementation or task-management skills. Without more specificity about what OpenSpec is or what kind of implementation, there's moderate conflict risk.	2 / 3
	Total	8 / 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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: arm/mlia
Commit: 3e21e30

Reviewed: 3 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.