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

76%

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 ./.github/skills/openspec-apply-change/SKILL.md

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

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 body is a well-structured, actionable workflow with concrete CLI commands, explicit state handling, and clear guardrails. It is slightly verbose in its output templates and lacks an explicit validation/test feedback loop before marking batch tasks complete.

Suggestions

Add an explicit validation checkpoint (e.g., run tests or verify the change compiles) before flipping a task's checkbox to complete, to satisfy the feedback-loop expectation for batch operations.

Trim or collapse the three full output templates into one compact example with placeholders to reduce token cost.

Merge 'Fluid Workflow Integration' into the existing guardrails to avoid restating the same pause-on-issue guidance twice.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean with inline CLI commands and no padding about concepts Claude already knows; the three full output templates and the 'Fluid Workflow Integration' section (which restates guardrails) are mildly trimmable, fitting the 'efficient with minor over-explanation' anchor.	4 / 5
Actionability	Concrete, executable commands (openspec status/instructions/list with --json), an explicit checkbox-flip instruction (`- [ ]` -> `- [x]`), and a named tool (AskUserQuestion) give mostly executable guidance; only minor gaps (no exact code for marking tasks) keep it below fully copy-paste-ready.	4 / 5
Workflow Clarity	A clear 7-step numbered sequence with explicit state handling (blocked, all_done), pause conditions, and guardrails provides most checkpoints; the batch task loop lacks an explicit 'verify changes / run tests before marking complete' feedback loop, so it falls just short of the top anchor.	4 / 5
Progressive Disclosure	The single SKILL.md is well-organized into clearly signaled sections with no nested references; no bundle files exist, and the content is appropriately self-contained, matching the 'good structure, minor organization gaps' anchor.	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 clear and complete, giving both a concrete capability statement and an explicit, trigger-rich 'Use when' clause. It is slightly light on enumerated specific actions and synonymous trigger terms, which keeps specificity and trigger quality below the top anchors.

Suggestions

Expand the capability clause with 1-2 more concrete actions (e.g., "mark tasks complete, navigate schema-driven task lists") to lift specificity.

Add a few natural synonyms users might say (e.g., "build", "finish", "do the tasks") to broaden trigger-term coverage.

Keep the OpenSpec qualifier prominent in every trigger phrase to maximize distinctiveness against generic task skills.

Dimension	Reasoning	Score
Specificity	Names the OpenSpec-change domain and one concrete action ("Implement tasks from an OpenSpec change") but offers no further specific actions, matching the anchor for domain plus 1-2 concrete actions without comprehensive coverage.	3 / 5
Completeness	It explicitly states what ("Implement tasks from an OpenSpec change") and when ("Use when the user wants to start implementing, continue implementation, or work through tasks") with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	"start implementing, continue implementation, or work through tasks" are natural phrases users would say, giving good keyword coverage; a few common variants (e.g., "build the change", "do the tasks") are absent, keeping it just below the comprehensive anchor.	4 / 5
Distinctiveness Conflict Risk	The OpenSpec-change scope and explicit triggers give it a clear niche with minimal conflict risk; "implement tasks" alone is somewhat generic without the OpenSpec qualifier, so it falls just short of the clearest-niche anchor.	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: arm/mlia
Path: .github/skills/openspec-apply-change/SKILL.md
Commit: e91557a

Reviewed: 5 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.