CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

openspec-apply-change

Implement tasks from an OpenSpec change. Use when the user wants to start implementing, continue implementation, or work through tasks. Also use when the user says "openspec apply", "opsx apply", or "openspec implement".

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

81%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 content is a highly actionable, well-sequenced workflow with concrete CLI commands, explicit state handling, and validation feedback loops. Its main weakness is token efficiency: the context/operationGuidance contract and the pause conditions are each repeated several times across sections, and the single long file could be consolidated or split.

Suggestions

State the context/operationGuidance contract once in a single section (or one guardrail block) and reference it from steps 3-4 instead of repeating the rules four times.

Merge the step 6 pause conditions with the Guardrails list, which currently duplicates them nearly verbatim.

Consider moving the three output templates into a referenced file to shorten the always-loaded body and improve navigation of the single-file structure.

DimensionReasoningScore

Conciseness

The body is dense with skill-specific guidance and avoids explaining general concepts, but it is noticeably repetitive: the context/operationGuidance handling rules appear in step 3, again in a dedicated paragraph, again in step 4, and again in three separate guardrail bullets, and the pause conditions are stated in both step 6 and Guardrails. This matches 'mostly efficient but could be tightened' rather than the more severely padded 2 anchor.

3 / 5

Actionability

Guidance is fully executable: copy-paste commands ('openspec status --change "<name>" --json', 'openspec instructions apply --change "<name>" --json', 'openspec list --json'), exact JSON fields to parse, and the precise checkbox edit '- [ ]' → '- [x]' at the returned sourcePath and line. Concrete output templates cover the common cases, matching the top anchor.

5 / 5

Workflow Clarity

A clear 7-step sequence with explicit state handling (blocked/all_done/otherwise), a verification feedback loop (rerun apply instructions and confirm the task is done and progress changed), pre-edit re-validation of the checkbox location, and explicit pause conditions. This matches the anchor for clear sequence with explicit validation steps and feedback loops.

5 / 5

Progressive Disclosure

There are no bundle files and no external references; everything lives in a single ~200-line file. Section organization is good (numbered Steps, three labeled Output templates, Guardrails, Fluid Workflow Integration) and no content clearly demands a separate file, matching 'good structure; minor organization gaps'. It falls short of 5 because the length and repetition across sections make the single-file layout harder to navigate than a well-split bundle would be.

4 / 5

Total

17

/

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 well-constructed: it states what the skill does and gives explicit, natural 'Use when' triggers including exact CLI aliases. Its main weaknesses are limited enumeration of concrete capabilities and slightly generic trigger phrasing that extends beyond the OpenSpec niche.

Suggestions

Add one or two more concrete capabilities (e.g., 'tracks task progress by checking off completed tasks') to raise specificity beyond a single action.

Qualify the generic triggers with the OpenSpec context (e.g., 'Use when the user wants to start or continue implementing tasks in an OpenSpec change') to reduce overlap with general implementation requests.

DimensionReasoningScore

Specificity

The description names the domain ('an OpenSpec change') and one concrete action ('Implement tasks'), which matches the anchor for naming a domain with 1-2 concrete actions. It does not enumerate multiple specific capabilities, so it falls short of the 4 anchor.

3 / 5

Completeness

It clearly answers 'what' ('Implement tasks from an OpenSpec change') and explicitly answers 'when' with a 'Use when...' clause and concrete trigger phrases including exact commands, matching the top anchor. It is not a 4 because the 'when' is fully explicit rather than only partially specified.

5 / 5

Trigger Term Quality

It includes natural phrases users would say ('start implementing', 'continue implementation', 'work through tasks') plus literal CLI invocations ('openspec apply', 'opsx apply', 'openspec implement'), giving good keyword coverage. A few natural variations (e.g., 'apply the change', 'work on tasks') are missing, keeping it below the comprehensive 5 anchor.

4 / 5

Distinctiveness Conflict Risk

'OpenSpec change' and the named CLI commands establish a clear niche with distinct triggers, but the generic phrasing 'wants to start implementing, continue implementation, or work through tasks' could overlap with ordinary implementation requests outside OpenSpec. This is mostly distinct with minor overlap risk, not a fully isolated niche.

4 / 5

Total

16

/

20

Passed

Validation

100%

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

finos/morphir-dotnet

Path

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

Reviewed

Table of Contents

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.