openspec-apply-change

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

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/openspec-apply-change/SKILL.md

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with concrete CLI commands and a well-validated multi-step workflow including error feedback loops. It loses points on conciseness from redundant guardrails/output templates and on progressive disclosure from keeping all detail inline in a longer single file.

Suggestions

Trim the Guardrails section to only items not already stated in the numbered steps, or fold it into the relevant step, to remove redundancy.

Consider moving the three full output templates to a short reference file (or condensing them to one template with variant notes) to reduce inline length and improve progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete commands, but the Guardrails section restates steps 6-7 and three full output templates add length that could be tightened, fitting the 'mostly efficient but includes some unnecessary explanation' anchor rather than the lean score-3.	2 / 3
Actionability	It gives copy-paste-ready commands (e.g., `openspec status --change "<name>" --json`, `openspec instructions apply --change "<name>" --json`) plus a concrete `- [ ]` -> `- [x]` checkbox instruction, matching fully executable guidance.	3 / 3
Workflow Clarity	A clear 7-step sequence is paired with explicit validation (status/schema parsing, blocked/all_done state handling) and pause-on-error or pause-on-ambiguity feedback loops, satisfying the clear-sequence-with-checkpoints anchor.	3 / 3
Progressive Disclosure	There are no bundle files and the single SKILL.md is well-sectioned, but at ~160 lines it exceeds the under-50-line auto-3 threshold and keeps three output templates plus guardrails inline with no one-level-deep references, fitting the score-2 'content that should be separate is inline' anchor.	2 / 3
	Total	10 / 12 Passed

Description

67%

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 cleanly answers both what the skill does and when to use it, with a concrete OpenSpec niche. It is held back by a single named action, limited trigger variation, and some overlap risk with sibling openspec skills.

Suggestions

List a couple more concrete actions (e.g., "run tasks, mark progress, and surface blockers") to lift specificity from a single verb to multiple concrete operations.

Broaden trigger phrasing with natural user variations like "implement a change", "work through pending tasks", or "resume an OpenSpec change".

Differentiate from openspec-continue-change by scoping the trigger to starting/working through tasks rather than "continue implementation".

Dimension	Reasoning	Score
Specificity	"Implement tasks from an OpenSpec change" names the domain and a single action but does not list multiple concrete operations, matching the 'names domain and some actions, but not comprehensive' anchor rather than the vague score-1 or the multi-action score-3.	2 / 3
Completeness	It states the "what" ("Implement tasks from an OpenSpec change") and an explicit "Use when the user wants to start implementing, continue implementation, or work through tasks" trigger, clearly answering both what and when.	3 / 3
Trigger Term Quality	The triggers "start implementing, continue implementation, or work through tasks" are natural phrases a user might say, but they lean on a single internal concept with few common variations, so coverage is partial rather than the broad score-3 set.	2 / 3
Distinctiveness Conflict Risk	"OpenSpec change" is a clear niche, but the "continue implementation" trigger could overlap with the sibling openspec-continue-change skill referenced in the body, so it is not yet a clean score-3 distinct trigger set.	2 / 3
	Total	9 / 12 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: 6a5171e

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.