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.

A strong, highly actionable workflow skill: concrete commands, explicit JSON parsing targets, exact checkbox-edit mechanics, and genuine feedback loops (stale-location check, rerun-and-verify after each task) with well-handled blocked/all_done states. Its weaknesses are redundancy — context/operationGuidance rules and pause conditions are restated across steps and guardrails — and a monolithic single-file layout that inlines material (output templates, store-selection details) that could be split into references. Neither weakness undermines the clarity of the executable workflow.

Suggestions

State the context/operationGuidance behavior contract once (in step 3) and reduce the guardrail bullets to a one-line pointer, cutting three duplicated bullets and the repeat in step 4.

Consolidate the duplicated completion messaging ("suggest review or verification as appropriate before archiving" appears in step 3, step 7, and the output template) into the output template only.

Move the three full output templates into an assets/reference file (or trim to one exemplar) to reduce inline bulk and improve progressive disclosure.

DimensionReasoningScore

Conciseness

The body is procedural and assumes Claude's competence (no concept explanations), but rules are duplicated across sections: context/operationGuidance handling is stated in step 3, restated in step 4, and repeated as three guardrail bullets; "suggest review or verification as appropriate before archiving" appears in both step 3 and step 7 plus the output template. Mostly efficient but could be tightened fits anchor 3; the repetition exceeds the 'minor instances' of anchor 4.

3 / 5

Actionability

Guidance is fully executable: copy-paste-ready commands ("openspec status --change \"<name>\" --json", "openspec instructions apply --change \"<name>\" --json"), concrete JSON fields to parse (schemaName, contextFiles, sourcePath, line), the exact checkbox edit ("- [ ]\" → \"- [x]"), and complete output templates. This matches anchor 5's copy-paste-ready coverage of the common cases.

5 / 5

Workflow Clarity

A clear 7-step sequence with explicit validation and feedback loops: before editing, confirm the checkbox at the returned sourcePath/line still matches and rerun instructions if stale; after completing a task, "rerun the apply instructions and confirm that task is now done and progress changed." Blocked/all_done state handling and enumerated pause conditions provide checkpoints and error-recovery paths, matching anchor 5.

5 / 5

Progressive Disclosure

No bundle files exist and the body references no external files; content is well-sectioned (Store selection, Project check, Input, Steps, Output templates, Guardrails). This is good structure with minor organization gaps (anchor 4): the ~195-line body keeps the store-selection logic and three full output templates inline, and the under-50-line simple-skill exception for a reference-free 5 does not apply.

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.

A well-formed description with an explicit what/when structure and strong command-phrase triggers that clearly tie it to the OpenSpec CLI. Its main limitation is thin capability coverage — it names the single overarching action rather than enumerating what the workflow concretely does. Trigger phrasing is good but includes a broad generic clause that slightly raises overlap risk with general implementation skills.

DimensionReasoningScore

Specificity

"Implement tasks from an OpenSpec change" names the domain and one concrete action but does not list several distinct capabilities (e.g., reading artifacts, updating task checkboxes, reporting progress). It matches the anchor 'Names domain and 1-2 concrete actions, but not comprehensive' — above 2 because the action is concrete, below 4 because there is no multi-action list.

3 / 5

Completeness

It explicitly answers both questions: what ("Implement tasks from an OpenSpec change") and when ("Use when the user wants to start implementing, continue implementation, or work through tasks. Also use when the user says 'openspec apply'..."), with concrete trigger phrases. This matches anchor 5; the 'when' is explicit and specific, not merely present.

5 / 5

Trigger Term Quality

Triggers include natural phrases ("start implementing", "continue implementation", "work through tasks") and exact CLI invocations ("openspec apply", "opsx apply", "openspec implement"), giving good keyword coverage. A few natural variants ("apply this change", "finish the tasks") are missing, so it fits anchor 4 rather than comprehensive anchor 5.

4 / 5

Distinctiveness Conflict Risk

The OpenSpec/opsx command triggers carve out a clear niche with minimal conflict risk, but the generic clause "start implementing, continue implementation, or work through tasks" could overlap with other implementation-workflow skills. Mostly distinct with minor overlap risk fits anchor 4; not 5 because of that broad trigger clause.

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

.agents/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.