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 highly actionable, well-sequenced workflow with strong validation checkpoints and feedback loops. Its weaknesses are redundancy — guardrails restate inline step guidance, and the context/operationGuidance rules appear twice — and a single-file structure that inlines niche edge-case handling.

Suggestions

Deduplicate the Guardrails section against the inline step guidance: the pause conditions, sourcePath/line rule, and context/operationGuidance contract are each stated twice.

Move the store-selection and root-null edge-case handling into a reference file (e.g., references/stores.md) and keep a one-line pointer in SKILL.md to slim the body.

Replace the three repeated "suggest review or verification as appropriate before archiving" phrasings with a single defined completion step referenced from each output template.

DimensionReasoningScore

Conciseness

Most tokens carry CLI-specific semantics Claude cannot know (store stickiness, root: null handling, blocked states), but the context/operationGuidance contract is stated twice (step 3 and Guardrails), "suggest review or verification as appropriate before archiving" appears three times, and the "Pause if" list duplicates the Guardrails section — it could be tightened.

3 / 5

Actionability

Fully executable throughout: copy-paste commands with flags (openspec status --change "<name>" --json), named JSON fields to parse, the exact checkbox edit (- [ ] to - [x]), and concrete output templates for completion and pause.

5 / 5

Workflow Clarity

A clear 7-step sequence with explicit state handling (blocked/all_done), validation feedback loops (rerun instructions after each task, confirm progress changed, refresh sourcePath/line before editing), defined pause conditions, and a guardrail checklist.

5 / 5

Progressive Disclosure

The single file is well-organized with clear sections and headers, and the core workflow belongs inline, but at ~195 lines the dense store-selection and root-null edge-case prose is inline detail that would fit a reference file, leaving minor organization gaps.

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-based triggers. Its main weakness is thin capability coverage — it describes a single action with variations rather than enumerating what the workflow involves (change selection, context reading, task tracking).

Suggestions

Enumerate the concrete sub-actions (select the change, read context artifacts, implement tasks in order, track progress) instead of restating one action three ways.

Add a natural synonym trigger such as "apply a change" or "work on the tasks for a change" to broaden keyword coverage.

DimensionReasoningScore

Specificity

"Implement tasks from an OpenSpec change" names the domain and one concrete action, but "start implementing, continue implementation, or work through tasks" are variations of that single action rather than a list of several distinct capabilities, matching anchor 3.

3 / 5

Completeness

It clearly answers both questions: the what ("Implement tasks from an OpenSpec change") and an explicit when ("Use when the user wants to... Also use when the user says...") with concrete trigger phrases and command names.

5 / 5

Trigger Term Quality

Natural phrases ("start implementing", "continue implementation", "work through tasks") plus exact command triggers ("openspec apply", "opsx apply", "openspec implement") give good coverage, though a few natural synonyms like "do the tasks" or "apply the change" are missing.

4 / 5

Distinctiveness Conflict Risk

The OpenSpec/opsx command triggers carve out a clear niche, but the generic phrase "work through tasks" could overlap with unrelated task-management skills, so minor overlap risk remains.

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

Fission-AI/OpenSpec

Path

test/fixtures/released-output/v1.16.0-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.