openspec-apply-change

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

Quality

80%

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

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 body is a well-sequenced, highly actionable workflow with explicit checkpoints, state handling, and feedback loops. Its weaknesses are conciseness (notable repetition between the inline steps, the context/guidance contract, and the Guardrails section) and progressive disclosure (all content inline for a long skill).

Suggestions

De-duplicate the Guardrails section against the inline pause conditions and the context/operationGuidance contract to remove restated guidance and tighten token use.

Tighten the 'Store selection' paragraph into a short rule plus one example; the sticky-flag explanation can be compressed without losing the override semantics.

Consider moving the three output templates and/or the Guardrails checklist into a references file to improve progressive disclosure for a skill of this length.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete commands, but the long 'Store selection' paragraph, the context/operationGuidance contract block (lines 57-70), and the Guardrails section substantially restate the inline pause conditions and steps, creating padding that could be tightened; this fits the score-3 anchor of mostly efficient with some unnecessary explanation.	3 / 5
Actionability	Copy-paste-ready commands with explicit flags ('openspec status --change "<name>" --json', 'openspec instructions apply --change "<name>" --json'), concrete JSON fields to parse, and literal output templates make the guidance fully executable and covering common cases, matching the score-5 anchor.	5 / 5
Workflow Clarity	Steps 1-7 are clearly sequenced with explicit checkpoints: status/schema check, blocked vs all_done state handling, per-task pause conditions (unclear, design issue, scope creep, error, interrupt), and a Guardrails checklist providing feedback loops for error recovery, matching the score-5 anchor.	5 / 5
Progressive Disclosure	No bundle directories (references/scripts/assets) exist and the skill is self-contained with well-labeled sections (Steps, Output templates, Guardrails, Fluid Workflow Integration) and no nested references; it scores 4 rather than 5 because at ~180 lines some material (output templates, guardrails) is inlined that could live in separate reference files for a skill this long.	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-formed: third-person voice, concrete domain, and an explicit 'Use when' clause with multiple triggers. Its main limitation is that the action vocabulary is narrow (all variants of 'implement') and trigger overlap with sibling OpenSpec skills is possible.

Suggestions

Broaden the action vocabulary beyond 'implement' variants to signal scope (e.g., 'scaffold, implement, and verify change tasks') so specificity reaches comprehensive coverage.

Disambiguate from sibling skills by narrowing the trigger (e.g., 'Use when starting fresh implementation of an OpenSpec change's tasks' vs. a separate continue skill).

Dimension	Reasoning	Score
Specificity	Quotes 'Implement tasks from an OpenSpec change' — names the domain and one concrete action, but the remaining phrases ('start implementing, continue implementation, work through tasks') are variations of the same action rather than distinct capabilities, matching the score-3 anchor of domain plus 1-2 actions without comprehensive coverage.	3 / 5
Completeness	It explicitly states the 'what' ('Implement tasks from an OpenSpec change') and the 'when' via a concrete 'Use when the user wants to start implementing, continue implementation, or work through tasks' clause with multiple trigger phrases, matching the score-5 anchor for both what and when.	5 / 5
Trigger Term Quality	Natural trigger phrases 'start implementing', 'continue implementation', and 'work through tasks' are phrases a user would plausibly say, giving good coverage; it sits below 5 because common synonyms or concrete noun forms (e.g., 'implement a change', 'build the spec') are not exhaustively covered.	4 / 5
Distinctiveness Conflict Risk	'OpenSpec change' is a distinct niche with clear triggers, but 'continue implementation' overlaps with sibling skills in the OpenSpec family (e.g., a continue-change skill), giving minor overlap risk rather than the minimal-conflict score-5 anchor.	4 / 5
	Total	16 / 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: 6926ccb

Reviewed: about 16 hours 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.