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

Securityby

Passed

No findings from the security scan

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 concrete CLI commands, explicit state handling, and a genuine per-task validation loop. The main cost is repetition: the context/operationGuidance contract and pause conditions each appear two to three times, which inflates the token budget without adding new guidance.

Suggestions

State the context/operationGuidance contract once (in step 3) and collapse the four related Guardrails bullets (194-197) into a single cross-reference, cutting ~15 lines of duplication.

Trim the Guardrails list to only rules not already stated verbatim in the Steps and Pause-if sections (e.g., drop the duplicates of 185-190).

Move the three full output templates into a short reference section or keep only one canonical example, since the completed/paused templates are close structural variants of each other.

Dimension	Reasoning	Score
Conciseness	Mostly efficient, workflow-specific instruction with no basic-concept padding, but the context/operationGuidance contract is stated three times (lines 71-84, 93-94, and again as four guardrail bullets at 194-197), and the Guardrails section restates the step-level pause conditions almost verbatim. Anchor 3 ('could be tightened') fits; it does not reach anchor 4 because the redundancy is more than minor.	3 / 5
Actionability	Every step carries copy-paste-ready commands with exact flags ('openspec status --change "<name>" --json', 'openspec instructions apply --change "<name>" --json'), concrete state handling (blocked/all_done), specific checkbox-edit mechanics ('- [ ]' → '- [x]' at the returned sourcePath and line), and filled-in output templates. Fully executable guidance matching anchor 5.	5 / 5
Workflow Clarity	A clearly sequenced 7-step workflow with an explicit feedback loop (rerun apply instructions after each task and confirm progress changed), pre-edit drift check on the checkbox location, explicit blocked/all_done state handling, and enumerated pause conditions. Anchor 5's validation-with-error-recovery pattern is fully present.	5 / 5
Progressive Disclosure	No bundle files exist and all content is inline in SKILL.md, but the ~200-line body is well-sectioned (Store selection, Project check, Steps, Outputs, Guardrails, Fluid Workflow) and everything present is runtime-needed operational guidance rather than reference material that clearly belongs in separate files. Good structure with minor organization gaps (e.g., the output templates could live in a reference file), matching anchor 4 rather than anchor 5's well-signaled external references.	4 / 5
	Total	17 / 20 Passed

Description

86%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 tight, well-structured description that clearly states both what the skill does and when to use it, with strong trigger coverage including exact CLI synonyms. Its only weaknesses are thin capability detail (a single action verb) and mildly generic natural-language triggers that create slight overlap risk with general implementation requests.

Suggestions

Add 1-2 concrete capability details to the 'what' clause, e.g., 'Implement tasks from an OpenSpec change: read planning artifacts, execute pending tasks, and update task progress via the openspec CLI.'

Qualify the generic triggers with the domain to reduce misfires, e.g., 'Use when the user wants to implement or continue an OpenSpec change' rather than 'work through tasks'.

Dimension	Reasoning	Score
Specificity	"Implement tasks from an OpenSpec change" names the domain and one concrete action, but offers no further detail on what implementation involves (e.g., reading artifacts, updating task checkboxes, reporting progress). This matches anchor 3 (1-2 concrete actions, not comprehensive) and falls clearly short of anchor 4's "several specific actions".	3 / 5
Completeness	Explicitly answers what ("Implement tasks from an OpenSpec change") and when ("Use when the user wants to start implementing... Also use when the user says 'openspec apply'...") with concrete trigger phrases. This matches anchor 5 exactly; anchor 4 would require the 'when' to be less explicit, which it is not.	5 / 5
Trigger Term Quality	Covers natural user phrasings ("start implementing", "continue implementation", "work through tasks") plus exact CLI invocations and their synonym ("openspec apply", "opsx apply", "openspec implement"). Coverage is comprehensive for this domain, matching anchor 5.	5 / 5
Distinctiveness Conflict Risk	The OpenSpec command triggers are highly distinct, but the generic phrases "start implementing", "continue implementation", or "work through tasks" could plausibly fire for non-OpenSpec implementation requests. Mostly distinct with minor overlap risk against general coding/implementation skills, matching anchor 4 rather than anchor 5's "minimal conflict risk".	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: Fission-AI/OpenSpec
Path: skills/openspec-apply-change/SKILL.md
Commit: 2500d6d

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.