openspec-apply-change

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

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

Quality

Content

67%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.

A clear, actionable workflow document with concrete CLI commands and explicit state/pause handling. The chief weakness is token efficiency, driven by redundant guardrails restating the step-level pause conditions and verbose output templates.

Suggestions

Collapse the Guardrails section or fold it into the relevant steps; its pause/ambiguity guidance duplicates the 'Pause if' block under Step 6.

Trim the three output templates to a compact schema (headers + key fields) rather than full annotated examples, reducing token cost without losing the format contract.

Add an explicit validation/re-check command for the implementation loop (e.g., re-running `openspec status` after marking tasks complete) to lift workflow_clarity toward 5.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and assumes competence, but the Guardrails section reiterates the Pause-if conditions already stated in Steps, and the three output templates are somewhat padded. Not a 4 because these redundancies are noticeable rather than minor.	3 / 5
Actionability	Provides concrete executable commands (`openspec status --change`, `openspec instructions apply`), specific JSON fields to parse, and an explicit checkbox update convention (`- [ ]` to `- [x]`). Falls short of 5 because it stops short of copy-paste-ready code for the implementation loop itself.	4 / 5
Workflow Clarity	A clear 7-step sequence with explicit state handling ('blocked', 'all_done') and pause/feedback checkpoints ('Pause if: task is unclear', 'Error or blocker encountered → report and wait'). Not a 5 because validation checkpoints are advisory rather than enforced with a concrete re-check command.	4 / 5
Progressive Disclosure	No bundle files exist, so this is scored on body structure alone: well-organized sections (Steps, Output templates, Guardrails, Fluid Workflow Integration) with clear headers and no nested references. Not a 5 because the output templates could arguably live in a separate reference, leaving the main body leaner.	4 / 5
	Total	15 / 20 Passed

Description

83%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.

A strong, well-formed description that explicitly states what the skill does and when to invoke it with natural trigger terms. The main room for improvement is breadth of action coverage and synonyms.

Dimension	Reasoning	Score
Specificity	Names the domain (OpenSpec change) and several concrete actions — 'start implementing', 'continue implementation', 'work through tasks' — with only minor coverage gaps. It does not reach a 5 because the action list is narrowly about implementing tasks rather than a comprehensive set of distinct capabilities.	4 / 5
Completeness	Explicitly answers both '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 anchor exactly.	5 / 5
Trigger Term Quality	Includes natural phrasings a user would say ('start implementing', 'continue implementation', 'work through tasks') with good coverage but few synonyms or file extensions, falling just short of comprehensive. Not a 3 because the listed terms are genuinely natural user language rather than technical jargon.	4 / 5
Distinctiveness Conflict Risk	Clearly scoped to OpenSpec changes with distinct triggers and minimal conflict risk, though it shares some surface with generic code-implementation skills. Not a 5 because 'work through tasks' could conceivably overlap with adjacent task-tracking skills.	4 / 5
	Total	17 / 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: fengshao1227/ccg-workflow
Path: .agents/skills/openspec-apply-change/SKILL.md
Commit: cc8cc34

Reviewed: 1 day 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.