openspec-apply-change

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

Quality

70%

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

Quality

Content

61%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 provides a clear, executable workflow built around concrete openspec CLI commands with explicit state handling and pause conditions. Its weaknesses are redundancy between step 6, the guardrails, and the output templates, and the absence of any verification checkpoint before marking tasks complete in a batch implementation loop.

Suggestions

Add a validation checkpoint per task (e.g., run relevant tests/build before flipping "- [ ]" to "- [x]") to satisfy the batch-operation feedback-loop requirement and raise workflow clarity.

Deduplicate the pause conditions stated in step 6 and repeated in the Guardrails section, and merge the three overlapping output templates into one template with optional sections.

Specify concretely where the tasks file lives (e.g., a typical contextFiles path pattern) so the checkbox update step is unambiguous without relying solely on CLI output inspection.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient — numbered steps, short command blocks, no explanations of concepts Claude already knows. However, it could be tightened: pause conditions appear twice ("Pause if:" in step 6 and again in "Guardrails"), and three full output template blocks overlap substantially with the step instructions. This fits 'mostly efficient but includes some unnecessary explanation or could be tightened', not the lean anchor 5.	3 / 5
Actionability	Commands are concrete and copy-paste ready ("openspec status --change \"<name>\" --json", "openspec instructions apply --change \"<name>\" --json", "openspec list --json") and task completion is mechanically specified ("- [ ] → - [x]"). Not a 5 because a few execution details are left implicit — e.g., the exact tasks file to edit is only identified indirectly via contextFiles, and no sample JSON output shapes are given to confirm parsing.	4 / 5
Workflow Clarity	There is a clear 7-step sequence with state handling ("state: \"blocked\"", "state: \"all_done\"") and pause conditions, but no validation/verification checkpoint after implementing each task (e.g., run tests/build before marking "- [x]"). Since step 6 is a batch operation ("loop until done or blocked" over all pending tasks), the rubric's cap of 3 for batch workflows without validation applies; it exceeds anchor 2 because the sequence and branch handling are well defined.	3 / 5
Progressive Disclosure	The content is well organized into labeled sections (steps, output templates, guardrails, workflow integration) with no nested references and no bundle files — everything needed is inline and CLI-driven. It matches 'good structure; most content is appropriately placed; minor organization gaps' rather than a 5, since the skill exceeds 50 lines and the three separate output templates plus the redundant guardrails block could be consolidated or trimmed.	4 / 5
	Total	14 / 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 concise, third-person, and explicitly pairs a clear capability statement with a well-formed 'Use when...' trigger clause covering several natural phrasings. Its main weakness is limited action coverage — it lists only 'implement tasks' without naming supporting behaviors — and it omits some obvious synonyms like 'apply a change'.

Suggestions

Enumerate a couple more concrete actions (e.g., 'Implement tasks from an OpenSpec change, reading change artifacts and marking task progress') to lift specificity.

Add common synonyms users would say, such as 'apply a change', 'execute pending tasks', or 'pick up implementation where it left off', to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	"Implement tasks from an OpenSpec change" names the domain (OpenSpec change) and one concrete action (implement tasks), matching the anchor for naming the domain plus 1-2 concrete actions. Not a 4 because only a single action is listed — there is no enumeration of what implementation involves (e.g., reading artifacts, marking tasks complete).	3 / 5
Completeness	It 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. This mirrors the anchor-5 good example structure (action statement plus an explicit 'Use when...' clause with multiple triggers).	5 / 5
Trigger Term Quality	The phrase "Use when the user wants to start implementing, continue implementation, or work through tasks" captures several natural user phrasings. Not a 5 because common synonyms such as "apply a change", "execute tasks", or "build the change" are missing, and no related file/CLI trigger terms beyond "implement" appear.	4 / 5
Distinctiveness Conflict Risk	"OpenSpec change" establishes a clear niche, so it is mostly distinct from other skills. Not a 5 because generic phrases like "start implementing" and "work through tasks" could also match general coding-implementation skills, creating minor overlap risk.	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: KunAgent/Kun
Path: .claude/skills/openspec-apply-change/SKILL.md
Commit: ebce7f6

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.