openspec-apply-change

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

Quality

72%

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 ./.claude/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.

The body is highly actionable with concrete CLI commands and a well-sequenced, validated workflow including error-feedback loops. It loses points mainly for conciseness redundancy and for being a monolithic file with no progressive disclosure to supporting references.

Suggestions

Remove the Guardrails redundancies that restate Step 6 pause conditions, or fold them into the step to reduce duplicate content.

Trim the three full output template blocks to concise skeletons, keeping only the structurally essential lines.

Consider extracting the long output templates or schema-specific context-file mappings into a reference file to introduce one-level-deep progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is action-oriented and avoids explaining concepts Claude already knows, but the Guardrails section restates Step 6 pause conditions and the full output templates are lengthy, fitting the score 2 anchor for mostly efficient with some tightening possible.	2 / 3
Actionability	Provides concrete executable commands (openspec status/instructions/list with --json), a concrete file-edit instruction (- [ ] to - [x]), and a named tool (AskUserQuestion), matching the score 3 anchor for fully executable, copy-paste-ready guidance.	3 / 3
Workflow Clarity	Seven numbered steps are clearly sequenced with explicit state handling (blocked, all_done) and pause-on-error feedback loops, satisfying the score 3 anchor for a clear sequence with validation checkpoints and error recovery.	3 / 3
Progressive Disclosure	Sections are well-organized, but the skill is a monolithic single file over the 50-line simple-skill carve-out with no one-level-deep references, matching the score 2 anchor for some structure but content that could be split remaining inline.	2 / 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, explicitly covering both what the skill does and when to use it with natural trigger phrasing. It is held back from a top score by listing only a single action and by potential overlap with sibling openspec skills.

Suggestions

Enumerate the concrete actions the skill performs (e.g. select a change, parse status/instructions, mark tasks complete, suggest archival) to raise specificity beyond a single verb.

Broaden trigger terms beyond OpenSpec jargon (e.g. "work through a change's task list", "finish pending implementation tasks") to improve natural keyword coverage.

Differentiate from sibling openspec skills by naming the distinct trigger (apply/implement vs. continue/plan) more sharply.

Dimension	Reasoning	Score
Specificity	Names a concrete domain and one concrete action ("Implement tasks from an OpenSpec change"), but lists only a single action rather than multiple specific capabilities, matching the anchor for score 2.	2 / 3
Completeness	Explicitly states both what ("Implement tasks from an OpenSpec change") and when ("Use when the user wants to start implementing, continue implementation, or work through tasks"), satisfying the score 3 anchor.	3 / 3
Trigger Term Quality	Triggers like "start implementing, continue implementation, or work through tasks" are natural phrasings, but they are anchored to OpenSpec jargon and miss broader common variations, fitting the score 2 anchor.	2 / 3
Distinctiveness Conflict Risk	The OpenSpec-change niche is fairly specific, but the implementation/continue framing could overlap with sibling openspec skills (e.g. continue-change, create-change), matching the score 2 anchor for some overlap risk.	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: PBH-BTN/PeerBanHelper
Path: .claude/skills/openspec-apply-change/SKILL.md
Commit: be872c1

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.